CN109461459A - Speech assessment method, apparatus, computer equipment and storage medium - Google Patents
Speech assessment method, apparatus, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109461459A CN109461459A CN201811493385.4A CN201811493385A CN109461459A CN 109461459 A CN109461459 A CN 109461459A CN 201811493385 A CN201811493385 A CN 201811493385A CN 109461459 A CN109461459 A CN 109461459A
- Authority
- CN
- China
- Prior art keywords
- pinyin information
- information
- user
- pinyin
- matching degree
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 230000009466 transformation Effects 0.000 claims abstract description 55
- 238000005259 measurement Methods 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 238000010168 coupling process Methods 0.000 claims description 19
- 238000005859 coupling reaction Methods 0.000 claims description 19
- 230000008878 coupling Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 14
- 238000005520 cutting process Methods 0.000 claims description 12
- 241001672694 Citrus reticulata Species 0.000 abstract description 22
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 abstract description 3
- 238000006243 chemical reaction Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 241000219095 Vitis Species 0.000 description 2
- 235000009754 Vitis X bourquina Nutrition 0.000 description 2
- 235000012333 Vitis X labruscana Nutrition 0.000 description 2
- 235000014787 Vitis vinifera Nutrition 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/69—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for evaluating synthetic or decoded voice signals
-
- 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
- G10L17/00—Speaker identification or verification techniques
- G10L17/04—Training, enrolment or model building
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses speech assessment method, apparatus, computer equipment and storage mediums.If method includes: to receive matching degree measurement request, from one text sentence of random selection as target text sentence；Typing prompt information is generated according to target text sentence to prompt user's typing voice messaging corresponding with target text sentence；If receiving user according to the voice messaging of typing prompt information institute typing, the voice messaging is converted to by the first Pinyin information by default voice transformation model；Target text sentence is converted into the second Pinyin information by pre-set text transformation model；The matching degree between the first Pinyin information and the second Pinyin information is calculated according to preset matching degree computation model to obtain the speech assessment of the user.The present invention is based on voice processing technologies, and the speech assessment of user is obtained by calculation, and can accurately obtain the matching degree between the voice messaging and mandarin that user is inputted, and meet the actual use demand of user.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of speech assessment method, apparatus, computer equipment and deposit
Storage media.
Background technique
The range of intelligent sound technical application is more and more extensive, the need pair when passing through intelligent sound technology input voice information
The voice messaging inputted is identified, is not suitable for other dialects since speech recognition is only applicable to mandarin, and existing
Voice information identification method can not obtain the matching degree between user institute input voice information and mandarin, and inputted in user
Voice messaging and mandarin between matching degree it is not high in the case where, significantly reduce to user's institute's input voice information carry out
The accuracy rate of identification.Thus, existing voice information identification method presence can not judge to match between voice messaging and mandarin
The problem of spending.
Summary of the invention
The embodiment of the invention provides a kind of speech assessment method, apparatus, computer equipment and storage mediums, it is intended to solve
The art methods the problem of matching degree between voice messaging and mandarin can not being judged.
In a first aspect, the embodiment of the invention provides a kind of speech assessment methods comprising:
If receiving matching degree measurement request, a text sentence is randomly choosed from pre-set text statement library as target
Text sentence；
Typing prompt information is generated according to the target text sentence to prompt user's typing and the target text sentence
Corresponding voice messaging；
If receiving the user according to the voice messaging of typing prompt information institute typing, pass through default voice conversion
The voice messaging is converted to the first Pinyin information by model；
The target text sentence is converted into the second Pinyin information by pre-set text transformation model；
According to preset matching degree computation model to the matching between first Pinyin information and second Pinyin information
Degree is calculated to obtain the speech assessment of the user.
Second aspect, the embodiment of the invention provides a kind of speech assessment devices comprising:
Target text sentence acquiring unit, if for receive matching degree measurement request, from pre-set text statement library with
Machine selects a text sentence as target text sentence；
Prompt information generation unit, for generating typing prompt information according to the target text sentence to prompt user to record
Enter voice messaging corresponding with the target text sentence；
First Pinyin information acquiring unit, if for receiving the user according to typing prompt information institute typing
The voice messaging is converted to the first Pinyin information by default voice transformation model by voice messaging；
Second Pinyin information acquiring unit, for being converted to the target text sentence by pre-set text transformation model
Second Pinyin information；
Speech assessment acquiring unit, for according to preset matching degree computation model to first Pinyin information and described the
Matching degree between two Pinyin informations is calculated to obtain the speech assessment of the user.
The third aspect, the embodiment of the present invention provide a kind of computer equipment again comprising memory, processor and storage
On the memory and the computer program that can run on the processor, the processor execute the computer program
Speech assessment method described in the above-mentioned first aspect of Shi Shixian.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, wherein the computer can
It reads storage medium and is stored with computer program, it is above-mentioned that the computer program when being executed by a processor executes the processor
Speech assessment method described in first aspect.
The embodiment of the invention provides a kind of speech assessment method, apparatus, computer equipment and storage mediums.By random
Selection obtains target text sentence, converts to the voice messaging of user institute typing and spelling that target text sentence is converted to
Message breath, which carries out matching degree calculating, can obtain the inputted voice of user by speech assessment to obtain the speech assessment of user
Matching degree between information and mandarin can accurately calculate the matching degree between voice messaging and mandarin, meet
The actual use demand of user.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow diagram of speech assessment method provided in an embodiment of the present invention；
Fig. 2 is the sub-process schematic diagram of speech assessment method provided in an embodiment of the present invention；
Fig. 3 is another sub-process schematic diagram of speech assessment method provided in an embodiment of the present invention；
Fig. 4 is another sub-process schematic diagram of speech assessment method provided in an embodiment of the present invention；
Fig. 5 is another flow diagram of speech assessment method provided in an embodiment of the present invention；
Fig. 6 is the schematic block diagram of speech assessment device provided in an embodiment of the present invention；
Fig. 7 is the subelement schematic block diagram of speech assessment device provided in an embodiment of the present invention；
Fig. 8 is another subelement schematic block diagram of speech assessment device provided in an embodiment of the present invention；
Fig. 9 is another subelement schematic block diagram of speech assessment device provided in an embodiment of the present invention；
Figure 10 is another schematic block diagram of speech assessment device provided in an embodiment of the present invention；
Figure 11 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Referring to Fig. 1, Fig. 1 is the flow diagram of speech assessment method provided in an embodiment of the present invention.The speech assessment
Method is applied in user terminal, and user terminal is to be scored with realizing voice messaging for executing speech assessment method
Terminal device, such as mobile phone, tablet computer, desktop computer, laptop etc..
