CN108847224A - A kind of sound mural painting plane display method and device - Google Patents
A kind of sound mural painting plane display method and device Download PDFInfo
- Publication number
- CN108847224A CN108847224A CN201810732031.4A CN201810732031A CN108847224A CN 108847224 A CN108847224 A CN 108847224A CN 201810732031 A CN201810732031 A CN 201810732031A CN 108847224 A CN108847224 A CN 108847224A
- Authority
- CN
- China
- Prior art keywords
- gender
- age
- voice
- recognition result
- sound
- 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 37
- 238000010422 painting Methods 0.000 title claims abstract description 30
- 238000000605 extraction Methods 0.000 claims description 21
- 238000003062 neural network model Methods 0.000 claims description 17
- 238000001514 detection method Methods 0.000 claims description 15
- 210000005036 nerve Anatomy 0.000 claims description 10
- 230000000694 effects Effects 0.000 claims description 9
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 10
- 230000002452 interceptive effect Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 235000008331 Pinus X rigitaeda Nutrition 0.000 description 1
- 235000011613 Pinus brutia Nutrition 0.000 description 1
- 241000018646 Pinus brutia Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000006403 short-term memory Effects 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
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09F—DISPLAYING; ADVERTISING; SIGNS; LABELS OR NAME-PLATES; SEALS
- G09F27/00—Combined visual and audible advertising or displaying, e.g. for public address
-
- 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
- G10L15/08—Speech classification or search
- G10L15/16—Speech classification or search using artificial neural networks
-
- 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
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
- G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
-
- 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
-
- 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
- G10L25/66—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 for extracting parameters related to health condition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses a kind of sound mural painting plane display method and devices.The present invention establishes age identification model and gender identification model, age and the gender that Application on Voiceprint Recognition judges speaker are carried out to voice to be identified, and then show corresponding pattern, it is unrelated with the decibel of sound in identification process, so speaker is without shouting, reduce influence of the noise to surrounding in sound wall use process, and different patterns can be shown according to the difference of age and gender, increase the diversity and interactivity of pattern, it solves current sound wall and is easy to produce noise and surrounding is impacted, and pattern is single, and the technical problem of lack of diversity and interactivity.
Description
Technical field
The present invention relates to sound techniques field more particularly to a kind of sound mural painting plane display methods.
Background technique
In order to improve amusement park and park public place recreational facilities diversity, people place in these public places
A kind of sound wall, sound wall can obtain the sound of ambient enviroment by sound pick-up, be according to the judgement of the size of sound decibel
The size of no display pattern and pattern.
This sound wall has certain interest, but due to that can only judge whether to show according to the size of sound decibel
The size of pattern and pattern needs great decibel when causing sometimes using the sound wall, impacts to surrounding, and scheme
Case is single, lack of diversity and interactivity.
Therefore, it results in current sound wall and is easy to produce noise and surrounding is impacted, and pattern is single, and lack
Diversity and interactive technical problem.
Summary of the invention
The present invention provides a kind of sound mural painting plane display method and device, solves current sound wall and be easy to produce and make an uproar
Sound impacts surrounding, and pattern is single, and lack of diversity and interactive technical problem.
The present invention provides a kind of sound mural painting plane display methods, including：
S1：Obtain the age training voice of the first preset quantity and the gender training voice of the second preset quantity；
S2：First nerves network model is trained to obtain age identification model, passability by age training voice
Not Xun Lian voice nervus opticus network model is trained to obtain gender identification model；
S3：Voice to be identified input age identification model is obtained into age recognition result, voice to be identified is inputted into gender
Identification model obtains gender recognition result, shows corresponding picture according to age recognition result and gender recognition result.
Preferably, step S3 is specifically included：
S31：Voice to be identified input age identification model is obtained into age recognition result, whether judges age recognition result
More than or equal to preset age threshold, if so, S32 is thened follow the steps, if it is not, thening follow the steps S33；
S32：Voice to be identified input gender identification model is obtained into gender recognition result, if gender recognition result is male,
It then shows the first picture, if gender recognition result is female, shows second picture；
S33：Voice to be identified input gender identification model is obtained into gender recognition result, if gender recognition result is male,
It then shows third picture, if gender recognition result is female, shows the 4th picture.
Preferably, after step S2, further include before step S3：Step S01；
S01：Feature extraction is carried out to voice to be identified by FBank feature extraction algorithm.
