CN114566258B - Planning system for dysarthria correction scheme in autism evaluation object - Google Patents
Planning system for dysarthria correction scheme in autism evaluation object Download PDFInfo
- Publication number
- CN114566258B CN114566258B CN202210056668.2A CN202210056668A CN114566258B CN 114566258 B CN114566258 B CN 114566258B CN 202210056668 A CN202210056668 A CN 202210056668A CN 114566258 B CN114566258 B CN 114566258B
- Authority
- CN
- China
- Prior art keywords
- training
- voice
- database
- pronunciation
- evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 289
- 206010013887 Dysarthria Diseases 0.000 title claims abstract description 84
- 238000012937 correction Methods 0.000 title claims abstract description 23
- 206010003805 Autism Diseases 0.000 title claims abstract description 22
- 208000020706 Autistic disease Diseases 0.000 title claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 271
- 238000000034 method Methods 0.000 claims abstract description 65
- 238000012360 testing method Methods 0.000 claims description 59
- 230000006698 induction Effects 0.000 claims description 27
- 241001672694 Citrus reticulata Species 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 8
- 230000007812 deficiency Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 4
- 238000007596 consolidation process Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 210000001584 soft palate Anatomy 0.000 description 23
- 210000001260 vocal cord Anatomy 0.000 description 23
- 238000010276 construction Methods 0.000 description 12
- 210000003205 muscle Anatomy 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 239000004744 fabric Substances 0.000 description 7
- 230000001737 promoting effect Effects 0.000 description 7
- 239000002023 wood Substances 0.000 description 7
- 210000003928 nasal cavity Anatomy 0.000 description 6
- 241000282326 Felis catus Species 0.000 description 5
- 241000251468 Actinopterygii Species 0.000 description 4
- 241000219109 Citrullus Species 0.000 description 4
- 235000012828 Citrullus lanatus var citroides Nutrition 0.000 description 4
- 240000007594 Oryza sativa Species 0.000 description 4
- 235000007164 Oryza sativa Nutrition 0.000 description 4
- 235000008429 bread Nutrition 0.000 description 4
- 210000004209 hair Anatomy 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 210000001331 nose Anatomy 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 235000009566 rice Nutrition 0.000 description 4
- 208000024891 symptom Diseases 0.000 description 4
- 235000005979 Citrus limon Nutrition 0.000 description 3
- 244000131522 Citrus pyriformis Species 0.000 description 3
- 241000252233 Cyprinus carpio Species 0.000 description 3
- 241000283070 Equus zebra Species 0.000 description 3
- 241000287828 Gallus gallus Species 0.000 description 3
- 241000257303 Hymenoptera Species 0.000 description 3
- 235000008446 instant noodles Nutrition 0.000 description 3
- 238000009774 resonance method Methods 0.000 description 3
- 238000010408 sweeping Methods 0.000 description 3
- 210000003813 thumb Anatomy 0.000 description 3
- 238000005406 washing Methods 0.000 description 3
- 235000001674 Agaricus brunnescens Nutrition 0.000 description 2
- 241000282472 Canis lupus familiaris Species 0.000 description 2
- 229920000742 Cotton Polymers 0.000 description 2
- 244000088415 Raphanus sativus Species 0.000 description 2
- 235000006140 Raphanus sativus var sativus Nutrition 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 208000035475 disorder Diseases 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 210000004709 eyebrow Anatomy 0.000 description 2
- 210000003811 finger Anatomy 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 230000001939 inductive effect Effects 0.000 description 2
- 238000004898 kneading Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 235000012149 noodles Nutrition 0.000 description 2
- 238000005728 strengthening Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 244000291564 Allium cepa Species 0.000 description 1
- 235000010167 Allium cepa var aggregatum Nutrition 0.000 description 1
- 241000252073 Anguilliformes Species 0.000 description 1
- 241000270299 Boa Species 0.000 description 1
- 241000283707 Capra Species 0.000 description 1
- 241000272201 Columbiformes Species 0.000 description 1
- 244000241257 Cucumis melo Species 0.000 description 1
- 235000015510 Cucumis melo subsp melo Nutrition 0.000 description 1
- 244000301850 Cupressus sempervirens Species 0.000 description 1
- 244000000626 Daucus carota Species 0.000 description 1
- 235000002767 Daucus carota Nutrition 0.000 description 1
- 244000061508 Eriobotrya japonica Species 0.000 description 1
- 235000009008 Eriobotrya japonica Nutrition 0.000 description 1
- 235000016623 Fragaria vesca Nutrition 0.000 description 1
- 240000009088 Fragaria x ananassa Species 0.000 description 1
- 235000011363 Fragaria x ananassa Nutrition 0.000 description 1
- 240000005979 Hordeum vulgare Species 0.000 description 1
- 235000007340 Hordeum vulgare Nutrition 0.000 description 1
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000000220 Panda oleosa Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 241000282373 Panthera pardus Species 0.000 description 1
- 235000008331 Pinus X rigitaeda Nutrition 0.000 description 1
- 241000018646 Pinus brutia Species 0.000 description 1
- 235000011613 Pinus brutia Nutrition 0.000 description 1
- 241001105482 Prionoxystus robiniae Species 0.000 description 1
- 206010039101 Rhinorrhoea Diseases 0.000 description 1
- 235000004789 Rosa xanthina Nutrition 0.000 description 1
- 241000109329 Rosa xanthina Species 0.000 description 1
- 244000007853 Sarothamnus scoparius Species 0.000 description 1
- 244000269722 Thea sinensis Species 0.000 description 1
- 244000185386 Thladiantha grosvenorii Species 0.000 description 1
- 235000011171 Thladiantha grosvenorii Nutrition 0.000 description 1
- 241001482311 Trionychidae Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 244000098338 Triticum aestivum Species 0.000 description 1
- 241001147416 Ursus maritimus Species 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- FJJCIZWZNKZHII-UHFFFAOYSA-N [4,6-bis(cyanoamino)-1,3,5-triazin-2-yl]cyanamide Chemical compound N#CNC1=NC(NC#N)=NC(NC#N)=N1 FJJCIZWZNKZHII-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 235000019993 champagne Nutrition 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 235000005822 corn Nutrition 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 235000013312 flour Nutrition 0.000 description 1
- 235000011389 fruit/vegetable juice Nutrition 0.000 description 1
- 239000010437 gem Substances 0.000 description 1
- 229910001751 gemstone Inorganic materials 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 244000144980 herd Species 0.000 description 1
- 235000015243 ice cream Nutrition 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 239000010985 leather Substances 0.000 description 1
- 235000011475 lollipops Nutrition 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 239000008267 milk Substances 0.000 description 1
- 210000004080 milk Anatomy 0.000 description 1
- 235000013336 milk Nutrition 0.000 description 1
- RZSCFTDHFNHMOR-UHFFFAOYSA-N n-(2,4-difluorophenyl)-2-[3-(trifluoromethyl)phenoxy]pyridine-3-carboxamide;1,1-dimethyl-3-(4-propan-2-ylphenyl)urea Chemical compound CC(C)C1=CC=C(NC(=O)N(C)C)C=C1.FC1=CC(F)=CC=C1NC(=O)C1=CC=CN=C1OC1=CC=CC(C(F)(F)F)=C1 RZSCFTDHFNHMOR-UHFFFAOYSA-N 0.000 description 1
- 208000010753 nasal discharge Diseases 0.000 description 1
- 239000002674 ointment Substances 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 231100000241 scar Toxicity 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000002791 soaking Methods 0.000 description 1
- 208000027765 speech disease Diseases 0.000 description 1
- 208000011293 voice disease Diseases 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/01—Assessment or evaluation of speech recognition systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Psychology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Hospice & Palliative Care (AREA)
- Developmental Disabilities (AREA)
- Child & Adolescent Psychology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses a system for planning dysarthria correction schemes in an autism evaluation object, which comprises an input module, an analysis module, a database module and an output module; the input module is used for inputting the voice evaluation data of the evaluation object into the analysis module; the analysis module is used for establishing dysarthria feature codes according to the voice evaluation data, inquiring corresponding database data in the database module according to the dysdysarthria feature codes, and obtaining training schemes corresponding to the dysdysdysarthria feature codes; the database module is used for storing a data table; the data table includes: database initial consonant information table, database gamma-delta coding-strategy chain corresponding table, database training suggestion chain corresponding table and database training method table; the output module is used for outputting the training scheme obtained by the analysis module; the system is used for realizing a method for planning dysarthria correction scheme in an autism evaluation object.
Description
Technical Field
The invention belongs to the technical field of auxiliary training of autism evaluation objects, and relates to a planning system of a traditional Chinese dysarthria correction scheme in an autism evaluation object.
Background
Aiming at various speech dysarthria of autism children, pushing corresponding correction schemes to help basic rehabilitation institutions to improve rehabilitation training efficiency, a set of retrieval tools are developed in a vast voice constructing database, and a convenient channel is established between screening evaluation and training schemes.
The evaluation and investigation of the sound construction and voice ability are that the children master the voice construction and voice ability of each phoneme, a group of Chinese sound construction and voice ability test monosyllabic words are developed for each initial consonant on the basis of the previous study, the sound construction and voice ability of the Mandarin initial consonant and the disorder type thereof are evaluated through a plurality of confusion analysis of the initial consonants, higher efficiency can be obtained in the aspect of measuring the voice errors of patients with the voice disorder, and scientific basis is provided for diagnosing the etiology of the sound construction disorder and formulating an correction scheme.
Disclosure of Invention
In order to solve the defects in the prior art, the invention aims to provide a planning system for a dysarthria correction scheme in an autism evaluation object.