As shown in Figure 1, the method comprising the steps of S110~S150.
If S110, receiving matching degree measurement request, a text sentence is randomly choosed from pre-set text statement library and is made
For target text sentence.
If receiving the matching degree measurement request that user is inputted, randomly choosed from the pre-set text statement library of user terminal
One text sentence is as target text sentence.Matching degree measurement request is user (user of user terminal) at user's end
The solicited message measured to the speech assessment of the user inputted in end, pre-set text statement library are in user terminal
It is default for storing the statement library of text sentence, it is for selection comprising a plurality of text sentence in pre-set text sentence.To increase
The accuracy that the speech assessment of user is measured by force, it is pre- from comprising a plurality of text sentence by randomly selected mode
If the occasional case in measurement process can be reduced as target text sentence by selecting one in text sentence library, to improve measurement
Accuracy.
S120, typing prompt information is generated to prompt user's typing and the target text according to the target text sentence
The corresponding voice messaging of sentence.
Typing prompt information is generated according to the target text sentence to prompt user's typing and the target text sentence
Corresponding voice messaging, specifically, generating the prompt information of typing voice messaging and in user in the target text sentence
It is shown in terminal, to prompt the user corresponding voice messaging of typing, user in the target text sentence to watch the prompt
Information simultaneously carries out typing to voice messaging according to the content of prompt information.
For example, generating corresponding prompt information is " please to be read aloud with mandarin following if target text sentence is " XXXX "
Content: XXXX ".
If S130, receiving the user according to the voice messaging of typing prompt information institute typing, by presetting language
The voice messaging is converted to the first Pinyin information by sound transformation model.
If receiving the user according to the voice messaging of typing prompt information institute typing, pass through default voice conversion
The voice messaging is converted to the first Pinyin information by model.For the voice messaging to the typing of user institute whether with corresponding text language
Sentence, which matches, to be judged, need to be by the way that the voice messaging of user institute typing is converted to the first Pinyin information, voice transformation model
It is the concrete model for voice messaging to be converted to the first Pinyin information, specifically includes acoustic model in voice transformation model
With phonetic feature dictionary.
In one embodiment, as shown in Fig. 2, step S130 includes sub-step S131 and S132.
S131, cutting is carried out to voice messaging to obtain institute in voice messaging according to the acoustic model in voice transformation model
The multiple phonemes for including.
Cutting is carried out to obtain included in voice messaging to voice messaging according to the acoustic model in voice transformation model
Multiple phonemes.Specifically, the voice messaging of user institute typing is made of, the sound of a character the phoneme of multiple character sounds
Element includes the frequency and tone color of the character sound.It include the phoneme of all character sounds in acoustic model, by by audio-frequency information
It is matched with phoneme all in acoustic model, cutting can be carried out to the phoneme of character single in audio-frequency information, by cutting
Divide and finally obtains multiple phonemes included in the audio-frequency information.
S132, obtained phoneme is matched with by all sounds according to the phonetic feature dictionary in Text region model
Element carries out being converted to the first Pinyin information.
According to the phonetic feature dictionary in Text region model to obtained phoneme matched with by all phonemes into
Row is converted to the first Pinyin information.It include the corresponding phoneme information of all character phonetics in phonetic feature dictionary, by by institute
Obtained phoneme phoneme information corresponding with character phonetic is matched, and can be phonetic feature by the phoneme conversion of single character
The character phonetic to match in dictionary with the phoneme, obtaining the corresponding character phonetic of all characters in the voice messaging can be real
It is now the first Pinyin information by all phoneme conversions included in voice messaging.
S140, the target text sentence is converted to by the second Pinyin information by pre-set text transformation model.
The target text sentence is converted into the second Pinyin information by pre-set text transformation model.Pre-set text conversion
Model is the model for target text sentence to be converted to the second Pinyin information, the Chinese pronunciation of each Chinese character or number
Phonetic can be led to be indicated, include the Pinyin information of all characters in text conversion model, by by target text sentence
Included in Chinese character or number matched with the character in text conversion model, target text sentence can be converted to the
Two Pinyin informations.
In one embodiment, as shown in figure 3, step S140 includes sub-step S141 and S142.
S141, the Pinyin information that each character in target text sentence is obtained by pre-set text transformation model.
The Pinyin information of each character in target text sentence is obtained by pre-set text transformation model.Specifically, passing through
Each Chinese character in target text sentence or number are matched with the character in text conversion model, the corresponding Chinese can be obtained
The Pinyin information of word or number in text conversion model, that is to say the phonetic for acquiring each character in target text sentence
Information.
For example, the Pinyin information for acquiring " fruit " is " gu ǒ ", the Pinyin information of "and" is " h é/h ú/hu ó/hu ò ".
S142, obtained Pinyin information is combined by pre-set text transformation model to obtain the second phonetic letter
Breath.
Obtained character is spelled in position of each character in target text sentence by pre-set text transformation model
Sound is combined to obtain the second Pinyin information.Specifically, if some character is not polyphone, directly by the reading of the character
Sound is added to the character the location of in target text sentence；If some character is polyphone, need through default text
This transformation model is by carrying out part of speech analysis to the character and front and back character, to select and the word from a variety of pronunciations of the character
It accords with a kind of pronunciation that current part of speech matches and is added to the character the location of in target text sentence.
For example, if in target text sentence a certain section be " apple and grape ", due to "and" be polyphone, then to its front and back
Character carries out part of speech analysis, and apple and grape are noun, then the part of speech of "and" at this time is determined by pre-set text transformation model
For structural auxiliary word, the Pinyin information when "and" is as structural auxiliary word is " h é ".