Preferably, after step S01, further include before step S3：Step S02；
S02：End-point detection is carried out to the voice to be identified after feature extraction by voice activity detection algorithm.
Preferably, neural network model is LSTM neural network model.
The present invention provides a kind of sound mural painting flat-panel display devices, including：
Training acquiring unit, for obtaining the age training voice of the first preset quantity and the gender instruction of the second preset quantity
Practice voice；
Model training unit obtains age knowledge for being trained by age training voice to first nerves network model
Other model is trained nervus opticus network model to obtain gender identification model by gender training voice；
Identify display unit, it, will be wait know for voice to be identified input age identification model to be obtained age recognition result
Other voice input gender identification model obtains gender recognition result, is corresponded to according to age recognition result and the display of gender recognition result
Picture.
Preferably, identification display unit specifically includes：
Age subelement judges the age for voice to be identified input age identification model to be obtained age recognition result
Whether recognition result is greater than or equal to preset age threshold, if so, the first subelement of triggering, if it is not, then the second son of triggering is single
Member；
First subelement, for voice to be identified input gender identification model to be obtained gender recognition result, if gender is known
Other result is male, then shows the first picture, if gender recognition result is female, shows second picture；
Second subelement, for voice to be identified input gender identification model to be obtained gender recognition result, if gender is known
Other result is male, then shows third picture, if gender recognition result is female, shows the 4th picture.
Preferably, further include：Feature subelement；
Feature subelement, for carrying out feature extraction to voice to be identified by FBank feature extraction algorithm.
Preferably, further include：Endpoint subelement；
Endpoint subelement, for carrying out endpoint inspection to the voice to be identified after feature extraction by voice activity detection algorithm
It surveys.
Preferably, neural network model is LSTM neural network model.
As can be seen from the above technical solutions, the present invention has the following advantages that：
The present invention provides a kind of sound mural painting plane display methods, including：S1：Obtain the age training of the first preset quantity
The gender of voice and the second preset quantity trains voice；S2：First nerves network model is instructed by age training voice
It gets to age identification model, nervus opticus network model is trained by gender training voice to obtain gender identification mould
Type；S3：Voice to be identified input age identification model is obtained into age recognition result, voice to be identified input gender is identified into mould
Type obtains gender recognition result, shows corresponding picture according to age recognition result and gender recognition result.
The present invention establishes age identification model and gender identification model, carries out Application on Voiceprint Recognition judgement to voice to be identified and speaks
The age of people and gender, and then show corresponding pattern, it is unrelated with the decibel of sound in identification process, so speaker is without big
Sound is shouted, and reduces influence of the noise to surrounding in sound wall use process, and can show according to the difference of age and gender
Show different patterns, increase the diversity and interactivity of pattern, solves current sound wall and be easy to produce noise to surrounding
It impacts, and pattern is single, and lack of diversity and interactive technical problem.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention without any creative labor, may be used also for those of ordinary skill in the art
To obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of one embodiment of sound mural painting plane display method provided in an embodiment of the present invention；
Fig. 2 is a kind of another embodiment of sound mural painting plane display method provided in an embodiment of the present invention；
Fig. 3 is a kind of one embodiment of sound mural painting flat-panel display device provided in an embodiment of the present invention.
Specific embodiment
The embodiment of the invention provides a kind of sound mural painting plane display method and devices, solve current sound wall and are easy
It generates noise to impact surrounding, and pattern is single, and lack of diversity and interactive technical problem.
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that disclosed below
Embodiment be only a part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
Those of ordinary skill's all other embodiment obtained without making creative work, belongs to protection of the present invention
Range.
Referring to Fig. 1, the embodiment of the invention provides a kind of one embodiment of sound mural painting plane display method, including：
Step 101：Obtain the age training voice of the first preset quantity and the gender training voice of the second preset quantity；
It should be noted that needing first to obtain the first preset quantity before establishing age identification model and gender identification model
Age training voice and the second preset quantity gender training voice as training sample.
Step 102：First nerves network model is trained to obtain age identification model by age training voice, is led to
Gender training voice is crossed nervus opticus network model is trained to obtain gender identification model；
It should be noted that having obtained the gender training of the age training voice and the second preset quantity of the first preset quantity
After voice, first nerves network model can be trained to obtain age identification model by age training voice, passed through
Gender training voice is trained nervus opticus network model to obtain gender identification model.