The invention provides a system for planning dysarthria correction schemes in an autism evaluation object, which comprises an acquisition module, an evaluation module, an input module, an analysis module, a database module and an output module;
The acquisition module is used for calling the target sound test words in the database module and acquiring the voice of the evaluation object once or for multiple times;
the evaluation module is used for processing and evaluating the collected voice and obtaining a voice evaluation result; the evaluation result is combined with the month age of the patient and the target sound to form voice evaluation data;
the input module is used for inputting the voice evaluation data of the evaluation object into the analysis module;
the analysis module is used for establishing dysarthria feature codes according to the voice evaluation data, inquiring corresponding database data in the database module according to the dysdysarthria feature codes, and obtaining training schemes corresponding to the dysdysdysarthria feature codes;
the database module is used for storing a data table, wherein the data table comprises a database initial consonant information table, a database gamma-delta coding-strategy chain corresponding table, a database training suggestion chain corresponding table and a database training method table;
the output module is used for outputting the training scheme obtained by the analysis module.
The planning system is executed according to a dysarthria correction scheme planning method in an autism evaluation object, and the planning method comprises the following steps of:
step A, establishing dysarthria feature codes according to voice evaluation data of an evaluation object;
Step B, inquiring corresponding database data according to the dysarthria feature codes to obtain a dysarthria correction training scheme;
and C, outputting the dysarthria correction training scheme.
The obtaining of the evaluation data comprises the steps of:
a1, collecting voice of an evaluation object;
a2, processing and evaluating the acquired voice to obtain an evaluation object voice evaluation result;
step A3: and forming voice evaluation data according to the voice evaluation result and the month age of the evaluation object and the target sound.
In the step A1, the voice of the evaluation object is tested and collected according to a test word list; the test word list is obtained by induction and arrangement according to the Chinese phonetic combination rule in the Chinese phonetic positive word method basic rule.
In step A1, the voice acquisition of the evaluation object is performed by the following steps:
1) Connecting a microphone and an ADC to a computer, wherein the microphone collects the voice of an evaluation object;
2) The ADC equipment samples at the speed of 48000 times per second, each sampling is cascaded through a multistage amplifier and a comparator, analog signals of voice are sampled into level signals with different voltages through an analog-to-digital conversion circuit, and the level signals are connected and transmitted to a computer through a 3.5mm interface or a USB interface and stored as sound files to be analyzed.
In step A2, the processing of the acquired voice includes:
the audio in the sound file is first filtered via the following algorithm:
the state equation of the system: x is x k =φ k,k-1 *x k-1 +Γ k-1 w k-1 ,
Measurement equation of the system: z is Z k =H k *x k +v k ;
Wherein: w (w) k-1 Is process white noise;
x k is the system state at time k;
H k is a parameter of the measurement system;
φ k,k-1 is the state transition moment;
v k for measuring noise;
Γ is the noise driving matrix;
Z k measuring the output of the equation for the system;
with optimal estimate x at time k-1 k-1 Based on the reference, predicting the state change amount at the k momentAt the same time, the state is observed to obtain an observed variable Z k Then analyzing between prediction and observation, or correcting the prediction by using the observed quantity to obtain the optimal state estimation x at k moment k ;
The filtered audio is voice audio with environmental noise removed, and the audio is further analyzed;
framing the filtered voice audio, taking 12000 times of sampling for 0.25 seconds as 1 frame, and slicing the whole section of audio; and searching corresponding combinations in the Chinese phonetic library, wherein the related algorithm is as follows:
let Q be the set of all possible hidden states and V be the set of all possible observed states, namely:
Q={q 1 ,q 2 ,...,q N },V={v 1 ,v 2 ,...v M };
Where N is the number of possible hidden states and M is the number of all possible observed states;
for a sequence with a length of T, I is a state sequence corresponding to the sequence T, and O is an observation sequence corresponding to the sequence T, namely:
I={i 1 ,i 2 ,...,i T },O={o 1 ,o 2 ,...o T };
wherein any one of the hidden states i t E Q, any one of the observation states o t ∈V;
Decomposing the pronunciation of each word of Mandarin Chinese into a plurality of frames, wherein in a Chinese phonetic library, a sequence set containing Q and V of each word is provided; and comparing and searching the input audio slices O and V to find out the corresponding characters.
In step A2, the speech evaluation result includes: positive solution, misinterpretation, loss, confusion; wherein,,
the positive solution refers to the voice evaluation result as follows: the Chinese phonetic alphabet of the single word obtained by the voice recognition of the evaluation object is consistent with the initial consonant and the final of the target sound Chinese phonetic alphabet;
the loss refers to the speech evaluation result being: single word obtained by speech recognition of evaluation objectThe Chinese phonetic alphabet of (2) is consistent with the vowel of the target sound, the initial consonant is not pronounciated, and the evaluation result is usedA representation;
the confusion refers to the speech assessment result being: the Chinese phonetic initial consonant of the single word obtained by the recognition of the voice of the evaluation object is different from the Chinese phonetic initial consonant of the target voice, but is related to the pronunciation mode or the pronunciation part of the Chinese phonetic initial consonant of the target voice; the voice evaluation result is used for evaluating the actual voice record of the object;
The misinterpretation refers to the speech evaluation result that: the speech evaluation result of the evaluation object does not belong to any one of positive solution, loss, confusion, and the speech evaluation result is indicated by "x".
If the evaluation result is misinterpretation or loss, the evaluation object has deficiency to the pronunciation mode and pronunciation part of the initial consonant;
if the evaluation result is confusion, determining the pronunciation mode and the deficiency condition of the pronunciation part of the initial consonant by referring to a confusion sound table;
the evaluation subject pronounces three times at the time of the test, and among the three pronunciations of the patient,
if the three times are positive solutions, pushing and consolidating relevant exercise F in a pushing scheme;
if the pronunciation mode or the pronunciation part is insufficient once in the three tests, the pronunciation of the evaluation object is learned, but is not stable enough, and the targeted exercise and consolidation are needed, and the pushing exercise mode is as follows: d, E and F;
if the pronunciation mode or the pronunciation part is insufficient twice in the three tests, the fact that the sound of the evaluation object is not obtained stably is indicated, the exercise needs to be strengthened, and the pushing exercise mode is as follows: c, D and E;
if the pronunciation mode or the pronunciation position is insufficient in all three tests, the evaluation object is proved to have problems on the pronunciation position and/or the pronunciation mode, and the basic training is carried out on the pronunciation position and/or the pronunciation mode, wherein the pushing training mode is as follows: if only the pronunciation part is insufficient, pushing B, C and D; if the pronunciation mode is insufficient, pushing A, C and D; if the pronunciation part and the pronunciation mode are insufficient, pushing A, B, C and D;
The push schemes for different pronunciation error causes and number of pronunciation errors are shown in table 1 below.
Wherein A is pronunciation position exercise, B is pronunciation mode exercise, C is pronunciation induction exercise, D is phonemic training exercise, E is phonemic contrast exercise, and F is speech enhancement exercise.
TABLE 1 push schemes for different pronunciation error causes and pronunciation error times
Error 0 times | Staggered 1 time | Staggered 2 times | 3 times by mistake | |
Pronunciation part | F | D→E→F | C→D→E | B→C→D |
Pronunciation mode | F | D→E→F | C→D→E | A→C→D |
Both are | F | D→E→F | C→D→E | A→B→C→D |
Wherein, the pronunciation part, the pronunciation mode and both are the reasons of pronunciation errors, and the error times are the error times of 0 times, 1 time, 2 times and 3 times.
α represents the month age of the evaluation subject, α=0-999;
for different initials, there is a corresponding preferred month-old range, for example, for b-tone, a preferred month-old range of 30 or more, and if the month-old of the evaluation target is less than 30, the relevant scheme is not pushed to the evaluation target. The correspondence between the specific initial consonants and the preferred month age zone is shown in table 2.
TABLE 2 correspondence table of different initial consonants and learned preferred month-old segments
the Mandarin Chinese initial consonant comprises: b. m, p, f, d, t, n, l, g, k, h, j, q, x, z, c, s, zh, ch, sh, r;
The beta represents a target sound, namely a target initial consonant for selecting testing from Chinese mandarin initial consonants;
the gamma represents the evaluation result of the voice of the evaluation object and is represented by epsilon, eta, lambda and specific confusion sounds; the epsilon represents that the voice evaluation result of the evaluation object is correct; the eta represents that the evaluation object voice evaluation result is a misinterpretation; the lambda represents that the speech evaluation result of the evaluation object is lost; the specific confusion sounds represent specific confusion sounds related to the pronunciation mode or pronunciation part of the target sound as the evaluation result of the evaluation target voice;
the delta represents the occurrence frequency of the voice evaluation result corresponding to the coding gamma, and the numerical range of the frequency is 1-3.
The method from the voice evaluation result to the establishment of dysarthria feature codes comprises the following steps:
alpha is used for representing the month age of the evaluation object of the test, and 0 is added to the left side to be 3 digits;
The specific initial consonant of the target sound of the test is represented by beta;
using gamma to represent the evaluation result of the speech of the evaluation object of the test;
the delta is used for representing the occurrence times of the voice evaluation result of the evaluation object of the test;
In the data of the database of the data,
database initial consonant table:
each initial consonant has specific attributes, and the initial consonants and the corresponding attributes are summarized into a database initial consonant table in a database; wherein the specific attributes of each initial consonant are respectively as follows: the target sound, the target sound should learn the month age, the target sound detailed information, the target sound type and the single double three syllable test words corresponding to the target sound; each attribute of the initial consonant corresponds to a row of entries in the database;
database gamma-delta encoding-policy chain correspondence table:
for each initial consonant, the codes of the gamma-delta composition are different because of the difference of the evaluation results, and each evaluation result code of each initial consonant is summarized into a database gamma-delta code-strategy chain corresponding table in a database; the database gamma-delta encoding-policy chain correspondence table has the following attributes: gamma-delta coding, target sound, evaluation result major class, confusing sound, error times and strategy chain; each attribute in the database gamma-delta coding-strategy chain corresponding table corresponds to a row of entries in the database;
database training suggestion chain correspondence table:
for each initial consonant, specific codes in the strategy chain have corresponding training suggestion chains, and a database training suggestion chain corresponding table is established; the database training suggestion chain correspondence table includes the following attributes: specific codes, target sounds and training suggestion chains in the strategy chain; each attribute in the database training suggestion chain table corresponds to a row of entries in the database.