S150, according to preset matching degree computation model between first Pinyin information and second Pinyin information
Matching degree is calculated to obtain the speech assessment of the user.
The matching degree between the first Pinyin information and the second Pinyin information is counted according to preset matching degree computation model
It calculates to obtain the matching degree between user institute input voice information and mandarin, that is to say the speech assessment of the user.Specifically,
Matching degree computation model is to spell to the model that matching degree is calculated between the first Pinyin information and the second Pinyin information, first
Message breath is the Pinyin information being converted to according to user institute input voice information, and the second Pinyin information is respective objects text language
The Pinyin information of sentence standard Chinese pronunciation, by calculating the matching degree between the first Pinyin information and the second Pinyin information,
The matching degree between user's institute's input voice information and the standard Chinese pronunciation of respective objects text sentence can be obtained, that is to say
Obtain the speech assessment of the user.
In one embodiment, as shown in figure 4, step S150 includes sub-step S151, S152 and S153.
S151, it is whether equal to the quantity of character phonetic included in first Pinyin information and the second Pinyin information into
Row judgement.
It, need to be to included in the first Pinyin information and the second Pinyin information before the speech assessment to user calculates
Whether the quantity of character is equal to be judged, is spelled specifically, obtaining character in the first Pinyin information and the second Pinyin information respectively
The quantity of sound simultaneously carries out judging that judging result can be obtained.
If judging result be character included in the first Pinyin information and the second Pinyin information quantity it is unequal, to
The prompt information of family sending voice messaging typing mistake.It can show that the voice messaging typing is wrong in the display equipment of user terminal
Prompt information accidentally can be according to the content of prompt information typing voice messaging again after user receives prompt information.
If the quantity of character phonetic included in S152, the first Pinyin information and the second Pinyin information is equal, first is spelled
Each character phonetic is matched with respective symbols phonetic in the second Pinyin information to obtain the matching of character phonetic in message breath
Number P.
If the quantity of character phonetic included in the first Pinyin information and the second Pinyin information is equal, by the first Pinyin information
In each character phonetic matched with respective symbols phonetic in the second Pinyin information, character phonetic coupling number P can be obtained.
The quantity of the character phonetic as included in the first Pinyin information and the second Pinyin information is equal, every in the first Pinyin information
An one character phonetic character phonetic corresponding with the second Pinyin information is corresponding, specifically, obtaining the first phonetic letter
First character phonetic is matched with first character phonetic in the second Pinyin information in breath, if in the first Pinyin information
One character phonetic matches with respective symbols phonetic in the second Pinyin information, then coupling number adds one；If not matching that, obtain
Character late phonetic is matched with phase character phonetic in the second Pinyin information in first Pinyin information, until the first phonetic
Last character phonetic completes matching in information, and obtaining coupling number at this time is final character phonetic coupling number P.
S153, according to the matching degree calculation formula in matching degree computation model: matching degree S=P/P0The use is calculated
The speech assessment at family, wherein P0For the quantity of character phonetic included in the second Pinyin information.
According to the matching degree calculation formula in matching degree computation model: matching degree S=P/P0The user institute is calculated
Matching degree between input voice information and mandarin that is to say the speech assessment of the user, wherein P0For the second Pinyin information
Included in character phonetic quantity, P be character phonetic coupling number.
Based on the above speech assessment method, the voice messaging inputted to user is scored after obtaining speech assessment,
It can be further compared by the way that matching degree threshold value is arranged in the user terminal with resulting speech assessment, if obtained voice
Scoring is less than matching degree threshold value, then does not carry out speech recognition to the voice messaging to be identified that user subsequently inputs；If obtained
Speech assessment is not less than matching degree threshold value, and the voice messaging to be identified that can be subsequently input to user carries out speech recognition, namely
It is that the voice messaging to be identified inputted again to the user after the speech assessment of user reaches certain and requires carries out voice knowledge
Not, the accuracy rate that voice messaging to be identified is identified is inputted to user to greatly improve.
In addition, the above speech assessment method also can be directly used for being trained the mandarin level of user itself, such as
User that is to say by obtaining speech assessment and obtain its matching degree between input voice information and mandarin, can understand
Understand the voice messaging that oneself is inputted whether standard, so as to be instructed by mandarin level of the above method to its own
Practice.
In one embodiment, as shown in figure 5, further including step S160 after step S150.
S160, the character phonetic not matched that in first Pinyin information with second Pinyin information is obtained to generate
Non-matching prompt information.
It obtains the character phonetic not matched that in the first Pinyin information with the second Pinyin information and generates non-matching prompt letter
Breath shown in the user terminal, with the standard Chinese pronunciation of the voice messaging that prompts user to be inputted and target text sentence it
Between the character phonetic that does not match that, user watch the non-matching prompt information can obtain when subsequent progress voice input it is required into
The improved part of row.
Target text sentence is obtained by random selection, convert simultaneously target text to the voice messaging of user institute typing
The Pinyin information that sentence is converted to, which carries out matching degree calculating, can be obtained with obtaining the speech assessment of user by speech assessment
Take the matching degree between family institute input voice information and mandarin, can to the matching degree between voice messaging and mandarin into
Row is accurate to be calculated, and the actual use demand of user is met.
The embodiment of the present invention also provides a kind of speech assessment device, and the speech assessment device is for executing aforementioned voice scoring
Any embodiment of method.Specifically, referring to Fig. 6, Fig. 6 is the schematic of speech assessment device provided in an embodiment of the present invention
Block diagram.The speech assessment device can be configured in the terminal devices such as desktop computer, laptop, tablet computer or mobile phone.
As shown in fig. 6, speech assessment device 100 includes target text sentence acquiring unit 110, prompt information generation unit
120, the first Pinyin information acquiring unit 130, the second Pinyin information acquiring unit 140 and speech assessment acquiring unit 150.
Target text sentence acquiring unit 110, if for receiving matching degree measurement request, from pre-set text statement library
A text sentence is randomly choosed as target text sentence.