Step 103：Voice to be identified input age identification model is obtained into age recognition result, voice to be identified is inputted
Gender identification model obtains gender recognition result, shows corresponding picture according to age recognition result and gender recognition result.
It should be noted that age recognition result is can be obtained into voice to be identified input age identification model, it will be to be identified
Gender recognition result can be obtained in voice input gender identification model, and the age of comprehensive speaker and gender show corresponding picture.
The present embodiment establishes age identification model and gender identification model, carries out Application on Voiceprint Recognition judgement to voice to be identified and says
Age and the gender of people are talked about, and then shows corresponding pattern, it is unrelated with the decibel of sound in identification process, so speaker is not necessarily to
It shouts, reduces influence of the noise to surrounding in sound wall use process, and can be with according to the difference of age and gender
It shows different patterns, increases the diversity and interactivity of pattern, solve current sound wall and be easy to produce noise to week
It encloses and impacts, and pattern is single, and lack of diversity and interactive technical problem.
The above are a kind of one embodiment of sound mural painting plane display method provided in an embodiment of the present invention, and the following are this hairs
A kind of another embodiment for sound mural painting plane display method that bright embodiment provides.
Referring to Fig. 2, the embodiment of the invention provides a kind of another embodiment of sound mural painting plane display method, packet
It includes：
Step 201：Obtain the age training voice of the first preset quantity and the gender training voice of the second preset quantity；
It should be noted that the first preset quantity and the second preset quantity can be determined according to the actual situation, such as
Obtain 1000 sections of age training voices and 1000 sections of gender training voices.
Age training voice and gender training voice have first been marked as prior information, such as 1000 sections of ages
Training voice may include 500 sections of voices for being noted as 40 years old people below, and 500 sections are noted as 40 years old or 40 years old or more
The voice of people, 1000 sections of gender training voices may include that 500 sections of voices for being noted as male and 500 sections are noted as women
Voice.
Step 202：First nerves network model is trained to obtain age identification model by age training voice, is led to
Gender training voice is crossed nervus opticus network model is trained to obtain gender identification model；
It should be noted that being trained to obtain age identification mould to first nerves network model by age training voice
Type is trained nervus opticus network model to obtain gender identification model by gender training voice.
Neural network model can select LSTM (Long Short-Term Memory, shot and long term note according to actual needs
Recall) neural network model, GRU (Gated Recurrent Unit, gating cycle) neural network model or RNN (Recurrent
Neural Network, circulation) models such as neural network model.
Step 203：Feature extraction is carried out to voice to be identified by FBank feature extraction algorithm；
It should be noted that FBank feature extraction algorithm is a kind of front-end processing algorithm, in a manner of being similar to human ear pair
Audio is handled, and the performance of speech recognition can be improved.
Voice to be identified is acquired by the sound pick-up of sound wall.
Step 204：End-point detection is carried out to the voice to be identified after feature extraction by voice activity detection algorithm；
It should be noted that voice activity detection (Voice Activity Detection, VAD) is also known as sound end inspection
It surveys or voice boundary is examined, refer to the presence or absence for detecting voice in noise circumstance, commonly used in voice coding, speech enhan-cement etc.
In speech processing system, playing reduces speech encoding rate, saves communication bandwidth, reduces energy consumption of mobile equipment and improve discrimination
The effects of.
Step 205：Voice to be identified input age identification model is obtained into age recognition result, judges age recognition result
Whether preset age threshold is greater than or equal to, if so, 206 are thened follow the steps, if it is not, thening follow the steps 207；
It should be noted that different age recognition methods can be used according to the mark difference of age training voice, such as
Fruit age training voice be only simply divided into two classes (such as 40 years old the following are one kind, 40 years old or be greater than 40 years old for one kind), that
Preset age threshold (such as with 40 years old for preset age threshold) can be set and judged whether judge age recognition result
More than or equal to preset age threshold, if so, 206 are thened follow the steps, if it is not, thening follow the steps 207.
If the age training voice can be divided into multiclass (such as 0 to 10 year old for one kind, 10 to 20 years old for one kind, 20 to 30 years old
For one kind etc.), then judge what age range speaker is in, different age ranges executes different steps.
Step 206：Voice to be identified input gender identification model is obtained into gender recognition result, if gender recognition result is
Male then shows the first picture, if gender recognition result is female, shows second picture；
It should be noted that when executing step 206, since current gender is broadly divided into male and two class of female, so wait know
Other voice input gender identification model obtains gender recognition result, if gender recognition result is male, the first picture is shown, if property
Other recognition result is female, then shows second picture.
