CN107680599A - User property recognition methods, device and electronic equipment - Google Patents
User property recognition methods, device and electronic equipment Download PDFInfo
- Publication number
- CN107680599A CN107680599A CN201710898676.0A CN201710898676A CN107680599A CN 107680599 A CN107680599 A CN 107680599A CN 201710898676 A CN201710898676 A CN 201710898676A CN 107680599 A CN107680599 A CN 107680599A
- Authority
- CN
- China
- Prior art keywords
- user
- far field
- vocal print
- print feature
- score value
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/04—Training, enrolment or model building
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
Abstract
The present invention proposes a kind of user property recognition methods, device and electronic equipment, and this method includes receiving the speech data of user's input；The far field vocal print feature of speech data is determined, and determines score value of the far field vocal print feature based on preset model；The attribute of user is determined according to score value.The identification precision of user property can be lifted by the present invention.
Description
Technical field
The present invention relates to technical field of electronic equipment, more particularly to a kind of user property recognition methods, device and electronics to set
It is standby.
Background technology
In correlation technique, typically the semanteme of user voice data is identified.
The content of the invention
It is contemplated that at least solves one of technical problem in correlation technique to a certain extent.
Therefore, it is an object of the present invention to propose a kind of user property recognition methods, user property can be lifted
Identify precision.
It is another object of the present invention to propose a kind of user property identification device.
It is another object of the present invention to propose a kind of non-transitorycomputer readable storage medium.
It is another object of the present invention to propose a kind of computer program product.
To reach above-mentioned purpose, user property recognition methods that first aspect present invention embodiment proposes, including：Receive and use
The speech data of family input；The far field vocal print feature of the speech data is determined, and it is pre- to determine that the far field vocal print feature is based on
If the score value of model；The attribute of the user is determined according to the score value.
The user property recognition methods that first aspect present invention embodiment proposes, the voice number inputted by receiving user
According to, determine the far field vocal print feature of speech data, and determine score value of the far field vocal print feature based on preset model, and according to point
Value determines the attribute of user, can lift the identification precision of user property.
To reach above-mentioned purpose, user property identification device that second aspect of the present invention embodiment proposes, including：Receive mould
Block, for receiving the speech data of user's input；First determining module, for determining that the far field vocal print of the speech data is special
Sign, and determine the score value of the far field vocal print feature based on preset model；Second determining module, for being determined according to the score value
The attribute of the user.
The user property identification device that second aspect of the present invention embodiment proposes, the voice number inputted by receiving user
According to, determine the far field vocal print feature of speech data, and determine score value of the far field vocal print feature based on preset model, and according to point
Value determines the attribute of user, can lift the identification precision of user property.
To reach above-mentioned purpose, non-transitorycomputer readable storage medium that third aspect present invention embodiment proposes,
When the instruction in the storage medium is performed by the processor of mobile terminal so that mobile terminal is able to carry out a kind of user
Attribute recognition approach, methods described include：Receive the speech data of user's input；Determine that the far field vocal print of the speech data is special
Sign, and determine the score value of the far field vocal print feature based on preset model；The attribute of the user is determined according to the score value.
The non-transitorycomputer readable storage medium that third aspect present invention embodiment proposes, inputted by receiving user
Speech data, determine the far field vocal print feature of speech data, and determine score value of the far field vocal print feature based on preset model, with
And the attribute of user is determined according to score value, the identification precision of user property can be lifted.
To reach above-mentioned purpose, the computer program product that fourth aspect present invention embodiment proposes, when the computer
When instruction in program product is by computing device, a kind of user property recognition methods is performed, methods described includes：Receive user
The speech data of input；The far field vocal print feature of the speech data is determined, and it is default to determine that the far field vocal print feature is based on
The score value of model；The attribute of the user is determined according to the score value.