If receiving the matching degree measurement request that user is inputted, randomly choosed from the pre-set text statement library of user terminal
One text sentence is as target text sentence.Matching degree measurement request is user (user of user terminal) at user's end
The solicited message measured to the speech assessment of the user inputted in end, pre-set text statement library are in user terminal
It is default for storing the statement library of text sentence, it is for selection comprising a plurality of text sentence in pre-set text sentence.To increase
The accuracy that the speech assessment of user is measured by force, it is pre- from comprising a plurality of text sentence by randomly selected mode
If the occasional case in measurement process can be reduced as target text sentence by selecting one in text sentence library, to improve measurement
Accuracy.
Prompt information generation unit 120, for generating typing prompt information according to the target text sentence to prompt to use
Family typing voice messaging corresponding with the target text sentence.
Typing prompt information is generated according to the target text sentence to prompt user's typing and the target text sentence
Corresponding voice messaging, specifically, generating the prompt information of typing voice messaging and in user in the target text sentence
It is shown in terminal, to prompt the user corresponding voice messaging of typing, user in the target text sentence to watch the prompt
Information simultaneously carries out typing to voice messaging according to the content of prompt information.
First Pinyin information acquiring unit 130, if being recorded for receiving the user according to the typing prompt information
The voice messaging is converted to the first Pinyin information by default voice transformation model by the voice messaging entered.
If receiving the user according to the voice messaging of typing prompt information institute typing, pass through default voice conversion
The voice messaging is converted to the first Pinyin information by model.For the voice messaging to the typing of user institute whether with corresponding text language
Sentence, which matches, to be judged, need to be by the way that the voice messaging of user institute typing is converted to the first Pinyin information, voice transformation model
It is the concrete model for voice messaging to be converted to the first Pinyin information, specifically includes acoustic model in voice transformation model
With phonetic feature dictionary.
In other inventive embodiments, as shown in fig. 7, the first Pinyin information acquiring unit 130 includes subelement: phoneme
Acquiring unit 131 and phoneme matching unit 132.
Phoneme acquiring unit 131, for according to the acoustic model in voice transformation model to voice messaging carry out cutting with
Obtain multiple phonemes included in voice messaging.
Cutting is carried out to obtain included in voice messaging to voice messaging according to the acoustic model in voice transformation model
Multiple phonemes.Specifically, the voice messaging of user institute typing is made of, the sound of a character the phoneme of multiple character sounds
Element includes the frequency and tone color of the character sound.It include the phoneme of all character sounds in acoustic model, by by audio-frequency information
It is matched with phoneme all in acoustic model, cutting can be carried out to the phoneme of character single in audio-frequency information, by cutting
Divide and finally obtains multiple phonemes included in the audio-frequency information.
Phoneme matching unit 132, for according to the phonetic feature dictionary in Text region model to obtained phoneme into
Row matching is to carry out all phonemes to be converted to the first Pinyin information.
According to the phonetic feature dictionary in Text region model to obtained phoneme matched with by all phonemes into
Row is converted to the first Pinyin information.It include the corresponding phoneme information of all character phonetics in phonetic feature dictionary, by by institute
Obtained phoneme phoneme information corresponding with character phonetic is matched, and can be phonetic feature by the phoneme conversion of single character
The character phonetic to match in dictionary with the phoneme, obtaining the corresponding character phonetic of all characters in the voice messaging can be real
It is now the first Pinyin information by all phoneme conversions included in voice messaging.
Second Pinyin information acquiring unit 140, for being turned the target text sentence by pre-set text transformation model
It is changed to the second Pinyin information.
The target text sentence is converted into the second Pinyin information by pre-set text transformation model.Pre-set text conversion
Model is the model for target text sentence to be converted to the second Pinyin information, the Chinese pronunciation of each Chinese character or number
Phonetic can be led to be indicated, include the Pinyin information of all characters in text conversion model, by by target text sentence
Included in Chinese character or number matched with the character in text conversion model, target text sentence can be converted to the
Two Pinyin informations.
In other inventive embodiments, as shown in figure 8, the second Pinyin information acquiring unit 140 includes subelement: character
Pinyin information acquiring unit 141 and Pinyin information assembled unit 142.
Character Pinyin information acquiring unit 141, it is every in target text sentence for being obtained by pre-set text transformation model
The Pinyin information of one character.
The Pinyin information of each character in target text sentence is obtained by pre-set text transformation model.Specifically, passing through
Each Chinese character in target text sentence or number are matched with the character in text conversion model, the corresponding Chinese can be obtained
The Pinyin information of word or number in text conversion model, that is to say the phonetic for acquiring each character in target text sentence
Information.
Pinyin information assembled unit 142, for carrying out group to obtained Pinyin information by pre-set text transformation model
It closes to obtain the second Pinyin information.
Obtained character is spelled in position of each character in target text sentence by pre-set text transformation model
Sound is combined to obtain the second Pinyin information.Specifically, if some character is not polyphone, directly by the reading of the character
Sound is added to the character the location of in target text sentence；If some character is polyphone, need through default text
This transformation model is by carrying out part of speech analysis to the character and front and back character, to select and the word from a variety of pronunciations of the character
It accords with a kind of pronunciation that current part of speech matches and is added to the character the location of in target text sentence.
Speech assessment acquiring unit 150 is used for according to preset matching degree computation model to first Pinyin information and institute
The matching degree between the second Pinyin information is stated to be calculated to obtain the speech assessment of the user.
The matching degree between the first Pinyin information and the second Pinyin information is counted according to preset matching degree computation model
It calculates to obtain the matching degree between user institute input voice information and mandarin, that is to say the speech assessment of the user.Specifically,
Matching degree computation model is to spell to the model that matching degree is calculated between the first Pinyin information and the second Pinyin information, first
Message breath is the Pinyin information being converted to according to user institute input voice information, and the second Pinyin information is respective objects text language
The Pinyin information of sentence standard Chinese pronunciation, by calculating the matching degree between the first Pinyin information and the second Pinyin information,
The matching degree between user's institute's input voice information and the standard Chinese pronunciation of respective objects text sentence can be obtained, that is to say
Obtain the speech assessment of the user.
In other inventive embodiments, as shown in figure 9, the speech assessment acquiring unit 150 includes subelement: judging unit
151, character phonetic coupling number acquiring unit 152 and scoring computing unit 153.