Database training method table:
for each training suggestion chain, the training method id in the training suggestion chain has corresponding specific content, and a database training method table is established, wherein the database training method table comprises the following attributes: target sound, method id in training suggestion chain and specific content corresponding to the method id; each attribute in the database training method table corresponds to a column of entries in the database.
When a specific training strategy is obtained through inquiry, firstly, positioning to a database initial consonant table through target sound, and reading the acquired month age of the initial consonant; if the month age of the evaluation object is smaller than the acquired month age of the initial consonant, not pushing the training scheme;
secondly, according to the gamma-delta code of the test, obtaining a strategy chain corresponding to the target sound of the test in a database gamma-delta code-strategy chain corresponding table according to the target sound and the gamma-delta code;
and according to the specific codes in the strategy chain corresponding to the target sound and the target sound, inquiring a database training suggestion chain corresponding table to obtain a training suggestion chain of the specific codes of the strategy chain.
And finally, inquiring a database training method table according to the target sound and the method ids in the training suggestion chain, obtaining the specific content corresponding to each method id, and combining to obtain the complete training scheme of the test.
The beneficial effects of the invention include: the invention provides a system for planning dysarthria correction schemes in an autism evaluation object, which can be used for realizing a method for planning dysdysdysdysarthria correction schemes in the autism evaluation object, and comprises the following steps: step A, establishing dysarthria feature codes according to voice evaluation data of an evaluation object; step B, inquiring corresponding database data according to the dysarthria feature codes to obtain a Chinese dysarthria correction training scheme; and C, outputting the dysarthria correction training scheme. The invention can obtain higher efficiency in the aspect of measuring the speech errors of patients with speech disorder, and provides scientific basis for diagnosing the etiology of dysarthria and making correction schemes.
Drawings
Fig. 1 is a block diagram of a dysarthria planning system according to the present invention.
Fig. 2 is a diagram of basic rules of the Chinese phonetic positive word method in the present invention.
Fig. 3 is a flow chart of a dysarthria planning method according to the present invention.
FIG. 4 is a flow chart of the "initial b" word test in the present invention.
Fig. 5 is a diagram of confusing sounds that may be generated by the "initial consonant b" of the present invention.
Fig. 6 is a schematic diagram of the "initial b" construction voice training strategy of the present invention.
Fig. 7 is a diagram of the "initial b" construction voice rule base of the present invention.
FIG. 8 is a flow chart of the "initial m" single word test in the present invention.
Fig. 9 is a diagram of confusing sounds that may be generated by "initial consonant m" in accordance with the present invention.
FIG. 10 is a schematic representation of the "initial m" construction voice training strategy of the present invention.
FIG. 11 is a diagram of a "initial m" construction voice rule base according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following specific examples and drawings. The procedures, conditions, experimental methods, etc. for carrying out the present invention are common knowledge and common knowledge in the art, except for the following specific references, and the present invention is not particularly limited.
The "initial consonant b" is a double lip non-air feed and a clear stop. Caused by the upper and lower lips touching or approaching, and blocking the air flow.
The "initial consonant m" is the double-lip clouded nasal sound. When sounding, the lips are closed, the soft palate descends, the nasal passages are opened, the vocal cords vibrate, and the air flow is sent out from the nasal passages.
The invention provides a system for planning a traditional Chinese dysarthria correction scheme in an autism patient, which is shown in fig. 1, and comprises an acquisition module, an evaluation module, an input module, an analysis module, a database module and an output module;
the acquisition module is used for calling the target sound test words in the database module and acquiring the voice of the evaluation object once or for multiple times;
The evaluation module is used for processing and evaluating the collected voice and obtaining a voice evaluation result; the evaluation result is combined with the month age of the patient and the target sound to form voice evaluation data;
the input module is used for inputting the voice evaluation data of the evaluation object into the analysis system;
the analysis module is used for establishing dysarthria feature codes according to the voice evaluation data, inquiring corresponding database data in the database module according to the dysdysarthria feature codes, and obtaining training schemes corresponding to the dysdysdysarthria feature codes;
the database module is used for storing a data table; the data table includes: database initial consonant information table, database gamma-delta coding-strategy chain corresponding table, database training suggestion chain corresponding table and database training method table;
the output module is used for outputting the training scheme obtained by the analysis module.
The 4 data tables stored in the database module are shown in tables 3-6, respectively:
table 3 database initial consonant information table
Table 4 database gamma-delta encoding-strategy chain correspondence table
Data sequence number | Data name | Data type | Description of data | Data example |
1 | name | VARchar | Gamma-delta encoding | ε-3 |
2 | phonetic | VARchar | Target sound | b |
3 | genre | VARchar | Evaluation result subclass (positive solution/missolution) | Positive solution |
4 | replacement | VARchar | The method is suitable for confusing what sound is | b |
5 | occurrence | INTEGER | The number of target voice errors | 0 |
6 | chain | VARchar | Policy chain | F |
Table 5 database training advice chain correspondence table
Data sequence number | Data name | Data type | Description of data | Data example |
1 | name | INTEGER | Specific coding in policy chain | F |
2 | phonetic | VARchar | Target sound | b |
3 | genre | VARchar | Training suggestion chain | 11→12→13 |
Table 6 database training method table
The invention also provides a Chinese dysarthria correction scheme planning method, which comprises the following steps:
step A, establishing dysarthria feature codes according to voice evaluation data of an evaluation object;
step B, inquiring corresponding database data according to the dysarthria feature codes to obtain a Chinese dysarthria training scheme;
and step C, pushing the Chinese sound construction training scheme.
The obtaining of the evaluation data comprises the steps of:
a1, collecting voice of an evaluation object;
in the step A1, the voice is tested and collected according to a test word list; the test word list is obtained by summarizing and arranging the Chinese phonetic combination rules in the basic rule of Chinese phonetic positive word method.
A2, processing and evaluating the acquired voice to obtain an evaluation object voice evaluation result;
step A3: and forming voice evaluation data according to the voice evaluation result and the month age of the evaluation object and the target sound.
In step A2, the processing of the acquired voice includes:
the audio in the sound file is first filtered via the following algorithm:
the state equation of the system: x is x k =φ k,k-1 *x k-1 +Γ k-1 w k-1 ,
Measurement equation of the system: z is Z k =H k *x k +v k ;
Wherein: w (w) k-1 Is process white noise;
x k is the system state at time k;
H k is a parameter of the measurement system;
φ k,k-1 is the state transition moment;
v k for measuring noise;
Γ is the noise driving matrix;
Z k measuring the output of the equation for the system;
with optimal estimate x at time k-1 k-1 Based on the prediction of the k timeState change amountAt the same time, the state is observed to obtain an observed variable Z k Correcting the predicted quantity by using the observed quantity to obtain an optimal state estimation x at the moment k k ;
The filtered audio is voice audio with environmental noise removed, and the audio is further analyzed;
framing the filtered voice audio, taking 12000 times of sampling for 0.25 seconds as 1 frame, and slicing the whole section of audio; and searching corresponding combinations in the Chinese phonetic library, wherein the related algorithm is as follows:
let Q be the set of all possible hidden states and V be the set of all possible observed states, namely:
Q={q 1 ,q 2 ,...,q N },V={v 1 ,v 2 ,...v M };
where N is the number of possible hidden states and M is the number of all possible observed states;
For a sequence with a length of T, I is a state sequence corresponding to the sequence T, and O is an observation sequence corresponding to the sequence T, namely:
I={i 1 ,i 2 ,...,i T },O={o 1 ,o 2 ,...o T };
wherein any one of the hidden states i t E Q, any one of the observation states o t ∈V;
Decomposing the pronunciation of each word of Mandarin Chinese into a plurality of frames, wherein in a Chinese phonetic library, a sequence set containing Q and V of each word is provided; and comparing and searching the input audio slice O with the input audio slice V to find out corresponding characters.
In step A2, the speech evaluation result includes: positive solution, misinterpretation, loss, confusion; wherein,,
the positive solution refers to the voice evaluation result as follows: the Chinese phonetic alphabet of the single word obtained by the voice recognition of the evaluation object is consistent with the initial consonant and the final of the target sound Chinese phonetic alphabet;
the loss refers to the speech evaluation result being: the Chinese phonetic alphabet of the single word obtained by the recognition of the voice of the evaluation object is consistent with the vowel of the target voice, the initial consonant is not pronounced, and the evaluation result is usedA representation;
the confusion refers to the speech assessment result being: the Chinese phonetic initial consonant of the single word obtained by the recognition of the voice of the evaluation object is different from the Chinese phonetic initial consonant of the target voice, but is related to the pronunciation mode or the pronunciation part of the Chinese phonetic initial consonant of the target voice; the voice evaluation result is used for evaluating the actual voice record of the object;
The misinterpretation refers to the speech evaluation result that: the speech evaluation result of the evaluation object does not belong to any one of positive solution, loss, confusion, and the speech evaluation result is indicated by "x".
Taking mandarin "initial b" as an example, the test material contains 3 monosyllabic words of "initial b": ba eight, bi pens and bu cloth, each word has a matched picture, and each sound of the evaluation object is required to be transmitted three times. The pronunciation time of the whole syllable and the interval between syllables are about 1 second; in order to induce the self-generated voice, the system can adopt a form of questioning, prompting or imitating, and requires the evaluation object to speak the word expressed by the picture, evaluate the voice of the autism evaluation object to the initial consonant b, and obtain a voice evaluation result;
the three words have no sequence and precedence relationship and can be randomly selected. Such as: when the first eight words are tested, whether the following test is performed or not can be selected according to the capability condition of the evaluation object. If the obstacle feature appears when the first "eight" word is tested, then the first "eight" word is the dominant; if the first "eight" word is correct and the second "pen" word has an obstacle feature, the second "pen" word is subject to; if the first "eight" word and the second "pen" word are correct, and the third "cloth" word presents an obstacle feature, the third "cloth" word is subject to.