The computer program product that fourth aspect present invention embodiment proposes, the speech data inputted by receiving user,
The far field vocal print feature of speech data is determined, and determines score value of the far field vocal print feature based on preset model, and according to score value
The attribute of user is determined, the identification precision of user property can be lifted.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein：
Fig. 1 is the schematic flow sheet for the user property recognition methods that one embodiment of the invention proposes；
Fig. 2 is the schematic flow sheet for the user property recognition methods that another embodiment of the present invention proposes；
Fig. 3 is the schematic flow sheet for the user property recognition methods that another embodiment of the present invention proposes；
Fig. 4 is the structural representation for the user property identification device that one embodiment of the invention proposes；
Fig. 5 is the structural representation for the user property identification device that another embodiment of the present invention proposes.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, is only used for explaining the present invention, and is not considered as limiting the invention.On the contrary, this
All changes that the embodiment of invention includes falling into the range of the spirit and intension of attached claims, modification and equivalent
Thing.
Fig. 1 is the schematic flow sheet for the user property recognition methods that one embodiment of the invention proposes.
The present embodiment is configured as illustrating in user property identification device with the user property recognition methods.
User property identification device can be set in the server in the present embodiment, or can also be arranged on mobile device
In, the embodiment of the present invention is not restricted to this.
User property recognition methods in the embodiment of the present invention, for knowing in the application to the attribute of user
Not, the attribute of user can be, for example, sex or age, and this is not restricted.
Wherein, application program can refer to run software program on an electronic device, and electronic equipment is, for example, personal electricity
Brain (Personal Computer, PC), cloud device or mobile device, mobile device such as smart mobile phone, or flat board electricity
Brain etc..
It should be noted that the executive agent of the embodiment of the present invention, can be, for example, server or movement on hardware
Central processing unit (Central Processing Unit, CPU) in equipment, on software can be, for example, server or
The back-stage management service of application program in mobile device, is not restricted to this.
The embodiment of the present invention carries out example by voice service class application program of application program, and this is not restricted.
Referring to Fig. 1, this method includes：
S101：Receive the speech data of user's input.
For example, user can in voice service class application program one section of speech data of typing.
In correlation technique, typically the semanteme of user voice data is identified.And in an embodiment of the present invention, by
Differed in the vocal print feature of different user sound, therefore, speech data owning user can be identified according to far field vocal print feature
Attribute, can accurately identify user property.
Speech data can be, for example, that " how is the weather condition of today”.
S102：The far field vocal print feature of speech data is determined, and determines score value of the far field vocal print feature based on preset model.
Preset model therein is default gauss hybrid models, and the preset model pre-establishes.
The quantity of the default gauss hybrid models is at least two, and user corresponding to different default gauss hybrid models belongs to
Property is identical or differs.
Far field vocal print feature therein can be specially mel-frequency cepstrum coefficient feature, and this is not restricted.
Alternatively, referring to Fig. 2, score value of the far field vocal print feature based on preset model is determined, including：
S201：Determine conditional probability function of the far field vocal print feature based on each preset model.
S202：Far field vocal print feature is given a mark according to each conditional probability function, obtained and each preset model pair
The score value answered.
In the case where the quantity of default gauss hybrid models is at least two, it may be determined that far field vocal print feature is based on every
The conditional probability function of individual preset model, then, far field vocal print feature is given a mark according to each conditional probability function, obtained
Score value corresponding with each preset model, i.e. score value of the far field vocal print feature on the basis of each preset model, due to presetting mould
Type is to be pre-established previously according to the far field vocal print feature of user's sample voice data, therefore, by determining that far field vocal print is special
The score value on the basis of each preset model is levied, so as to subsequently demarcate the attribute of user according to the score value, user's category can be lifted
Property identification precision, also, due to far field vocal print feature collection be relatively easy to, therefore, method for improving perform simplification, section
About hardware layout cost.
S103：The attribute of user is determined according to score value.
Attribute therein is sex and/or age, or or user voice data in the intonation demarcated, it is right
This is not restricted.
Alternatively, it will be worth belonging to preset model corresponding to the score value of maximum and belong in score value corresponding with each preset model
Attribute of the property as user.