Judging unit 151, for the number to character phonetic included in first Pinyin information and the second Pinyin information
Whether amount is equal to be judged.
It, need to be to included in the first Pinyin information and the second Pinyin information before the speech assessment to user calculates
Whether the quantity of character is equal to be judged, is spelled specifically, obtaining character in the first Pinyin information and the second Pinyin information respectively
The quantity of sound simultaneously carries out judging that judging result can be obtained.
If judging result be character included in the first Pinyin information and the second Pinyin information quantity it is unequal, to
The prompt information of family sending voice messaging typing mistake.It can show that the voice messaging typing is wrong in the display equipment of user terminal
Prompt information accidentally can be according to the content of prompt information typing voice messaging again after user receives prompt information.
Character phonetic coupling number acquiring unit 152, if for word included in the first Pinyin information and the second Pinyin information
Accord with phonetic quantity it is equal, by respective symbols phonetic in each character phonetic in the first Pinyin information and the second Pinyin information into
Row matching is to obtain character phonetic coupling number P.
If the quantity of character phonetic included in the first Pinyin information and the second Pinyin information is equal, by the first Pinyin information
In each character phonetic matched with respective symbols phonetic in the second Pinyin information, character phonetic coupling number P can be obtained.
The quantity of the character phonetic as included in the first Pinyin information and the second Pinyin information is equal, every in the first Pinyin information
An one character phonetic character phonetic corresponding with the second Pinyin information is corresponding, specifically, obtaining the first phonetic letter
First character phonetic is matched with first character phonetic in the second Pinyin information in breath, if in the first Pinyin information
One character phonetic matches with respective symbols phonetic in the second Pinyin information, then coupling number adds one；If not matching that, obtain
Character late phonetic is matched with phase character phonetic in the second Pinyin information in first Pinyin information, until the first phonetic
Last character phonetic completes matching in information, and obtaining coupling number at this time is final character phonetic coupling number P.
Score computing unit 153, for according to the matching degree calculation formula in matching degree computation model: matching degree S=P/
P0The speech assessment of the user is calculated, wherein P0For the quantity of character phonetic included in the second Pinyin information.
According to the matching degree calculation formula in matching degree computation model: matching degree S=P/P0The user institute is calculated
Matching degree between input voice information and mandarin that is to say the speech assessment of the user, wherein P0For the second Pinyin information
Included in character phonetic quantity, P be character phonetic coupling number.
By being arranged matching degree threshold value in the user terminal, and the voice messaging that user is inputted by the above method into
Row scoring obtain speech assessment, if obtained speech assessment be less than matching degree threshold value, not to user subsequently input wait know
Other voice messaging carries out speech recognition；If obtained speech assessment is not less than matching degree threshold value, user can be subsequently input
Voice messaging to be identified carry out speech recognition, that is to say after the speech assessment of user reaches certain and requires again to the user
The voice messaging to be identified that is inputted carries out speech recognition, inputs voice messaging to be identified to greatly improve to user and knows
Other accuracy rate.
In addition, user that is to say by obtaining speech assessment and obtain its between input voice information and mandarin
With degree, i.e., it will be clearly understood that the voice messaging oneself inputted whether standard, therefore user can be by the above method to its own
Mandarin level be trained.Teacher can issue the language reading aloud operation and being read aloud using above-mentioned speech assessment method student
Message breath scores, by the matching degree read aloud between operation and standard Chinese pronunciation by being completed in a manner of objective to student
It is calculated.
In other inventive embodiments, as shown in Figure 10, the speech assessment device 100 further includes subelement: non-matching to mention
Show information generating unit 160.
Non-matching prompt information generation unit 160 is believed for obtaining in first Pinyin information with second phonetic
The character phonetic not matched that is ceased to generate non-matching prompt information.
It obtains the character phonetic not matched that in the first Pinyin information with the second Pinyin information and generates non-matching prompt letter
Breath shown in the user terminal, with the standard Chinese pronunciation of the voice messaging that prompts user to be inputted and target text sentence it
Between the character phonetic that does not match that, user watch the non-matching prompt information can obtain when subsequent progress voice input it is required into
The improved part of row.
Target text sentence is obtained by random selection, convert simultaneously target text to the voice messaging of user institute typing
The Pinyin information that sentence is converted to, which carries out matching degree calculating, can be obtained with obtaining the speech assessment of user by speech assessment
Take the matching degree between family institute input voice information and mandarin, can to the matching degree between voice messaging and mandarin into
Row is accurate to be calculated, and the actual use demand of user is met.
Above-mentioned speech assessment device can be implemented as the form of computer program, which can be in such as Figure 11 institute
It is run in the computer equipment shown.
Figure 11 is please referred to, Figure 11 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Refering to fig. 11, which includes processor 502, memory and the net connected by system bus 501
Network interface 505, wherein memory may include non-volatile memory medium 503 and built-in storage 504.
The non-volatile memory medium 503 can storage program area 5031 and computer program 5032.The computer program
5032 are performed, and processor 502 may make to execute speech assessment method.
The processor 502 supports the operation of entire computer equipment 500 for providing calculating and control ability.
The built-in storage 504 provides environment for the operation of the computer program 5032 in non-volatile memory medium 503, should
When computer program 5032 is executed by processor 502, processor 502 may make to execute speech assessment method.
The network interface 505 is for carrying out network communication, such as the transmission of offer data information.Those skilled in the art can
To understand, structure shown in Figure 11, only the block diagram of part-structure relevant to the present invention program, is not constituted to this hair
The restriction for the computer equipment 500 that bright scheme is applied thereon, specific computer equipment 500 may include than as shown in the figure
More or fewer components perhaps combine certain components or with different component layouts.
Wherein, the processor 502 is for running computer program 5032 stored in memory, to realize following function
Can: if receiving matching degree measurement request, a text sentence is randomly choosed from pre-set text statement library as target text
Sentence；Typing prompt information is generated according to the target text sentence to prompt user's typing opposite with the target text sentence
The voice messaging answered；If receiving the user according to the voice messaging of typing prompt information institute typing, by presetting language
The voice messaging is converted to the first Pinyin information by sound transformation model；By pre-set text transformation model by the target text
Sentence is converted to the second Pinyin information；According to preset matching degree computation model to first Pinyin information and second phonetic
Matching degree between information is calculated to obtain the speech assessment of the user.