Or,
taking mandarin "consonant m" as an example, the test material contains 3 monosyllabic words of "consonant m": ma, mi, mu, each word has a matching picture, requiring three passes per sound of the evaluation object. The pronunciation time of the whole syllable and the interval between syllables are about 1 second; in order to induce the self-generated voice, the system can adopt a form of questioning, prompting or imitating, and requires the evaluation object to speak the word expressed by the picture, evaluate the voice of the autism evaluation object to the initial consonant m, and obtain a voice evaluation result;
the three words have no sequence and precedence relationship and can be randomly selected. Such as: when the first 'mother' word is tested, whether the following test is carried out or not can be selected according to the capability condition of the evaluation object. If the obstacle feature appears when the first "mother" word is tested, then the first "mother" word is the dominant; if the first "m" word is correct and the second "m" word has an obstacle feature, the second "m" word is used as the reference; if the first "mother" word and the second "rice" word are correct, and the third "wood" word has an obstacle feature, the third "wood" word is subject to.
If the evaluation result is misinterpretation or loss, the evaluation object has deficiency to the pronunciation mode and pronunciation part of the initial consonant;
If the evaluation result is confusion, determining the pronunciation mode and the deficiency condition of the pronunciation part of the initial consonant by referring to a confusion sound table;
the evaluation object pronounces three times at the time of the test, and among the three pronunciations of the evaluation object,
if the three times are positive solutions, pushing and consolidating relevant exercise F in a pushing scheme;
if the pronunciation mode or the pronunciation part is insufficient once in the three tests, the pronunciation of the evaluation object is learned, but is not stable enough, and the targeted exercise and consolidation are needed, and the pushing exercise mode is as follows: d, E and F;
if the pronunciation mode or the pronunciation part is insufficient twice in the three tests, the fact that the sound of the evaluation object is not obtained stably is indicated, the exercise needs to be strengthened, and the pushing exercise mode is as follows: c, D and E;
if the pronunciation mode or the pronunciation position is insufficient in all three tests, the evaluation object is proved to have problems on the pronunciation position and/or the pronunciation mode, and the basic training is carried out on the pronunciation position and/or the pronunciation mode, wherein the pushing training mode is as follows: if only the pronunciation part is insufficient, pushing B, C and D; if the pronunciation mode is insufficient, pushing A, C and D; if the pronunciation part and the pronunciation mode are insufficient, pushing A, B, C and D;
After the voice of the autism evaluation object is obtained, the planning system records the voice of the patient, selects to analyze and evaluate the voice, and records the evaluation results as positive solution, misinterpretation 'X', omissionConfusion: real pronunciation;
the following table 7 is an "initial b" phoneme acquisition evaluation record table:
table 7 "initial b" phoneme obtainment evaluation record table
Taking an "eight" tone as an example, the flow of the speech evaluation result acquisition is shown in fig. 4.
According to the evaluation result of the system on the sound construction condition, the autism evaluation object may form a voice confusion phenomenon of two dimensions on the sound production part or the sound production mode when producing sound; wherein, since the b-tone is double-lip, the autism evaluation object may form pronunciation part confusion on the pronunciation part, forming tongue tip middle tone d or tongue root tone g; meanwhile, since the b sound is a non-air-feed stop sound, the sound producing method is confused, and an air-feed stop sound p, a nose sound m or a wipe sound f is formed, as shown in fig. 5.
The following table 8 is an "initial m" phoneme acquisition evaluation record table:
table 8 "initial m" phonemes acquisition evaluation record table
Taking the "mother" sound as an example, the flow of the voice evaluation result acquisition is shown in fig. 8.
According to the evaluation result of the system on the sound construction condition, the autism evaluation object may form a voice confusion phenomenon of two dimensions on the sound production part or the sound production mode when producing sound; the m and b sounds are the same but the sounds are different, and the m sound is a voiced sound and the b sound is a stop sound without air supply, so that the sounds are mixed as shown in fig. 9.
Table 9 confusing sound table of initial consonants b, m
Initial consonant | Confusion sound (pronunciation mode) | Confusion sound (pronunciation part) | Confusion sound (others) |
b | m,p | d,g | f |
m | b |
α represents the month age of the evaluation subject, α=0-999; if the month age represented by alpha is less than 3 bits, 0 is added to the left side to be 3 bits;
the Mandarin Chinese initial consonant comprises: b. m, p, f, d, t, n, l, g, k, h, j, q, x, z, c, s, zh, ch, sh, r;
the beta represents a target sound, namely a target initial consonant for selecting testing from Chinese mandarin initial consonants;
the gamma represents the evaluation result of the voice of the evaluation object and is represented by epsilon, eta, lambda and specific confusion sounds; the epsilon represents that the voice evaluation result of the evaluation object is correct; the eta represents that the evaluation object voice evaluation result is a misinterpretation; the lambda represents that the speech evaluation result of the evaluation object is lost; the specific confusion sounds represent specific confusion sounds related to the pronunciation mode or pronunciation part of the target sound as the evaluation result of the evaluation target voice;
the delta represents the occurrence frequency of the voice evaluation result corresponding to the coding gamma, and the numerical range of the frequency is 1-3.
Examples: there is a half child 2 years old whose initial b is evaluated to let him read "eight" and he see an alternative, and read "horse" in two passes, the symptoms are encoded as:
examples: there is a half child 3 years old whose initial consonant m is evaluated to allow him to read "mother" and he to read "hair" three times with the following symptoms:
step B, inquiring corresponding database data according to the dysarthria feature codes to obtain a dysarthria correction training scheme;
1) Examples of "initial consonant b
Taking the mandarin "initial consonant b" as an example, establishing a complete "initial consonant b" obstacle training scheme database according to the voice evaluation result of the "initial consonant b" and the established dysarthria feature codes; the basic flow of the training scheme obtained by the voice evaluation result and the established dysarthria feature codes is shown in figure 3.
The different dysarthria feature codes were analyzed according to the basic flow in fig. 3 to form a training protocol table, as shown in table 10 below:
table 10 initial b-structure dysarthria characteristic code and training strategy code corresponding table
The training scheme in table 10 may be represented as a rule base graph as in fig. 7.
In fig. 7, there are 6 training targets, including: a pronunciation part exercise (oral movement), B pronunciation mode exercise (oral movement), C pronunciation induction exercise, D phoneme training exercise, E phoneme contrast exercise and F voice strengthening exercise.
As can be seen from table 10, the training regimen table includes 22 cases in total, involving a training strategy divided into three layers:
first layer training strategy: type I-type VII, each type consisting of a number of training strategy codes in a training chain;
second layer training strategy: training strategy codes A, B, C, D, E, F, each consisting of a number of specific training suggestions;
third layer training strategy: training methods 1-13, each specific training suggestion chain contains rich and specific training methods.
The three-layer training strategy described above is shown in table 11 below:
TABLE 11 initial b three-layer training strategy table
A. B, C, D, E, F six targets and corresponding specific training strategies are as follows:
target a: pronunciation part exercise (oral movement)
1. Resistance method: is used for improving the strength of the labial muscle. The therapist sits face-to-face with the patient. The therapist pushes the upper lip of the patient upwards with the tongue depressor, so that the patient resists downwards with force, and the process is repeated for a plurality of times. The therapist then pushes down on the patient's lower lip with the tongue depressor, allowing the patient to resist upward force, repeated several times.
2. A butt kneading method: for increasing the strength of the labial muscle. The therapist sits face-to-face with the patient. The therapist puts the thumb and the index finger on two sides of the patient's person respectively, gently pinch them, and stretch them forward, and at the same time, requires the patient to perform smiling action, and repeat for several times. Note that with a smile of the lips, the smile cannot be done with the back of the head.
3. Sounding kiss: the lips were closed and then separated, and a kissing sound was made, repeated several times.
4. Clamping the tongue depressor: the tongue depressor was clamped with the lips and held for 5 seconds, repeated several times.
Target B: pronunciation mode exercise (oral movement)
5. (if b is confused with m), oral resonance and nasal training can be reduced to correct nasal hyperfunction. Carrying out oral resonance training by using the monosyllabic words of 'fish and puff' and the clothes and adobe; the following words are read aloud while the vowel portion in each word is lengthened: aunt, sister, grandpa, knowledge, watermelon, chicken, carp, flower, tooth, mouth, running, sweeping, watering flowers, and washing clothes.
5. (other if b-tone confusion is p, g, f, d), b-pronunciation mode learning: the lips are tightly closed to form a blockage, and a small amount of air flow breaks through the blockage of the lips to produce sound;
Target C: pronunciation inducing exercise
6. b pronunciation induction: the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
target D: phonemic training exercises
7. Monosyllabic words:
a: 8. white, clasped, leopard, spot, bind, back, run, bounce.
i: pen, soft-shelled turtle, watch, plait, ice.
u: cloth, neck.
8. Double syllable words:
double syllables (front):
a: dad, bus, swing, white paper, newspaper, precious stone, zebra, wrench, shell, vest, bandage.
i: gecko, nose, javelin, hotel, plait, bat, villa, pin.
u: walking, wave.
Double syllables (post):
a: broom, pine and cypress, bread, schoolbag, castle, blackboard, picture book, water pump, wing, shoulder, ice lolly and teacup.
i: pencils, walls, tatamis, watches, champagnes, long whips, soldiers.
u: arm, running.
9. Three syllable words:
trisyllabic (front):
a: ballet, white radish, storm, bowling ball, safe, office, polar bear, baby-backed, shoelace tie.
i: magic and ice cream.
u: glass, unpleasant.
Trisyllabic (middle):
a: baby, hundred years old, stool, baseball, quilt, and jumping.
i: nasal discharge, pencil box, clock store, firecracker and refrigerator.
u: long neck and big steps.