Or also can be by score value corresponding to each preset model, value is more than pre- corresponding to the score value of a predetermined threshold value
If attribute of the affiliated attribute of model as optional user, then, continue value being more than the score value of predetermined threshold value and multiple default
The matching of model is demarcated, so as to therefrom determine a target score, and using attribute corresponding to the target score as
The attribute of user, this is not restricted.
By will directly be worth belonging to preset model corresponding to the score value of maximum and belong in score value corresponding with each preset model
Property attribute as user, it is simple easily to realize, and recognition effect is preferable.
In the present embodiment, by receiving the speech data of user's input, the far field vocal print feature of speech data is determined, and really
Score value of the Dingyuan field vocal print feature based on preset model, and the attribute of user is determined according to score value, user property can be lifted
Identification precision.
Fig. 3 is the schematic flow sheet for the user property recognition methods that another embodiment of the present invention proposes.
Before above-mentioned S101, preset model can also be established by following steps, including：
S301：The data of different attribute user are gathered as sample data.
S302：It is determined that far field corresponding with every sample data vocal print feature.
S303：Model training is carried out to gauss hybrid models according to corresponding far field vocal print feature, obtained and different attribute
Corresponding gauss hybrid models, as default gauss hybrid models.
Alternatively, model training is carried out to gauss hybrid models according to corresponding far field vocal print feature, including：According to corresponding
Far field vocal print feature, using expectation-maximization algorithm to gauss hybrid models carry out model training.
In an embodiment of the present invention, the quantity of gauss hybrid models corresponding with different attribute can be multiple to enter one
Step ground, the quantity of gauss hybrid models corresponding with identical attribute can also be multiple, by training multiple default Gausses to mix
Matched moulds type, characteristic matchings can be carried out based on multiple default gauss hybrid models, from another dimension it is determined that during user property
Degree has ensured Attribute Recognition precision.
By using expectation-maximization algorithm to gauss hybrid models carry out model training, can establish more match it is pre-
If model, and then, lift the identification precision of user property.
In the present embodiment, be used as sample data by the data for gathering different attribute user, it is determined that with every sample data
Corresponding far field vocal print feature, and model training is carried out to gauss hybrid models according to corresponding far field vocal print feature, obtain
Gauss hybrid models corresponding with different attribute, as default gauss hybrid models, by training multiple default Gaussian Mixture moulds
Type, it can carry out characteristic matchings it is determined that when user property based on multiple default gauss hybrid models, protected from another dimension
Attribute Recognition precision is hindered.
Fig. 4 is the structural representation for the user property identification device that one embodiment of the invention proposes.
Referring to Fig. 4, the device 400 includes：
Receiving module 401, for receiving the speech data of user's input.
First determining module 402, for determining the far field vocal print feature of speech data, and determine that far field vocal print feature is based on
The score value of preset model.
Second determining module 403, for determining the attribute of user according to score value.
Alternatively, in some embodiments, referring to Fig. 5, preset model is default gauss hybrid models, in addition to：3rd is true
Cover half block 404, wherein,
3rd determining module 404, for gathering the data of different attribute user as sample data, and determine with per galley proof
Far field vocal print feature corresponding to notebook data, and model instruction is carried out to gauss hybrid models according to corresponding far field vocal print feature
Practice, gauss hybrid models corresponding with different attribute are obtained, as default gauss hybrid models.
Alternatively, in some embodiments, the 3rd determining module 404, it is specifically used for：
According to corresponding far field vocal print feature, model training is carried out to gauss hybrid models using expectation-maximization algorithm.
Alternatively, in some embodiments, the first determining module 402, it is specifically used for：
Determine conditional probability function of the far field vocal print feature based on each preset model；
Far field vocal print feature is given a mark according to each conditional probability function, obtains corresponding with each preset model point
Value.
Alternatively, in some embodiments, the second determining module 403, it is specifically used for：
The affiliated attribute of preset model corresponding to the score value of maximum will be worth as using in score value corresponding with each preset model
The attribute at family.
Alternatively, in some embodiments, attribute is sex and/or age.