In one embodiment, it is recorded if processor 502 receives the user in execution according to the typing prompt information
The voice messaging entered is held when the voice messaging being converted to the step of the first Pinyin information by default voice transformation model
The following operation of row: cutting is carried out to voice messaging to obtain being wrapped in voice messaging according to the acoustic model in voice transformation model
The multiple phonemes contained；Obtained phoneme is matched with by all sounds according to the phonetic feature dictionary in Text region model
Element carries out being converted to the first Pinyin information.
In one embodiment, processor 502 is turned the target text sentence by pre-set text transformation model in execution
It when being changed to the step of the second Pinyin information, performs the following operations: being obtained in target text sentence by pre-set text transformation model
The Pinyin information of each character；Obtained Pinyin information is combined by pre-set text transformation model to obtain the second spelling
Message breath.
In one embodiment, processor 502 is being executed according to preset matching degree computation model to first Pinyin information
When matching degree between second Pinyin information is calculated to obtain the step of the speech assessment of the user, execute such as
Lower operation: whether equal to the quantity of character phonetic included in first Pinyin information and the second Pinyin information to sentence
It is disconnected；It, will be every in the first Pinyin information if the quantity of character phonetic included in the first Pinyin information and the second Pinyin information is equal
One character phonetic is matched with respective symbols phonetic in the second Pinyin information to obtain character phonetic coupling number P；According to
With the matching degree calculation formula in degree computation model: matching degree S=P/P0The speech assessment of the user is calculated, wherein P0
For the quantity of character phonetic included in the second Pinyin information.
In one embodiment, processor 502 is being executed according to preset matching degree computation model to first Pinyin information
After the step of matching degree between second Pinyin information is calculated to obtain the speech assessment of the user, also hold
The following operation of row: it is non-to generate to obtain the character phonetic not matched that in first Pinyin information with second Pinyin information
Match prompt information.
It will be understood by those skilled in the art that the embodiment of computer equipment shown in Figure 11 is not constituted to computer
The restriction of equipment specific composition, in other embodiments, computer equipment may include components more more or fewer than diagram, or
Person combines certain components or different component layouts.For example, in some embodiments, computer equipment can only include depositing
Reservoir and processor, in such embodiments, the structure and function of memory and processor are consistent with embodiment illustrated in fig. 11,
Details are not described herein.
It should be appreciated that in embodiments of the present invention, processor 502 can be central processing unit (Central
ProcessingUnit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable GateArray, FPGA) or other programmable logic devices
Part, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
The processor is also possible to any conventional processor etc..
Computer readable storage medium is provided in another embodiment of the invention.The computer readable storage medium can be with
For non-volatile computer readable storage medium.The computer-readable recording medium storage has computer program, wherein calculating
If machine program performed the steps of when being executed by processor receive matching degree measurement request, from pre-set text statement library with
Machine selects a text sentence as target text sentence；Typing prompt information is generated according to the target text sentence to prompt
User's typing voice messaging corresponding with the target text sentence；It prompts to believe according to the typing if receiving the user
The voice messaging is converted to the first Pinyin information by default voice transformation model by the voice messaging for ceasing institute's typing；Pass through
The target text sentence is converted to the second Pinyin information by pre-set text transformation model；According to preset matching degree computation model pair
Matching degree between first Pinyin information and second Pinyin information is calculated to obtain the voice of the user and comment
Point.
In one embodiment, if described receive the user according to the voice of typing prompt information institute typing letter
Breath, by presetting the step of voice messaging is converted to the first Pinyin information by voice transformation model, comprising: turned according to voice
Acoustic model in mold changing type carries out cutting to voice messaging to obtain multiple phonemes included in voice messaging；According to text
Phonetic feature dictionary in identification model matches obtained phoneme to carry out all phonemes to be converted to the first spelling
Message breath.
In one embodiment, described that the target text sentence is converted to by the second phonetic by pre-set text transformation model
The step of information, comprising: the Pinyin information of each character in target text sentence is obtained by pre-set text transformation model；Pass through
Pre-set text transformation model is combined obtained Pinyin information to obtain the second Pinyin information.
In one embodiment, described that first Pinyin information and described second are spelled according to preset matching degree computation model
The step of matching degree between message breath is calculated to obtain the speech assessment of the user, comprising: to first phonetic
Whether the quantity of character phonetic included in information and the second Pinyin information is equal to be judged；If the first Pinyin information and second
The quantity of character phonetic included in Pinyin information is equal, each character phonetic in the first Pinyin information and the second phonetic are believed
Respective symbols phonetic is matched to obtain character phonetic coupling number P in breath；According to the matching degree meter in matching degree computation model
Calculate formula: matching degree S=P/P0The speech assessment of the user is calculated, wherein P0For word included in the second Pinyin information
Accord with the quantity of phonetic.
In one embodiment, described that first Pinyin information and described second are spelled according to preset matching degree computation model
After the step of matching degree between message breath is calculated to obtain the speech assessment of the user, further includes: described in acquisition
The character phonetic not matched that in first Pinyin information with second Pinyin information is to generate non-matching prompt information.