Trisyllabic (post):
a: dam, hail down, floor drag, teeterboard, light and honor board, gold prize cup, notebook.
i: watercolor pencils, darts, road sides and shallot oil cakes.
u: carrot.
Target E: phonemic contrast exercise
10 (m), b-m: bag/cat, father/curse, cloth/wood, board/full, braid/face.
10 (p), b-p: white/card, carry/climb, neck/salve, bag/throw, nose/skin.
10 (d), b-d: newspaper/theft, fort/island, father/big, eight/lap, nose/flute.
10 (g), b-g: pack/cake, plate/driver, bind/harbor, run/root, complement/bone.
10 (f), b-f: quilt/lung, cloth/father, father/hair, neck/Buddha, and mix/meal.
Target F: speech enhancement exercise
11. b, repeating voice:
baby carrying schoolbag, dad pulling radish, berber and dad holding hand, wherein the back of Berber carries watermelon and white pen in the knapsack of wave.
12. b, voice switching: the sister likes zebra, the bust is beside the sister, the cotton quilt is covered with bread and the writing brush is beside the wood stick.
Bai Ping the loquat is peeled off, firecrackers are exploded, and the artillery is running, and the coach has a whip, a stopwatch and a leather bag.
The father has no white hair, the burden of the white hair person, the chalk is beside the dart, and the canvas shoes are placed under the dart.
The sheet has spots, the stool is arranged on the floor, the handle is arranged on the floor, and the large knife scar is arranged on the face.
The watch is eating the ice sucker, the white pigeon is near the eight-Ge, the office is provided with a pen, and the wall is provided with a stick.
13. b, voice rotation: dad buys puff, mom is soaking instant noodles, spot dogs are rolling, and girls wear white gowns.
2) "initial consonant m" as an example "
Taking the mandarin "initial consonant m" as an example, establishing a complete "initial consonant m" obstacle training scheme database according to the evaluation result of the "initial consonant m" and the established dysarthria feature codes; the subsequent training of the initial m-phonemes can be used for improving the initial phonemes accuracy and the voice confusion accuracy, and the basic flow of the training scheme obtained by the evaluation result and the established dysarthria feature codes is shown in figure 3.
The different dysarthria feature codes were analyzed according to the basic flow in fig. 3 to form a training protocol table, as shown in table 12 below:
table 12 initial consonant m-structure dysarthria characteristic code and training strategy code corresponding table
The training schemes in table 12 may be represented as rule base graphs as in fig. 11.
In fig. 11, there are 6 training targets, including: a pronunciation part exercise (oral movement), B pronunciation mode exercise (oral movement), C pronunciation induction exercise, D phoneme training exercise, E phoneme contrast exercise and F voice strengthening exercise.
As can be seen from table 12, the training regimen table includes a total of 10 cases, involving a training strategy divided into three layers:
first layer training strategy: type I-type IV, each type is composed of a plurality of training strategy codes in a training chain;
second layer training strategy: training strategy codes A, B, C, D, E, F, each consisting of a number of specific training suggestions;
third layer training strategy: training methods 1-13, each specific training suggestion chain contains rich and specific training methods.
The three-layer training strategy described above is shown in table 13 below:
TABLE 13 initial m three-layer training strategy table
A. B, C, D, E, F six targets and corresponding specific training strategies are as follows:
target a: pronunciation part exercise (oral movement)
1. Resistance method: is used for improving the strength of the labial muscle. The therapist sits face-to-face with the patient. The therapist pushes the upper lip of the patient upwards with the tongue depressor, so that the patient resists downwards with force, and the process is repeated for a plurality of times. The therapist then pushes down on the patient's lower lip with the tongue depressor, allowing the patient to resist upward force, repeated several times.
2. A butt kneading method: for increasing the strength of the labial muscle. The therapist sits face-to-face with the patient. The therapist puts the thumb and the index finger on two sides of the patient's person respectively, gently pinch them, and stretch them forward, and at the same time, requires the patient to perform smiling action, and repeat for several times. Note that with a smile of the lips, the smile cannot be done with the back of the head.
3. Sounding kiss: the lips were closed and then separated, and a kissing sound was made, repeated several times.
4. Clamping the tongue depressor: the tongue depressor was clamped with the lips and held for 5 seconds, repeated several times.
Target B: pronunciation mode exercise (oral movement)
5. Can adopt an oral resonance method and reduce nasal tone training to correct nasal tone hyperfunction. Carrying out oral resonance training by using the monosyllabic words of 'fish and puff' and the clothes and adobe; the following words are read aloud while the vowel portion in each word is lengthened: aunt, sister, grandpa, knowledge, watermelon, chicken, carp, flower, tooth, mouth, running, sweeping, watering flowers, and washing clothes.
Target C: pronunciation inducing exercise
6. m pronunciation induction: the lips are tightly closed, the soft palate descends, a nasal cavity channel is opened, the vocal cords vibrate, and air flow is sent out from the nasal cavity;
target D: phonemic training exercises
7. Monosyllabic words:
a: mother, horse, buy, cat, coal, full, door, busy, dream;
i: rice, bazao, meow, flour;
u: touch, wood, mound;
8. double syllable words:
double syllables (front):
a: ants, wheat, towels, hats, roses, jogging, eels, bolts, boas.
i: rice, bees, stopwatches, agility, bread, and lists.
u: mushrooms, trojans.
Double syllables (post):
a: mom, mountain, eyebrow, strawberry, romantic, gate, lemon, and glabrous.
i: corn, blow out, temple, peasant, stretched noodles, signature.
u: stroking, building blocks, letters, eyes.
9. Three syllable words:
trisyllabic (front):
a: microphone, owl, sweater, mermaid, cartoon book, door handle.
i: camouflage clothes, cast, cat, baker, postcard.
u: motorcycle and shepherd.
Trisyllabic (middle):
a: small ants, barley tea, carpenterworm, sweater, eyebrow, full, goats, guide dogs, lemon juice.
i: hami melon, sketch, facial mask, and sandwich.
u: flower mushrooms, thumb, cabin.
Trisyllabic (post):
a: momordica grosvenori, buying and selling, pandas, small flower cat, sister, slow walking, looking at the gate, and white in the daytime dream.
i: nectar, sixty seconds, instant noodles and intelligence.
u: building blocks are put up in desert.
Target E: phonemic contrast exercise
10 (b), m-b: bag/cat, father/curse, cloth/wood, board/full, braid/face.
Target F: speech enhancement exercise
11. m voice repetition:
the mother touches the kittens, the kittens are called, the sister does not have towels, the mother touches the clear face, the clear noodles do not have rice.
12. m voice switching: the sister likes zebra, the bust is beside the sister, the cotton quilt is covered with bread and the writing brush is beside the wood stick.
13. m voice rotation: dad buys puff, mom buys lemon on instant noodles, and the herd drinks mare milk.
Example 1
For example, 22 autism evaluation subjects in the following table are evaluated for their initial consonant b, let them follow "eight", evaluate the sound-constructing ability and plan the corresponding training advice:
evaluation object 1: the pronunciation is correct, the three times are read as eight, and the dysarthria feature codes are obtained according to the evaluation result and other data:
111, scheme push: type I (F)
Namely, three times of pronunciation are correct, the type of the pushed training strategy is type I, the training strategy is encoded as F according to a three-layer training strategy table, and specific training suggestions are performed according to the following sequence:
speech repetition (11)
Speech switching (12)
Voice alternate (13)
The target sound of the patient in the test is b, b is positioned in the initial consonant table, the acquired month age of the read initial consonant is 30, and 30 is less than 92, so that the training advice is normally pushed.
And secondly, according to 1-3 of the test, obtaining a strategy chain F corresponding to the test in a coding table according to the target sound b and the codes 1-3.
And inquiring a strategy chain table according to the tested target sound b and the strategy chain F, and obtaining the strategy corresponding to the test from 11 to 12 to 13 in the strategy chain table.
And finally, inquiring a strategy table according to the target sound b and the strategies 11,12 and 13 to obtain a specific training scheme of the test.