It should be noted that the explanation in earlier figures 1- Fig. 3 embodiments to user property recognition methods embodiment
Suitable for the user property identification device 400 of the embodiment, its realization principle is similar, and here is omitted.
In the present embodiment, by receiving the speech data of user's input, the far field vocal print feature of speech data is determined, and really
Score value of the Dingyuan field vocal print feature based on preset model, and the attribute of user is determined according to score value, user property can be lifted
Identification precision.
In order to realize above-described embodiment, the present invention also proposes a kind of non-transitorycomputer readable storage medium, works as storage
Instruction in medium by terminal computing device when so that terminal is able to carry out a kind of user property recognition methods, method bag
Include：
Receive the speech data of user's input；
The far field vocal print feature of speech data is determined, and determines score value of the far field vocal print feature based on preset model；
The attribute of user is determined according to score value.
Non-transitorycomputer readable storage medium in the present embodiment, the speech data inputted by receiving user, really
Determine the far field vocal print feature of speech data, and determine score value of the far field vocal print feature based on preset model, and it is true according to score value
Determine the attribute of user, the identification precision of user property can be lifted.
In order to realize above-described embodiment, the present invention also proposes a kind of computer program product, when in computer program product
Instruction when being executed by processor, perform a kind of user property recognition methods, method includes：
Receive the speech data of user's input；
The far field vocal print feature of speech data is determined, and determines score value of the far field vocal print feature based on preset model；
The attribute of user is determined according to score value.
Computer program product in the present embodiment, the speech data inputted by receiving user, determines speech data
Far field vocal print feature, and score value of the far field vocal print feature based on preset model is determined, and the attribute of user is determined according to score value,
The identification precision of user property can be lifted.
It should be noted that in the description of the invention, term " first ", " second " etc. are only used for describing purpose, without
It is understood that to indicate or implying relative importance.In addition, in the description of the invention, unless otherwise indicated, the implication of " multiple "
It is two or more.
Any process or method described otherwise above description in flow chart or herein is construed as, and represents to include
Module, fragment or the portion of the code of the executable instruction of one or more the step of being used to realize specific logical function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage
Or firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized：With the logic gates for realizing logic function to data-signal
Discrete logic, have suitable combinational logic gate circuit application specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method carries
Suddenly it is that by program the hardware of correlation can be instructed to complete, described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing module, can also
That unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
Block can both be realized in the form of hardware, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and as independent production marketing or in use, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Necessarily refer to identical embodiment or example.Moreover, specific features, structure, material or the feature of description can be any
One or more embodiments or example in combine in an appropriate manner.
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, one of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changed, replacing and modification.
Claims (14)
1. a kind of user property recognition methods, it is characterised in that comprise the following steps：
Receive the speech data of user's input；
The far field vocal print feature of the speech data is determined, and determines the score value of the far field vocal print feature based on preset model；
The attribute of the user is determined according to the score value.
2. user property recognition methods as claimed in claim 1, it is characterised in that the preset model is default Gaussian Mixture
Model, the default gauss hybrid models determine in the following manner；
The data of different attribute user are gathered as sample data；
It is determined that far field corresponding with every sample data vocal print feature；
Model training is carried out to gauss hybrid models according to the corresponding far field vocal print feature, obtained and the different attribute pair
The gauss hybrid models answered, as the default gauss hybrid models.
3. user property recognition methods as claimed in claim 2, it is characterised in that described according to the corresponding far field vocal print
Feature carries out model training to gauss hybrid models, including：
According to the corresponding far field vocal print feature, model training is carried out to gauss hybrid models using expectation-maximization algorithm.
4. user property recognition methods as claimed in claim 1, it is characterised in that described to determine the far field vocal print feature base
In the score value of preset model, including：
Determine the conditional probability function of the far field vocal print feature based on each preset model；
The far field vocal print feature is given a mark according to each conditional probability function, obtained corresponding with each preset model
Score value.