Step 207：Voice to be identified input gender identification model is obtained into gender recognition result, if gender recognition result is
Male then shows third picture, if gender recognition result is female, shows the 4th picture.
It should be noted that voice to be identified input gender identification model is obtained gender identification when executing step 207
As a result, showing third picture if gender recognition result is male, if gender recognition result is female, the 4th picture is shown.
First picture, second picture, third picture and the 4th picture can according to all age group and property another characteristic into
Row selection, for example, the first picture can choose guest-welcoming pine picture, for indicating spy of 40 years old or more the man as pillar in family
Sign, second picture can choose the fresh flower picture to burst forth, 40 years old or more woman be likened into the fresh flower held, third picture can
To select love picture, man is filled with life vigor within expression 40 years old or less, and the 4th picture can choose the fresh flower that a bud just ready to burst
The youthful vigor of picture expression 40 years old or less woman.
The display of picture is shown by the LED screen of sound wall.
The present embodiment establishes age identification model and gender identification model, carries out Application on Voiceprint Recognition judgement to voice to be identified and says
Age and the gender of people are talked about, and then shows corresponding pattern, it is unrelated with the decibel of sound in identification process, so speaker is not necessarily to
It shouts, reduces influence of the noise to surrounding in sound wall use process.
And different patterns can be shown according to the difference of age and gender, increase the diversity and interaction of pattern
Property.
Neural network model can select LSTM neural network model, GRU neural network model or mind according to actual needs
Through models such as network models.
Feature extraction can also be carried out to voice to be identified by FBank feature extraction algorithm, pass through speech terminals detection
Algorithm to voice to be identified carry out end-point detection, reduce speech encoding rate, save communication bandwidth, reduce energy consumption of mobile equipment and
Improve discrimination.
In conclusion the sound mural painting plane display method of the present embodiment, which solves current sound wall, is easy to produce noise pair
Surrounding impacts, and pattern is single, and lack of diversity and interactive technical problem.
The above are a kind of another embodiments of sound mural painting plane display method provided in an embodiment of the present invention, and the following are this
A kind of one embodiment for sound mural painting flat-panel display device that inventive embodiments provide.
Referring to Fig. 3, the embodiment of the invention provides a kind of one embodiment of sound mural painting flat-panel display device, including：
Training acquiring unit 301, the property of age training voice and the second preset quantity for obtaining the first preset quantity
It Xun Lian not voice；
Model training unit 302, for being trained to obtain year to first nerves network model by age training voice
Age identification model is trained nervus opticus network model to obtain gender identification model by gender training voice；
Identify display unit 303, it, will be to for voice to be identified input age identification model to be obtained age recognition result
Identification voice input gender identification model obtains gender recognition result, is shown pair according to age recognition result and gender recognition result
The picture answered.
Further, identification display unit 303 specifically includes：
Age subelement 3031 judges for voice to be identified input age identification model to be obtained age recognition result
Whether age recognition result is greater than or equal to preset age threshold, if so, the first subelement 3032 of triggering, if it is not, then triggering
Second subelement 3033；
First subelement 3032, for voice to be identified input gender identification model to be obtained gender recognition result, if property
Other recognition result is male, then shows the first picture, if gender recognition result is female, shows second picture；
Second subelement 3033, for voice to be identified input gender identification model to be obtained gender recognition result, if property
Other recognition result is male, then shows third picture, if gender recognition result is female, shows the 4th picture.
Further, further include：Feature subelement 304；
Feature subelement 304, for carrying out feature extraction to voice to be identified by FBank feature extraction algorithm.
Further, further include：Endpoint subelement 305；
Endpoint subelement 305, for being held by voice activity detection algorithm to the voice to be identified after feature extraction
Point detection.
Further, neural network model is LSTM neural network model.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed system, device and method 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 a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit
It closes or communicates to connect, can be electrical property, mechanical or other forms.
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.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
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, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member 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 is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) executes the complete of each embodiment the method for the present invention
Portion or part steps.And storage medium above-mentioned includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although referring to before
Stating embodiment, invention is explained in detail, those skilled in the art should understand that：It still can be to preceding
Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features；And these
It modifies or replaces, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of sound mural painting plane display method, which is characterized in that including：
S1：Obtain the age training voice of the first preset quantity and the gender training voice of the second preset quantity；
S2：First nerves network model is trained to obtain age identification model by age training voice, is instructed by gender
Practice voice nervus opticus network model is trained to obtain gender identification model；
S3：Voice to be identified input age identification model is obtained into age recognition result, by voice to be identified input gender identification
Model obtains gender recognition result, shows corresponding picture according to age recognition result and gender recognition result.