000, scheme push: type II (A→B→C→D)
Namely, three times of pronunciation are omitted, the type of the pushed training strategy is type II, the training strategy codes are A, B, C and D, and specific training suggestions are performed according to the following sequence:
pronunciation part learning: improving the double-lip muscle strength-resistance method (1) and the opposite pinching method (2); promoting double-lip closing-sounding kissing (3) and clamping the tongue depressor (4);
b pronunciation mode learning (5): the lips are tightly closed to form a blockage, and a small amount of air flow breaks through the blockage of the lips to produce sound;
b pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: monosyllabic word (7), double syllable word (8), trisyllabic word (9)
Evaluation object 3: with two-pass pronunciation omission, the dysarthria characteristics are obtained according to the evaluation result and other data Encoded as
001/010/100, scheme push: type III (C→D→E)
Namely, three-pass pronunciation has two-pass pronunciation omission, the type of the pushed training strategy is type III, the training strategy codes are C- & gt D- & gt E, and specific training suggestions are performed according to the following sequence:
b pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-m, b-p, b-d, b-g, b-f (10);
evaluation object 4: with one pass of pronunciation omission, the dysarthria characteristic codes are obtained according to the evaluation result and other data
011/101/110, scheme push: type IV (D→E→F)
Namely, three-pass pronunciation has one-pass pronunciation omission, the type of the pushed training strategy is type IV according to a three-layer training strategy table, the training strategy codes are D- & gt E- & gt F, and specific training suggestions are performed according to the following sequence:
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-m, b-p, b-d, b-g, b-f (10);
speech training: voice repetition (11), voice switching (12), voice rotation (13);
Evaluation object 5: three-pass pronunciation misinterpretation, and according to the evaluation result and other data, obtaining dysarthria characteristic codes as
000, scheme push: type II (A→B→C→D)
The three-pass pronunciation equalization solution is carried out, the type of the pushed training strategy is II, the training strategy codes are A, B, C and D, and the specific training suggestions are carried out according to the following sequence:
pronunciation part learning: improving the double-lip muscle strength-resistance method (1) and the opposite pinching method (2); promoting double-lip closing-sounding kissing (3) and clamping the tongue depressor (4);
b pronunciation mode learning (5): the lips are tightly closed to form a blockage, and a small amount of air flow breaks through the blockage of the lips to produce sound;
b pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: monosyllabic word (7), double syllable word (8), trisyllabic word (9)
Evaluation object 6: two-pass pronunciation misinterpretation, according to the evaluation result and other data, obtaining dysarthria characteristic codes as
001/010/100, scheme push: type III (C→D→E)
The three-pass pronunciation has two-pass pronunciation misinterpretation, the type of the pushed training strategy is type III, the training strategy codes are C- & gt D- & gt E, and specific training suggestions are performed according to the following sequence:
B pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-m, b-p, b-d, b-g, b-f (10);
evaluation object 7: one-pass pronunciation misinterpretation, and obtaining dysarthria characteristic codes as according to the evaluation result and other data
011/101/110, scheme push: type IV (D→E→F)
Namely, three-pass pronunciation has one-pass pronunciation misinterpretation, the type of the pushed training strategy is type IV according to a three-layer training strategy table, the training strategy codes are D- & gt E- & gt F, and specific training suggestions are performed according to the following sequence:
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-m, b-p, b-d, b-g, b-f (10);
speech training: voice repetition (11), voice switching (12), voice rotation (13);
evaluation object 8: the three-pass pronunciation confusion is m-pronunciation, and the dysarthria characteristic codes are obtained according to the evaluation result and other data
000, scheme push: type V (B→C→D)
Namely, three-pass pronunciation is mixed into m tones, the type of the pushed training strategy is the type V, the training strategy codes are B- & gt C- & gt D according to a three-layer training strategy table, and specific training suggestions are performed according to the following sequence:
B pronunciation mode learning (5 m): can adopt an oral resonance method and reduce nasal tone training to correct nasal tone hyperfunction. Carrying out oral resonance training by using the monosyllabic words of 'fish and puff' and the clothes and adobe; the following words are read aloud while the vowel portion in each word is lengthened: aunt, sister, grandpa, knowledge, watermelon, chicken, carp, flower, tooth, mouth, running, sweeping, watering flowers, and washing clothes.
B pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: monosyllabic word (7), double syllable word (8), trisyllabic word (9)
Evaluation object 9: the two-pass pronunciation confusion is m-pronunciation, and the dysarthria characteristic codes are obtained according to the evaluation result and other data
001/010/100, scheme push: type III (C→D→E)
Namely, in three-pass pronunciation, two-pass confusion is m-tone, the type of the pushed training strategy is type III, the training strategy codes are C-D-E according to a three-layer training strategy table, and specific training suggestions are performed according to the following sequence:
b pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
Phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-m (10);
evaluation object 10: the one-pass pronunciation confusion is m-pronunciation, and the dysarthria characteristic codes are obtained according to the evaluation result and other data
011/101/110, scheme push: type IV (D→E→F)
Namely m tones are mixed in one pass of three passes of pronunciation, the type of the pushed training strategy is type IV according to a three-layer training strategy table, the training strategy codes are D-E-F, and specific training suggestions are performed according to the following sequence:
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-m (10);
speech training: voice repetition (11), voice switching (12), voice rotation (13);
evaluation object 11: the three-pass pronunciation is mixed into p-tone, and the dysarthria characteristic code is obtained according to the evaluation result and other data
000, scheme push: type V (B→C→D)
Namely, the three-pass pronunciation is mixed into p-tone, the type of the pushed training strategy is the type V, the training strategy codes are B-C-D according to the three-layer training strategy table, and the specific training suggestions are carried out according to the following sequence:
b pronunciation mode learning (5 dpfg): the lips are tightly closed to form a blockage, and a small amount of air flow breaks through the blockage of the lips to produce sound;
B pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: monosyllabic word (7), double syllable word (8), trisyllabic word (9)
Evaluation object 12: the two-pass pronunciation is mixed into p-tone, and the dysarthria characteristic code is obtained according to the evaluation result and other data
001/010/100, scheme push: type III (C→D→E)
Namely, in three-pass pronunciation, two passes are confused into p-tone, the type of the pushed training strategy is type III according to a three-layer training strategy table, the training strategy codes are C-D-E, and specific training suggestions are performed according to the following sequence:
b pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-p (10);
evaluation object 13: the one-pass pronunciation is mixed into p-tone, and the dysarthria characteristic code is obtained according to the evaluation result and other data
011/101/110, scheme push: type IV (D→E→F)
Namely, in three pronunciations, one of the three pronunciations is confused into p-tone, the type of the training strategy pushed is type IV according to a three-layer training strategy table, the training strategy codes are D-E-F, and specific training suggestions are performed according to the following sequence:
Phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-p (10);
speech training: voice repetition (11), voice switching (12), voice rotation (13);
evaluation object 14: the three-pass pronunciation is mixed into d sound, and the dysarthria characteristic code is obtained according to the evaluation result and other data
000, scheme push: type VI (A→C→D)
Namely D sound is mixed in three-pass pronunciation, the type of the pushed training strategy is type VI according to a three-layer training strategy table, the training strategy codes are A, C and D, and specific training suggestions are carried out according to the following sequence:
pronunciation part learning: improving the double-lip muscle strength-resistance method (1) and the opposite pinching method (2); promoting double-lip closing-sounding kissing (3) and clamping the tongue depressor (4);
b pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
evaluation object 15: the two-pass pronunciation is mixed into d sound, and the dysarthria characteristic code is obtained according to the evaluation result and other data
001/010/100, scheme push: type III (C→D→E)
Namely, in three-pass pronunciation, two-pass confusion is D sound, the type of the pushed training strategy is type III, the training strategy codes are C-D-E according to a three-layer training strategy table, and specific training suggestions are performed according to the following sequence:
B pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-d (10);
evaluation object 16: the one-pass pronunciation confusion is d-pronunciation, and the dysarthria characteristic codes are obtained according to the evaluation result and other data
011/101/110, scheme push: type IV (D→E→F)
Namely, in three pronunciations, one of the three pronunciations is confused, the type of the pushed training strategy is type IV according to a three-layer training strategy table, the training strategy codes are D, E and F, and specific training suggestions are performed according to the following sequence:
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-d (10);
speech training: speech repetition (11), speech switching (12), speech rotation (13)
Evaluation object 17: the three-pass pronunciation confusion is g-tone, and the dysarthria characteristic code is obtained according to the evaluation result and other data
000, scheme push: type VI (A→C→D)
Namely, the confusion in three pronunciations is g-tone, the type of the pushed training strategy is type VI according to a three-layer training strategy table, the training strategy codes are A, C and D, and specific training suggestions are carried out according to the following sequence:
Pronunciation part learning: improving the double-lip muscle strength-resistance method (1) and the opposite pinching method (2); promoting double-lip closing-sounding kissing (3) and clamping the tongue depressor (4);
b pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
evaluation object 18: the confusion of the two-pass pronunciation is g-tone, and the dysarthria characteristic code is obtained according to the evaluation result and other data
001/010/100, scheme push: type III (C→D→E)
Namely, in three-pass pronunciation, two-pass confusion is g-tone, the type of the pushed training strategy is type III, the training strategy codes are C-D-E according to a three-layer training strategy table, and specific training suggestions are performed according to the following sequence:
b pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-g (10);
evaluation object 19: the one-pass pronunciation confusion is g-tone, and the dysarthria characteristic codes are obtained according to the evaluation result and other data />
011/101/110, scheme push: type IV (D→E→F)
Namely, in three pronunciations, one of the three pronunciations is confused into g, the type of the pushed training strategy is type IV according to a three-layer training strategy table, the training strategy codes are D-E-F, and specific training suggestions are performed according to the following sequence:
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-g (10);
speech training: speech repetition (11), speech switching (12), speech rotation (13)
Evaluation object 20: the three-pass pronunciation is mixed into f-sound, and the dysarthria characteristic code is obtained according to the evaluation result and other data
000, scheme push: type II (A→B→C→D)
Namely, in three pronunciations, one of the three pronunciations is confused as f-tone, the type of the pushed training strategy is type II, the training strategy codes are A, B, C and D, and the specific training suggestions are carried out according to the following sequence:
pronunciation part learning: improving the double-lip muscle strength-resistance method (1) and the opposite pinching method (2); promoting double-lip closing-sounding kissing (3) and clamping the tongue depressor (4);
b pronunciation mode learning (5 dpfg): the lips are tightly closed to form a blockage, and a small amount of air flow breaks through the blockage of the lips to produce sound;
b pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
Phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
evaluation object 21: the two-pass pronunciation is mixed into f-sound, and the dysarthria characteristic code is obtained according to the evaluation result and other data
001/010/100, scheme push: type III (C→D→E)
Namely, in three-pass pronunciation, two-pass confusion is f-tone, the type of the pushed training strategy is type III, the training strategy codes are C-D-E according to a three-layer training strategy table, and specific training suggestions are performed according to the following sequence:
b pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-f (10);
evaluation object 22: the one-pass pronunciation confusion is f-sound, and the dysarthria characteristic codes are obtained according to the evaluation result and other data
011/101/110, scheme push: type IV (D→E→F)
Namely, in three pronunciations, one of the three pronunciations is confused into F-tone, the type of the pushed training strategy is type IV according to a three-layer training strategy table, the training strategy codes are D-E-F, and specific training suggestions are performed according to the following sequence:
Phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: b-f (10);
and (3) voice training: speech repetition (11), speech switching (12), speech rotation (13).