5. user property recognition methods as claimed in claim 4, it is characterised in that described that the use is determined according to the score value
The attribute at family, including：
By in the score value corresponding with each preset model, it is worth the affiliated attribute of preset model corresponding to the score value of maximum and makees
For the attribute of the user.
6. the user property recognition methods as described in claim any one of 1-5, it is characterised in that the attribute be sex and/
Or the age.
A kind of 7. user property identification device, it is characterised in that including：
Receiving module, for receiving the speech data of user's input；
First determining module, for determining the far field vocal print feature of the speech data, and determine the far field vocal print feature base
In the score value of preset model；
Second determining module, for determining the attribute of the user according to the score value.
8. user property identification device as claimed in claim 7, it is characterised in that the preset model is default Gaussian Mixture
Model, in addition to：3rd determining module, wherein,
3rd determining module, for gathering the data of different attribute user as sample data, and determine and every sample
Far field vocal print feature corresponding to data, and model instruction is carried out to gauss hybrid models according to the corresponding far field vocal print feature
Practice, gauss hybrid models corresponding with the different attribute are obtained, as the default gauss hybrid models.
9. user property identification device as claimed in claim 8, it is characterised in that the 3rd determining module, be specifically used for：
According to the corresponding far field vocal print feature, model training is carried out to gauss hybrid models using expectation-maximization algorithm.
10. user property identification device as claimed in claim 7, it is characterised in that first determining module is specific to use
In：
Determine the conditional probability function of the far field vocal print feature based on each preset model；
The far field vocal print feature is given a mark according to each conditional probability function, obtained corresponding with each preset model
Score value.
11. user property identification device as claimed in claim 10, it is characterised in that second determining module is specific to use
In：
By in the score value corresponding with each preset model, it is worth the affiliated attribute of preset model corresponding to the score value of maximum and makees
For the attribute of the user.
12. the user property identification device as described in claim any one of 7-11, it is characterised in that the attribute is sex
And/or the age.
13. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, it is characterised in that the program
The user property recognition methods as any one of claim 1-6 is realized when being executed by processor.
14. a kind of computer program product, when the instruction in the computer program product is by computing device, perform one kind
User property recognition methods, methods described include：
Receive the speech data of user's input；
The far field vocal print feature of the speech data is determined, and determines the score value of the far field vocal print feature based on preset model；
The attribute of the user is determined according to the score value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710898676.0A CN107680599A (en) | 2017-09-28 | 2017-09-28 | User property recognition methods, device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710898676.0A CN107680599A (en) | 2017-09-28 | 2017-09-28 | User property recognition methods, device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107680599A true CN107680599A (en) | 2018-02-09 |
Family
ID=61138299
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710898676.0A Pending CN107680599A (en) | 2017-09-28 | 2017-09-28 | User property recognition methods, device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107680599A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109841218A (en) * | 2019-01-31 | 2019-06-04 | 北京声智科技有限公司 | A kind of voiceprint registration method and device for far field environment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1543641A (en) * | 2001-06-19 | 2004-11-03 | �������ֿ� | Speaker recognition systems |
| CN101178897A (en) * | 2007-12-05 | 2008-05-14 | 浙江大学 | Speaking man recognizing method using base frequency envelope to eliminate emotion voice |
| CN102262440A (en) * | 2010-06-11 | 2011-11-30 | 微软公司 | Multi-modal gender recognition |
| CN102834842A (en) * | 2010-03-23 | 2012-12-19 | 诺基亚公司 | Method and apparatus for determining a user age range |