It is apparent to those skilled in the art that for convenience of description and succinctly, foregoing description is set
The specific work process of standby, device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
Those of ordinary skill in the art may be aware that unit described in conjunction with the examples disclosed in the embodiments of the present disclosure and algorithm
Step can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and software
Interchangeability generally describes each exemplary composition and step according to function in the above description.These functions are studied carefully
Unexpectedly the specific application and design constraint depending on technical solution are implemented in hardware or software.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided by the present invention, it should be understood that disclosed unit and method, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only logical function partition, there may be another division manner in actual implementation, can also will be with the same function
Unit set is at a unit, such as multiple units or components can be combined or can be integrated into another system or some
Feature can be ignored, or not execute.In addition, shown or discussed mutual coupling, direct-coupling or communication connection can
Be through some interfaces, the indirect coupling or communication connection of device or unit, be also possible to electricity, mechanical or other shapes
Formula connection.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of unit therein can be selected to realize the embodiment of the present invention according to the actual needs
Purpose.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, is also possible to two or more units and is integrated in one unit.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention substantially or
Person says that all or part of the part that contributes to existing technology or the technical solution can body in the form of software products
Reveal and, which is stored in a computer readable storage medium, including some instructions are used so that one
Platform computer equipment (can be personal computer, server or the network equipment etc.) executes described in each embodiment of the present invention
The all or part of the steps of method.And computer readable storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory
The various media that can store program code such as (ROM, Read-Only Memory), magnetic or disk.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (10)
1. a kind of speech assessment method characterized by comprising
If receiving matching degree measurement request, a text sentence is randomly choosed from pre-set text statement library as target text
Sentence；
Typing prompt information is generated according to the target text sentence to prompt user's typing opposite with the target text sentence
The voice messaging answered；
If receiving the user according to the voice messaging of typing prompt information institute typing, by presetting voice transformation model
The voice messaging is converted into the first Pinyin information；
The target text sentence is converted into the second Pinyin information by pre-set text transformation model；
According to preset matching degree computation model to the matching degree between first Pinyin information and second Pinyin information into
Row is calculated to obtain the speech assessment of the user.
2. speech assessment method according to claim 1, which is characterized in that described by presetting voice transformation model for language
Message breath is converted to the first Pinyin information, comprising:
It is more included in voice messaging to obtain that cutting is carried out to voice messaging according to the acoustic model in voice transformation model
A phoneme；
Obtained phoneme is matched to turn all phonemes according to the phonetic feature dictionary in Text region model
It gets in return to the first Pinyin information.
3. speech assessment method according to claim 1, which is characterized in that it is described by pre-set text transformation model by institute
It states target text sentence and is converted to the second Pinyin information, comprising:
The Pinyin information of each character in target text sentence is obtained by pre-set text transformation model；
Obtained Pinyin information is combined by pre-set text transformation model to obtain the second Pinyin information.
4. speech assessment method according to claim 1, which is characterized in that described according to preset matching degree computation model pair
Matching degree between first Pinyin information and second Pinyin information is calculated to obtain the voice of the user and comment
Point, comprising:
It is whether equal to the quantity of character phonetic included in first Pinyin information and the second Pinyin information to judge；
It, will be every in the first Pinyin information if the quantity of character phonetic included in the first Pinyin information and the second Pinyin information is equal
One character phonetic is matched with respective symbols phonetic in the second Pinyin information to obtain character phonetic coupling number P；
According to the matching degree calculation formula in matching degree computation model: matching degree S=P/P0The voice that the user is calculated is commented
Point, wherein P0For the quantity of character phonetic included in the second Pinyin information.
5. speech assessment method according to claim 1, which is characterized in that described according to preset matching degree computation model pair
Matching degree between first Pinyin information and second Pinyin information is calculated to obtain the voice of the user and comment
/ after, further includes:
The character phonetic not matched that in first Pinyin information with second Pinyin information is obtained to generate non-matching mention
Show information.
6. a kind of speech assessment device characterized by comprising
Target text sentence acquiring unit, if being selected at random from pre-set text statement library for receiving matching degree measurement request
A text sentence is selected as target text sentence；
Prompt information generation unit, for according to the target text sentence generate typing prompt information with prompt user's typing with
The corresponding voice messaging of the target text sentence；
First Pinyin information acquiring unit, if for receiving the user according to the voice of typing prompt information institute typing
The voice messaging is converted to the first Pinyin information by default voice transformation model by information；
Second Pinyin information acquiring unit, for the target text sentence to be converted to second by pre-set text transformation model
Pinyin information；
Speech assessment acquiring unit, for being spelled according to preset matching degree computation model to first Pinyin information and described second
Matching degree between message breath is calculated to obtain the speech assessment of the user.
7. speech assessment device according to claim 6, which is characterized in that the first Pinyin information acquiring unit, packet
It includes:
Phoneme acquiring unit, for carrying out cutting to voice messaging according to the acoustic model in voice transformation model to obtain voice
Multiple phonemes included in information；
Phoneme matching unit, for according to the phonetic feature dictionary in Text region model to obtained phoneme matched with
All phonemes are carried out to be converted to the first Pinyin information.
8. speech assessment device according to claim 6, which is characterized in that the second Pinyin information acquiring unit, packet
It includes:
Character Pinyin information acquiring unit, for obtaining each character in target text sentence by pre-set text transformation model
Pinyin information；
Pinyin information assembled unit, for being combined obtained Pinyin information to obtain by pre-set text transformation model
Second Pinyin information.
9. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 5 when executing the computer program
Any one of described in speech assessment method.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence, the computer program make the processor execute such as language described in any one of claim 1 to 5 when being executed by a processor
Sound methods of marking.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811493385.4A CN109461459A (en) | 2018-12-07 | 2018-12-07 | Speech assessment method, apparatus, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811493385.4A CN109461459A (en) | 2018-12-07 | 2018-12-07 | Speech assessment method, apparatus, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109461459A true CN109461459A (en) | 2019-03-12 |
Family
ID=65612699
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811493385.4A Pending CN109461459A (en) | 2018-12-07 | 2018-12-07 | Speech assessment method, apparatus, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109461459A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110085210A (en) * | 2019-03-15 | 2019-08-02 | 平安科技（深圳）有限公司 | Interactive information test method, device, computer equipment and storage medium |
| CN110136721A (en) * | 2019-04-09 | 2019-08-16 | 北京大米科技有限公司 | A kind of scoring generation method, device, storage medium and electronic equipment |
| CN111027794A (en) * | 2019-03-29 | 2020-04-17 | 广东小天才科技有限公司 | Dictation operation correcting method and learning equipment |
| CN111179937A (en) * | 2019-12-24 | 2020-05-19 | 上海眼控科技股份有限公司 | Method, apparatus and computer-readable storage medium for text processing |
| CN112291281A (en) * | 2019-07-09 | 2021-01-29 | 钉钉控股（开曼）有限公司 | Voice broadcast and voice broadcast content setting method and device |
| CN112634858A (en) * | 2020-12-16 | 2021-04-09 | 平安科技（深圳）有限公司 | Speech synthesis method, speech synthesis device, computer equipment and storage medium |
| CN113793611A (en) * | 2021-08-27 | 2021-12-14 | 上海浦东发展银行股份有限公司 | Scoring method, scoring device, computer equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1455386A (en) * | 2002-11-01 | 2003-11-12 | 中国科学院声学研究所 | Imbedded voice synthesis method and system |
| CN103559880A (en) * | 2013-11-08 | 2014-02-05 | 百度在线网络技术（北京）有限公司 | Voice input system and voice input method |
| CN107204184A (en) * | 2017-05-10 | 2017-09-26 | 平安科技（深圳）有限公司 | Audio recognition method and system |
| CN107659847A (en) * | 2016-09-22 | 2018-02-02 | 腾讯科技（北京）有限公司 | Voice interface method and apparatus |
| CN107731228A (en) * | 2017-09-20 | 2018-02-23 | 百度在线网络技术（北京）有限公司 | The text conversion method and device of English voice messaging |
| CN108766437A (en) * | 2018-05-31 | 2018-11-06 | 平安科技（深圳）有限公司 | Audio recognition method, device, computer equipment and storage medium |
-
2018
- 2018-12-07 CN CN201811493385.4A patent/CN109461459A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1455386A (en) * | 2002-11-01 | 2003-11-12 | 中国科学院声学研究所 | Imbedded voice synthesis method and system |
| CN103559880A (en) * | 2013-11-08 | 2014-02-05 | 百度在线网络技术（北京）有限公司 | Voice input system and voice input method |
| CN107659847A (en) * | 2016-09-22 | 2018-02-02 | 腾讯科技（北京）有限公司 | Voice interface method and apparatus |
| CN107204184A (en) * | 2017-05-10 | 2017-09-26 | 平安科技（深圳）有限公司 | Audio recognition method and system |
| CN107731228A (en) * | 2017-09-20 | 2018-02-23 | 百度在线网络技术（北京）有限公司 | The text conversion method and device of English voice messaging |
| CN108766437A (en) * | 2018-05-31 | 2018-11-06 | 平安科技（深圳）有限公司 | Audio recognition method, device, computer equipment and storage medium |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110085210A (en) * | 2019-03-15 | 2019-08-02 | 平安科技（深圳）有限公司 | Interactive information test method, device, computer equipment and storage medium |
| CN110085210B (en) * | 2019-03-15 | 2023-10-13 | 平安科技（深圳）有限公司 | Interactive information testing method and device, computer equipment and storage medium |
| CN111027794A (en) * | 2019-03-29 | 2020-04-17 | 广东小天才科技有限公司 | Dictation operation correcting method and learning equipment |
| CN111027794B (en) * | 2019-03-29 | 2023-09-26 | 广东小天才科技有限公司 | Correction method and learning equipment for dictation operation |
| CN110136721A (en) * | 2019-04-09 | 2019-08-16 | 北京大米科技有限公司 | A kind of scoring generation method, device, storage medium and electronic equipment |
| CN112291281A (en) * | 2019-07-09 | 2021-01-29 | 钉钉控股（开曼）有限公司 | Voice broadcast and voice broadcast content setting method and device |
| CN112291281B (en) * | 2019-07-09 | 2023-11-03 | 钉钉控股（开曼）有限公司 | Voice broadcasting and voice broadcasting content setting method and device |
| CN111179937A (en) * | 2019-12-24 | 2020-05-19 | 上海眼控科技股份有限公司 | Method, apparatus and computer-readable storage medium for text processing |
| CN112634858A (en) * | 2020-12-16 | 2021-04-09 | 平安科技（深圳）有限公司 | Speech synthesis method, speech synthesis device, computer equipment and storage medium |
| CN112634858B (en) * | 2020-12-16 | 2024-01-23 | 平安科技（深圳）有限公司 | Speech synthesis method, device, computer equipment and storage medium |
| CN113793611A (en) * | 2021-08-27 | 2021-12-14 | 上海浦东发展银行股份有限公司 | Scoring method, scoring device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109461459A (en) | Speech assessment method, apparatus, computer equipment and storage medium | |
| CN103714048B (en) | Method and system for correcting text | |
| EP2958105B1 (en) | Method and apparatus for speech synthesis based on large corpus | |
| EP3504709B1 (en) | Determining phonetic relationships | |
| CN109817201B (en) | Language learning method and device, electronic equipment and readable storage medium | |
| CN109637521A (en) | A kind of lip reading recognition methods and device based on deep learning | |
| CN111402862B (en) | Speech recognition method, device, storage medium and equipment | |
| Klatt et al. | On the automatic recognition of continuous speech: Implications from a spectrogram-reading experiment | |
| CN106935239A (en) | The construction method and device of a kind of pronunciation dictionary | |
| JP2005321817A (en) | Method and apparatus for obtaining combining information from speech signals for adaptive interaction in teaching and testing | |
| US11410642B2 (en) | Method and system using phoneme embedding | |
| CN108877782A (en) | Audio recognition method and device | |
| CN109817244B (en) | Spoken language evaluation method, device, equipment and storage medium | |
| CN111833853A (en) | Voice processing method and device, electronic equipment and computer readable storage medium | |
| CN109166569B (en) | Detection method and device for phoneme mislabeling | |
| CN103050115A (en) | Recognizing device, recognizing method, generating device, and generating method | |
| CN104639742B (en) | The spoken method and device of mobile terminal CAL | |
| CN110335608A (en) | Voice print verification method, apparatus, equipment and storage medium | |
| CN109658931A (en) | Voice interactive method, device, computer equipment and storage medium | |
| CN110148413B (en) | Voice evaluation method and related device | |
| CN109582775B (en) | Information input method, device, computer equipment and storage medium | |
| CN110503956A (en) | Audio recognition method, device, medium and electronic equipment | |
| JP2004053652A (en) | Pronunciation judging system, server for managing system and program therefor | |
| JP2006208644A (en) | Server system and method for measuring linguistic speaking ability | |
| CN109697975B (en) | Voice evaluation method and device |
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 |