Example 2
For example, 10 autism evaluation subjects in the following table are used for evaluating the initial consonant m, allowing the initial consonant m to follow the "mother", evaluating the sound-constructing ability and planning corresponding training advice:
evaluation object 1: the pronunciation is correct, the three times are read as 'mother', and the dysarthria characteristic codes are obtained according to the evaluation result and other data:
111, scheme push: type I (F)
Namely, three times of pronunciation are correct, the type of the pushed training strategy is type I, the training strategy is encoded as F according to a three-layer training strategy table, and specific training suggestions are performed according to the following sequence:
speech repetition (11)
Speech switching (12)
Voice alternate (13)
The target sound of the test of the evaluation object is m, m is positioned in the initial consonant table, the acquired month age of the read initial consonant is 30, 30 is less than 92, and therefore the training suggestion is normally pushed.
And secondly, according to 1-3 of the test, obtaining a strategy chain F corresponding to the test in a coding table according to the target sound m and the codes 1-3.
And inquiring a strategy chain table according to the tested target sound m and the strategy chain F, and obtaining the strategy corresponding to the test from 11 to 12 to 13 in the strategy chain table.
And finally, inquiring a strategy table according to the target sound m and the strategies 11,12 and 13 to obtain a specific training scheme of the test.
Evaluation object 2: if three pronunciations of the evaluation object are omitted, the symptom codes are as follows:
000, scheme push: type II (A→B→C→D)
Namely, three times of pronunciation are omitted, the type of the pushed training strategy is type II, the training strategy codes are A, B, C and D, and specific training suggestions are performed according to the following sequence:
pronunciation part learning: improving the double-lip muscle strength-resistance method (1) and the opposite pinching method (2); promoting double-lip closing-sounding kissing (3) and clamping the tongue depressor (4);
m pronunciation mode learning (5): the lips are tightly closed to form a blockage, and a small amount of air flow breaks through the blockage of the lips to produce sound;
m pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: monosyllabic word (7), double syllable word (8), trisyllabic word (9)
Evaluation object 3: the two-pass pronunciation omission is generated, and the dysarthria characteristic codes are obtained according to the evaluation result and other data/>
001/010/100, scheme push: type III (C→D→E)
Namely, three-pass pronunciation has two-pass pronunciation omission, the type of the pushed training strategy is type III, the training strategy codes are C- & gt D- & gt E, and specific training suggestions are performed according to the following sequence:
M pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: m-b (10);
evaluation object 4: with one pass of pronunciation omission, the dysarthria characteristic codes are obtained according to the evaluation result and other data
011/101/110, scheme push: type IV (D→E→F)
Namely, three-pass pronunciation has one-pass pronunciation omission, the type of the pushed training strategy is type IV according to a three-layer training strategy table, the training strategy codes are D- & gt E- & gt F, and specific training suggestions are performed according to the following sequence:
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: m-b (10);
speech training: voice repetition (11), voice switching (12), voice rotation (13);
evaluation object 5: three-pass pronunciation misinterpretation, and according to the evaluation result and other data, obtaining dysarthria characteristic codes as
000, scheme push: type II (A→B→C→D)
The three-pass pronunciation equalization solution is carried out, the type of the pushed training strategy is II, the training strategy codes are A, B, C and D, and the specific training suggestions are carried out according to the following sequence:
Pronunciation part learning: improving the double-lip muscle strength-resistance method (1) and the opposite pinching method (2); promoting double-lip closing-sounding kissing (3) and clamping the tongue depressor (4);
m pronunciation mode learning (5): the lips are tightly closed to form a blockage, and a small amount of air flow breaks through the blockage of the lips to produce sound;
m pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: monosyllabic word (7), double syllable word (8), trisyllabic word (9)
Evaluation object 6: two-pass pronunciation misinterpretation, according to the evaluation result and other data, obtaining dysarthria characteristic codes as
001/010/100, scheme push: type III (C→D→E)
The three-pass pronunciation has two-pass pronunciation misinterpretation, the type of the pushed training strategy is type III, the training strategy codes are C- & gt D- & gt E, and specific training suggestions are performed according to the following sequence:
m pronunciation induction (6): the double lips are tightly closed, the soft palate is lifted to block the nasal passages, the air flow breaks through the blockage of the double lips, the vocal cords do not vibrate, and the air flow is weaker;
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: m-b (10);
evaluation object 7: one-pass pronunciation misinterpretation, and obtaining dysarthria characteristic codes as according to the evaluation result and other data
011/101/110, scheme push: type IV (D→E→F)
Namely, three-pass pronunciation has one-pass pronunciation misinterpretation, the type of the pushed training strategy is type IV according to a three-layer training strategy table, the training strategy codes are D- & gt E- & gt F, and specific training suggestions are performed according to the following sequence:
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: m-b (10);
and (3) voice training: voice repetition (11), voice switching (12), voice rotation (13);
evaluation object 8: the three-pass pronunciation is mixed into b sound, and the dysarthria characteristic code is obtained according to the evaluation result and other data
000, scheme push: type V (B→C→D)
Namely, three-pass pronunciation is mixed into B-tone, the type of the pushed training strategy is the type V, the training strategy codes are B- & gt C- & gt D according to a three-layer training strategy table, and specific training suggestions are performed according to the following sequence:
m pronunciation mode learning (5 m): an oral resonance method may be employed. Carrying out oral resonance training by using the monosyllabic words of 'fish and puff' and the clothes and adobe;
b pronunciation induction (6): the lips are tightly closed, the soft palate descends, a nasal cavity channel is opened, the vocal cords vibrate, and air flow is sent out from the nasal cavity;
phoneme learning: monosyllabic word (7), double syllable word (8), trisyllabic word (9)
Evaluation object 9: the secondary pronunciation confusion is b sound, and the dysarthria characteristic codes are obtained according to the evaluation result and other data
001/010/100, scheme push: type III (C→D→E)
Namely, in three-pass pronunciation, two-pass confusion is b sound, the type of the pushed training strategy is type III, the training strategy codes are C-D-E according to a three-layer training strategy table, and specific training suggestions are performed according to the following sequence:
b pronunciation induction (6): the lips are tightly closed, the soft palate descends, a nasal cavity channel is opened, the vocal cords vibrate, and air flow is sent out from the nasal cavity;
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: m-b (10);
evaluation object 10: the one-pass pronunciation confusion is b-tone, and the dysarthria characteristic codes are obtained according to the evaluation result and other data
011/101/110, scheme push: type IV (D→E→F)
Namely, in three pronunciations, one of the three pronunciations is confused into b-tone, the type of the pushed training strategy is type IV according to a three-layer training strategy table, the training strategy codes are D-E-F, and specific training suggestions are performed according to the following sequence:
phoneme learning: a monosyllabic word (7), a double syllable word (8) and a trisyllabic word (9);
speech confusion: m-b (10);
And (3) voice training: speech repetition (11), speech switching (12), speech rotation (13).
The protection of the present invention is not limited to the above embodiments. Variations and advantages that would occur to one skilled in the art are included within the invention without departing from the spirit and scope of the inventive concept, and the scope of the invention is defined by the appended claims.