| CN103310788A (en) * | 2013-05-23 | 2013-09-18 | 北京云知声信息技术有限公司 | Voice information identification method and system |
| CN103943104A (en) * | 2014-04-15 | 2014-07-23 | 海信集团有限公司 | Voice information recognition method and terminal equipment |
| CN104700843A (en) * | 2015-02-05 | 2015-06-10 | 海信集团有限公司 | Method and device for identifying ages |
| CN105700682A (en) * | 2016-01-08 | 2016-06-22 | 北京乐驾科技有限公司 | Intelligent gender and emotion recognition detection system and method based on vision and voice |
| CN105761720A (en) * | 2016-04-19 | 2016-07-13 | 北京地平线机器人技术研发有限公司 | Interaction system based on voice attribute classification, and method thereof |
-
2017
- 2017-09-28 CN CN201710898676.0A patent/CN107680599A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1543641A (en) * | 2001-06-19 | 2004-11-03 | �������ֿ� | Speaker recognition systems |
| CN101178897A (en) * | 2007-12-05 | 2008-05-14 | 浙江大学 | Speaking man recognizing method using base frequency envelope to eliminate emotion voice |
| CN102834842A (en) * | 2010-03-23 | 2012-12-19 | 诺基亚公司 | Method and apparatus for determining a user age range |
| CN102262440A (en) * | 2010-06-11 | 2011-11-30 | 微软公司 | Multi-modal gender recognition |
| CN103310788A (en) * | 2013-05-23 | 2013-09-18 | 北京云知声信息技术有限公司 | Voice information identification method and system |
| CN103943104A (en) * | 2014-04-15 | 2014-07-23 | 海信集团有限公司 | Voice information recognition method and terminal equipment |
| CN104700843A (en) * | 2015-02-05 | 2015-06-10 | 海信集团有限公司 | Method and device for identifying ages |
| CN105700682A (en) * | 2016-01-08 | 2016-06-22 | 北京乐驾科技有限公司 | Intelligent gender and emotion recognition detection system and method based on vision and voice |
| CN105761720A (en) * | 2016-04-19 | 2016-07-13 | 北京地平线机器人技术研发有限公司 | Interaction system based on voice attribute classification, and method thereof |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109841218A (en) * | 2019-01-31 | 2019-06-04 | 北京声智科技有限公司 | A kind of voiceprint registration method and device for far field environment |
| CN109841218B (en) * | 2019-01-31 | 2020-10-27 | 北京声智科技有限公司 | Voiceprint registration method and device for far-field environment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109658938A (en) | The method, apparatus of voice and text matches, equipment and computer-readable medium | |
| CN109145204B (en) | Portrait label generation and use method and system | |
| CN111078887B (en) | Text classification method and device | |
| CN103970743B (en) | A kind of recommendation method for personalized information, system and search engine in the search | |
| CN106997342B (en) | Intention identification method and device based on multi-round interaction | |
| CN110222330B (en) | Semantic recognition method and device, storage medium and computer equipment | |
| CN110196948A (en) | Content recommendation method and device, computer equipment and storage medium | |
| CN107679564A (en) | Sample data recommends method and its device | |
| CN109308895A (en) | Acoustic training model method, apparatus, equipment and computer-readable medium | |
| US20210383793A1 (en) | Information presentation device, and information presentation method | |
| CN110070140A (en) | Method and device is determined based on user's similitude of multi-class information | |
| CN102741861B (en) | Cross the image identification system of complete dictionary based on cascade | |
| CN111243604B (en) | Training method for speaker recognition neural network model supporting multiple awakening words, speaker recognition method and system | |
| CN107844531B (en) | Answer output method and device and computer equipment | |
| CN113947693A (en) | Method and device for obtaining target object recognition model and electronic equipment | |
| CN114626380A (en) | Entity identification method and device, electronic equipment and storage medium | |
| CN111210840A (en) | Age prediction method, device and equipment | |
| CN107680599A (en) | User property recognition methods, device and electronic equipment | |
| CN111949793B (en) | User intention recognition method and device and terminal equipment | |
| CN111931491B (en) | Domain dictionary construction method and device | |
| CN109543187B (en) | Method and device for generating electronic medical record characteristics and storage medium | |
| CN111261196A (en) | Age estimation method, device and equipment | |
| CN109726726B (en) | Event detection method and device in video | |
| CN110619090A (en) | Regional attraction assessment method and device | |
| WO2022141867A1 (en) | Speech recognition method and apparatus, and electronic device and readable storage medium |
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 |
Application publication date: 20180209 |
|
| RJ01 | Rejection of invention patent application after publication |