2. a kind of sound mural painting plane display method according to claim 1, which is characterized in that step S3 is specifically included：
S31：Voice to be identified input age identification model is obtained into age recognition result, judges whether age recognition result is greater than
Or it is equal to preset age threshold, if so, S32 is thened follow the steps, if it is not, thening follow the steps S33；
S32：Voice to be identified input gender identification model is obtained into gender recognition result, if gender recognition result is male, is shown
Show the first picture, if gender recognition result is female, shows second picture；
S33：Voice to be identified input gender identification model is obtained into gender recognition result, if gender recognition result is male, is shown
Show third picture, if gender recognition result is female, shows the 4th picture.
3. a kind of sound mural painting plane display method according to claim 1, which is characterized in that after step S2, step S3
Further include before：Step S01；
S01：Feature extraction is carried out to voice to be identified by FBank feature extraction algorithm.
4. a kind of sound mural painting plane display method according to claim 3, which is characterized in that after step S01, step S3
Further include before：Step S02；
S02：End-point detection is carried out to the voice to be identified after feature extraction by voice activity detection algorithm.
5. a kind of sound mural painting plane display method according to claim 1, which is characterized in that neural network model LSTM
Neural network model.
6. a kind of sound mural painting flat-panel display device, which is characterized in that including：
Training acquiring unit, for obtaining the age training voice of the first preset quantity and the gender training language of the second preset quantity
Sound；
Model training unit obtains age identification mould for being trained by age training voice to first nerves network model
Type is trained nervus opticus network model to obtain gender identification model by gender training voice；
Display unit is identified, for voice to be identified input age identification model to be obtained age recognition result, by language to be identified
Sound input gender identification model obtains gender recognition result, shows corresponding figure according to age recognition result and gender recognition result
Piece.
7. a kind of sound mural painting flat-panel display device according to claim 6, which is characterized in that identification display unit specifically wraps
It includes：
Age subelement judges that the age identifies for voice to be identified input age identification model to be obtained age recognition result
As a result whether it is greater than or equal to preset age threshold, if so, the first subelement of triggering, if it is not, then triggering the second subelement；
First subelement, for voice to be identified input gender identification model to be obtained gender recognition result, if gender identification knot
Fruit is male, then shows the first picture, if gender recognition result is female, shows second picture；
Second subelement, for voice to be identified input gender identification model to be obtained gender recognition result, if gender identification knot
Fruit is male, then shows third picture, if gender recognition result is female, shows the 4th picture.
8. a kind of sound mural painting flat-panel display device according to claim 6, which is characterized in that further include：Feature subelement；
Feature subelement, for carrying out feature extraction to voice to be identified by FBank feature extraction algorithm.
9. a kind of sound mural painting flat-panel display device according to claim 8, which is characterized in that further include：Endpoint subelement；
Endpoint subelement, for carrying out end-point detection to the voice to be identified after feature extraction by voice activity detection algorithm.
10. a kind of sound mural painting flat-panel display device according to claim 6, which is characterized in that neural network model is
LSTM neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810732031.4A CN108847224A (en) | 2018-07-05 | 2018-07-05 | A kind of sound mural painting plane display method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810732031.4A CN108847224A (en) | 2018-07-05 | 2018-07-05 | A kind of sound mural painting plane display method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108847224A true CN108847224A (en) | 2018-11-20 |
Family
ID=64201569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810732031.4A Pending CN108847224A (en) | 2018-07-05 | 2018-07-05 | A kind of sound mural painting plane display method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108847224A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110211569A (en) * | 2019-07-09 | 2019-09-06 | 浙江百应科技有限公司 | Real-time gender identification method based on voice map and deep learning |
| CN110619889A (en) * | 2019-09-19 | 2019-12-27 | Oppo广东移动通信有限公司 | Sign data identification method and device, electronic equipment and storage medium |
| CN111128235A (en) * | 2019-12-05 | 2020-05-08 | 厦门快商通科技股份有限公司 | Age prediction method, device and equipment based on voice |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700843A (en) * | 2015-02-05 | 2015-06-10 | 海信集团有限公司 | Method and device for identifying ages |
| CN105319714A (en) * | 2014-07-31 | 2016-02-10 | 精工爱普生株式会社 | Display apparatus, method for controlling display apparatus, and program |
| CN105448214A (en) * | 2015-09-15 | 2016-03-30 | 北京合盒互动科技有限公司 | Advertisement display method and device of controllable electronic screen |
| CN105850115A (en) * | 2013-12-23 | 2016-08-10 | 三星电子株式会社 | Electronic apparatus and control method thereof |
| CN107871497A (en) * | 2016-09-23 | 2018-04-03 | 北京眼神科技有限公司 | Audio recognition method and device |
-
2018
- 2018-07-05 CN CN201810732031.4A patent/CN108847224A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105850115A (en) * | 2013-12-23 | 2016-08-10 | 三星电子株式会社 | Electronic apparatus and control method thereof |
| CN105319714A (en) * | 2014-07-31 | 2016-02-10 | 精工爱普生株式会社 | Display apparatus, method for controlling display apparatus, and program |
| CN104700843A (en) * | 2015-02-05 | 2015-06-10 | 海信集团有限公司 | Method and device for identifying ages |
| CN105448214A (en) * | 2015-09-15 | 2016-03-30 | 北京合盒互动科技有限公司 | Advertisement display method and device of controllable electronic screen |
| CN107871497A (en) * | 2016-09-23 | 2018-04-03 | 北京眼神科技有限公司 | Audio recognition method and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110211569A (en) * | 2019-07-09 | 2019-09-06 | 浙江百应科技有限公司 | Real-time gender identification method based on voice map and deep learning |
| CN110619889A (en) * | 2019-09-19 | 2019-12-27 | Oppo广东移动通信有限公司 | Sign data identification method and device, electronic equipment and storage medium |
| CN110619889B (en) * | 2019-09-19 | 2022-03-15 | Oppo广东移动通信有限公司 | Sign data identification method and device, electronic equipment and storage medium |
| CN111128235A (en) * | 2019-12-05 | 2020-05-08 | 厦门快商通科技股份有限公司 | Age prediction method, device and equipment based on voice |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109769099B (en) | Method and device for detecting abnormality of call person | |
| CN107481718B (en) | Audio recognition method, device, storage medium and electronic equipment | |
| CN105868827B (en) | A kind of multi-modal exchange method of intelligent robot and intelligent robot | |
| CN108847224A (en) | A kind of sound mural painting plane display method and device | |
| CN105047194B (en) | A kind of self study sound spectrograph feature extracting method for speech emotion recognition | |
| CN108417201B (en) | Single-channel multi-speaker identity recognition method and system | |
| CN108986835A (en) | Based on speech de-noising method, apparatus, equipment and the medium for improving GAN network | |
| CN108428446A (en) | Audio recognition method and device | |
| US8861779B2 (en) | Methods for electronically analysing a dialogue and corresponding systems | |
| US20110131041A1 (en) | Systems And Methods For Synthesis Of Motion For Animation Of Virtual Heads/Characters Via Voice Processing In Portable Devices | |
| CN109523616A (en) | A kind of FA Facial Animation generation method, device, equipment and readable storage medium storing program for executing | |
| CN108986798B (en) | Processing method, device and the equipment of voice data | |
| CN106683666B (en) | A kind of domain-adaptive method based on deep neural network | |
| CN106504768A (en) | Phone testing audio frequency classification method and device based on artificial intelligence | |
| CN110148399A (en) | A kind of control method of smart machine, device, equipment and medium | |
| US10755704B2 (en) | Information processing apparatus | |
| CN110865705A (en) | Multi-mode converged communication method and device, head-mounted equipment and storage medium | |
| CN111312218B (en) | Neural network training and voice endpoint detection method and device | |
| CN110610534A (en) | Automatic mouth shape animation generation method based on Actor-Critic algorithm | |
| CN110490428A (en) | Job of air traffic control method for evaluating quality and relevant apparatus | |
| Song et al. | Frustration recognition from speech during game interaction using wide residual networks | |
| CN111179915A (en) | Age identification method and device based on voice | |
| CN113555032A (en) | Multi-speaker scene recognition and network training method and device | |
| CN107910004A (en) | Voiced translation processing method and processing device | |
| CN109697978A (en) | Method and apparatus for generating model |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181120 |