Claims (5)
1. The system is characterized by comprising an input module, an analysis module, a database module, an output module, an acquisition module and an evaluation module;
the input module is used for inputting the voice evaluation data of the evaluation object into the analysis module;
the analysis module is used for establishing dysarthria feature codes according to the voice evaluation data, inquiring corresponding database data in the database module according to the dysdysarthria feature codes, and obtaining training schemes corresponding to the dysdysdysarthria feature codes;
the database module is used for storing a data table; the data table includes: database initial consonant information table, database gamma-delta coding-strategy chain corresponding table, database training suggestion chain corresponding table and database training method table;
The output module is used for outputting the training scheme obtained by the analysis module;
the acquisition module is used for calling the target sound test words in the database module and acquiring the voice of the evaluation object once or for multiple times;
the evaluation module is used for processing and evaluating the collected voice to obtain a voice evaluation result; the evaluation result is combined with the month age of the patient and the target sound to form voice evaluation data;
the system is executed according to a method for planning a dysarthria correction scheme in an autism evaluation object, and the method comprises the following steps:
step A, establishing dysarthria feature codes according to voice evaluation data of an evaluation object; the obtaining of the evaluation data comprises the steps of:
a1, collecting voice of an evaluation object;
a2, processing and evaluating the acquired voice to obtain an evaluation object voice evaluation result;
in step A2, the speech evaluation result includes: positive solution, misinterpretation, loss, confusion; wherein,,
the positive solution refers to the voice evaluation result as follows: the Chinese phonetic alphabet of the single word obtained by the voice recognition of the evaluation object is consistent with the initial consonant and the final of the target sound Chinese phonetic alphabet;
the loss refers to the speech evaluation result being: the Chinese phonetic alphabet of the single word obtained by the recognition of the voice of the evaluation object is consistent with the vowel of the target voice, the initial consonant is not pronounced, and the evaluation result is used A representation;
the confusion refers to the speech assessment result being: the Chinese phonetic initial consonant of the single word obtained by the recognition of the voice of the evaluation object is different from the Chinese phonetic initial consonant of the target voice, but is related to the pronunciation mode or the pronunciation part of the Chinese phonetic initial consonant of the target voice; the voice evaluation result is used for evaluating the actual voice record of the object;
the misinterpretation refers to the speech evaluation result that: the speech evaluation result of the evaluation object does not belong to any one of positive solution, loss and confusion, and the speech evaluation result is represented by X;
if the evaluation result is misinterpretation or loss, the evaluation object has deficiency to the pronunciation mode and pronunciation part of the initial consonant;
if the evaluation result is confusion, determining the pronunciation mode and the deficiency condition of the pronunciation part of the initial consonant by referring to a confusion sound table;
the evaluation object pronounces three times at the time of the test, and among the three pronunciations of the evaluation object,
if the three times are positive solutions, pushing and consolidating relevant exercise F in a pushing scheme;
if the pronunciation mode or the pronunciation part is insufficient once in the three tests, the pronunciation of the evaluation object is learned, but is not stable enough, and the targeted exercise and consolidation are needed, and the pushing exercise mode is as follows: d, E and F;
If the pronunciation mode or the pronunciation part is insufficient twice in the three tests, the fact that the sound of the evaluation object is not obtained stably is indicated, the exercise needs to be strengthened, and the pushing exercise mode is as follows: c, D and E;
if the pronunciation mode or the pronunciation position is insufficient in all three tests, the evaluation object is proved to have problems on the pronunciation position and/or the pronunciation mode, and the basic training is carried out on the pronunciation position and/or the pronunciation mode, wherein the pushing training mode is as follows: if only the pronunciation part is insufficient, pushing B, C and D; if the pronunciation mode is insufficient, pushing A, C and D; if the pronunciation part and the pronunciation mode are insufficient, pushing A, B, C and D;
wherein A is pronunciation part exercise, B is pronunciation mode exercise, C is pronunciation induction exercise, D is phonemic training exercise, E is phonemic contrast exercise, and F is speech enhancement exercise;
step A3: forming voice evaluation data by combining the month age of the evaluation object and the target sound according to the voice evaluation result;
step B, inquiring corresponding database data according to the dysarthria feature codes to obtain a Chinese dysarthria correction training scheme;
step C, outputting the dysarthria correction training scheme;
α represents the month age of the evaluation subject, α=0-999;
the Mandarin Chinese initial consonant comprises: b. m, p, f, d, t, n, l, g, k, h, j, q, x, z, c, s, zh, ch, sh, r;
the beta represents a target sound, namely a target initial consonant for selecting testing from Chinese mandarin initial consonants;
the gamma represents the evaluation result of the voice of the evaluation object and is represented by epsilon, eta, lambda and specific confusion sounds; the epsilon represents that the voice evaluation result of the evaluation object is correct; the eta represents that the evaluation object voice evaluation result is a misinterpretation; the lambda represents that the speech evaluation result of the evaluation object is lost; the specific confusion sounds represent specific confusion sounds related to the pronunciation mode or pronunciation part of the target sound as the evaluation result of the evaluation target voice;
the delta represents the occurrence times of the voice evaluation result corresponding to the coding gamma, and the numerical range of the times is 1-3;
the method from the voice evaluation result to the establishment of dysarthria feature codes comprises the following steps:
alpha is used for representing the month age of the evaluation object of the test, and 0 is added to the left side to be 3 digits;
the specific initial consonant of the target sound of the test is represented by beta;
using gamma to represent the evaluation result of the speech of the evaluation object of the test;
the delta is used for representing the occurrence times of the voice evaluation result of the evaluation object of the test;
the character alpha,Splicing beta, gamma and delta to obtain the final dysarthria characteristic code of alpha-/>-β-γ-Δ;
Wherein, the corresponding relation of the b-structure dysarthria characteristic codes of the initial consonants and the training strategy codes is as follows:
2. the system of claim 1, wherein in step A1, the speech is collected according to a test vocabulary; the test word list is obtained by summarizing and arranging the Chinese phonetic combination rules in the basic rule of Chinese phonetic positive word method.
3. The system of claim 1, wherein in step A1, the voice acquisition of the evaluation object is performed by:
1) Connecting a microphone and an ADC to a computer, wherein the microphone collects the voice of an evaluation object;
2) The ADC equipment samples at the speed of 48000 times per second, each sampling is cascaded through a multistage amplifier and a comparator, analog signals of voice are sampled into level signals with different voltages through an analog-to-digital conversion circuit, and the level signals are connected and transmitted to a computer through a 3.5mm interface or a USB interface and stored as sound files to be analyzed.
4. The system of claim 1, wherein, in the database data,
each initial consonant has specific attributes, and the initial consonants and the corresponding attributes are summarized into a database initial consonant table in a database; wherein the specific attributes of each initial consonant are respectively as follows: the target sound, the target sound should learn the month age, the target sound detailed information, the target sound type and the single double three syllable test words corresponding to the target sound; each attribute of the initial consonant corresponds to a row of entries in the database;
for each initial consonant, the codes of the gamma-delta composition are different because of the difference of the evaluation results, and each evaluation result code of each initial consonant is summarized into a database gamma-delta code-strategy chain corresponding table in a database; the database gamma-delta encoding-policy chain correspondence table has the following attributes: gamma-delta coding, target sound, evaluation result major class, confusing sound, error times and strategy chain; each attribute in the database gamma-delta coding-strategy chain corresponding table corresponds to a row of entries in the database;
for each initial consonant, specific codes in the strategy chain have corresponding training suggestion chains, and a database training suggestion chain corresponding table is established; the database training suggestion chain correspondence table includes the following attributes: specific codes, target sounds and training suggestion chains in the strategy chain; each attribute in the database training suggestion chain corresponding table corresponds to a row of entries in the database;
For each training suggestion chain, the training method id in the training suggestion chain has corresponding specific content, and a database training method table is established, wherein the database training method table comprises the following attributes: target sound, method id in training suggestion chain and specific content corresponding to the method id; each attribute in the database training method table corresponds to a column of entries in the database.
5. The system of claim 1, wherein, based on the dysarthria feature codes, the corresponding database data is queried,
when a specific training strategy is obtained through inquiry, firstly, positioning to a database initial consonant information table through target sound, and reading the acquired month age of the initial consonant; if the month age of the evaluation object is smaller than the acquired month age of the initial consonant, not pushing the training scheme;
secondly, according to the gamma-delta code of the test, obtaining a strategy chain corresponding to the target sound of the test in a database gamma-delta code-strategy chain corresponding table according to the target sound and the gamma-delta code;
according to specific codes in the strategy chain corresponding to the target sound and the target sound, inquiring a database training suggestion chain corresponding table to obtain a training suggestion chain of the specific codes of the strategy chain;
And finally, inquiring a database training method table according to the target sound and the method ids in the training suggestion chain, obtaining the specific content corresponding to each method id, and combining to obtain the complete training scheme of the test.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210056668.2A CN114566258B (en) | 2022-01-18 | 2022-01-18 | Planning system for dysarthria correction scheme in autism evaluation object |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210056668.2A CN114566258B (en) | 2022-01-18 | 2022-01-18 | Planning system for dysarthria correction scheme in autism evaluation object |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114566258A CN114566258A (en) | 2022-05-31 |
CN114566258B true CN114566258B (en) | 2023-04-21 |
Family
ID=81711945
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210056668.2A Active CN114566258B (en) | 2022-01-18 | 2022-01-18 | Planning system for dysarthria correction scheme in autism evaluation object |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114566258B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2020151092A (en) * | 2019-03-19 | 2020-09-24 | Impute株式会社 | Autism treatment support system, autism treatment support device, and program |
WO2021014014A1 (en) * | 2019-07-25 | 2021-01-28 | Sensorion | Treatment and/or prevention of lesions in the central auditory nervous system |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI431563B (en) * | 2010-08-03 | 2014-03-21 | Ind Tech Res Inst | Language learning system, language learning method, and computer product thereof |
CN107301863A (en) * | 2017-07-13 | 2017-10-27 | 江苏师范大学 | A kind of deaf-mute child's disfluency method of rehabilitation and rehabilitation training system |
JP2022529762A (en) * | 2019-04-26 | 2022-06-24 | ガヘ リ | Learning system for improving pronunciation |
US20210312942A1 (en) * | 2020-04-06 | 2021-10-07 | Winterlight Labs Inc. | System, method, and computer program for cognitive training |
CN113111952A (en) * | 2021-04-20 | 2021-07-13 | 北京心康医学科技有限公司 | Sleep training method and system based on artificial intelligence |
-
2022
- 2022-01-18 CN CN202210056668.2A patent/CN114566258B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2020151092A (en) * | 2019-03-19 | 2020-09-24 | Impute株式会社 | Autism treatment support system, autism treatment support device, and program |
WO2021014014A1 (en) * | 2019-07-25 | 2021-01-28 | Sensorion | Treatment and/or prevention of lesions in the central auditory nervous system |
Also Published As
Publication number | Publication date |
---|---|
CN114566258A (en) | 2022-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
O'Connor | Better English Pronunciation | |
CN106851216B (en) | A kind of classroom behavior monitoring system and method based on face and speech recognition | |
Nishimoto et al. | Japanese normative set of 359 pictures | |
Klapper | Teaching children to read | |
O'Brien | Reading: Its psychology and pedagogy | |
CN114566258B (en) | Planning system for dysarthria correction scheme in autism evaluation object | |
CN114582369A (en) | Initial consonant dysarthria analysis system based on speech recognition | |
CN114566248A (en) | Intelligent pushing method for Chinese sound construction training scheme | |
CN114566255A (en) | Initial consonant dysarthria feature coding generation method and system | |
CN114944218A (en) | Data query processing method and database system for correcting consonant dysarthria | |
CN114566257A (en) | Correction scheme generation system for dysarthria of initial consonant b | |
Starch | Experiments in educational psychology | |
Barrows et al. | The Teacher's Book of Phonetics | |
CN114566259A (en) | Correction scheme generation system for m dysarthria of initial consonant | |
Wittry | Baton basics: Communicating music through gestures | |
CN103927022B (en) | A kind of shape Chinese-character phonetic letter input method | |
CN114566256A (en) | Correction scheme generation system for consonant d dysarthria | |
Soveran | From Cree to English. Part One: the Sound System. | |
Murdoch | Analytic Elocution: Containing Studies, Theoretical and Practical, of Expressive Speech | |
Edkins | The evolution of the Chinese language: As exemplifying the origin and growth of human speech | |
Blackiston | The Teacher: Hints on School Management | |
Bell | Principles of Speech and Dictionary of Sounds | |
Middleton | A study on the effectiveness of the breath impulse technique in the instruction of wind instrument performers | |
Brozbă | From Zero to Hero: English phonetics and phonology | |
Чистіліна | Practical Course of Phonetics |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |