CN110136717A - Voice recognition processing method, apparatus, system and vehicle - Google Patents
Voice recognition processing method, apparatus, system and vehicle Download PDFInfo
- Publication number
- CN110136717A CN110136717A CN201910429228.5A CN201910429228A CN110136717A CN 110136717 A CN110136717 A CN 110136717A CN 201910429228 A CN201910429228 A CN 201910429228A CN 110136717 A CN110136717 A CN 110136717A
- Authority
- CN
- China
- Prior art keywords
- speech recognition
- voice
- cloud platform
- result
- voice data
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 25
- 238000012360 testing method Methods 0.000 claims abstract description 42
- 238000004458 analytical method Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims description 22
- 238000011990 functional testing Methods 0.000 claims description 6
- 238000011056 performance test Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000000034 method Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012827 research and development 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
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Navigation (AREA)
Abstract
The invention proposes a kind of voice recognition processing method, apparatus, system and vehicle, which includes: the voice data for obtaining different user under different recording conditions；Voice data is input to tested square cloud platform；Tested square cloud platform is obtained to the speech recognition result and speech recognition parameter of voice data；Analysis comparison is carried out to speech recognition result and speech recognition parameter, generates test result；Adjustment is optimized according to platform parameters of the test result to tested side's cloud platform, and returns to execution and voice data is input to tested square cloud platform step, the speech recognition result after being optimized.Voice recognition processing method, apparatus, system and vehicle of the invention can comprehensively, objectively assess tested side's cloud platform；Meanwhile adjustment can also be optimized to the platform parameters of tested side's cloud platform according to test result.
Description
Technical field
The present invention relates to voice technology field more particularly to a kind of voice recognition processing method, apparatus, system and vehicle.
Background technique
It is more and more for the vehicle-mounted speech recognition platforms used currently on the market, Iflytek, Baidu, Tencent, Yun Zhi
Tens company such as sound can provide speech recognition platforms.The discrimination for the speech recognition platforms that different company provides, identification effect
Rate, the system that can be docked are had nothing in common with each other.And as vehicle manufacturer, it is typically only capable to enough by the description of supplier to different languages
Sound identifying platform carries out subjective evaluation, can not carry out comprehensive, objective assessment to different speech recognition platforms.
Summary of the invention
The present invention is directed to solve at least some of the technical problems in related technologies.
For this purpose, the first purpose of this invention is to propose a kind of voice recognition processing method, the relatively more tested side of analysis
For cloud platform to the speech recognition result and speech recognition parameter of voice data, generating test result can be complete according to test result
Tested side's cloud platform is objectively assessed in face；Meanwhile it can also be to the platform of tested side's cloud platform according to test result
Parameter optimizes adjustment.
Second object of the present invention is to propose a kind of voice recognition processing device.
Third object of the present invention is to propose a kind of speech recognition processing system.
Fourth object of the present invention is to propose a kind of vehicle.
In order to achieve the above object, first aspect present invention embodiment proposes a kind of voice recognition processing method, comprising:
Obtain the voice data of different user under different recording conditions；
The voice data is input to tested square cloud platform；
Tested side's cloud platform is obtained to the speech recognition result and speech recognition parameter of the voice data；
Analysis comparison is carried out to institute's speech recognition result and the speech recognition parameter, generates test result；
Adjustment is optimized according to platform parameters of the test result to tested side's cloud platform, and is returned described in execution
The voice data is input to tested square cloud platform step, the speech recognition result after being optimized.
The voice recognition processing method proposed according to embodiments of the present invention, obtains the language of different user under different recording conditions
Sound data；Voice data is input to tested square cloud platform；Obtain speech recognition of the tested square cloud platform to voice data
And speech recognition parameter as a result；Analysis comparison is carried out to speech recognition result and speech recognition parameter, generates test result；According to
Test result optimizes adjustment to the platform parameters of tested side's cloud platform, and return execution voice data is input to it is tested
Examination side's cloud platform step, the speech recognition result after being optimized.According to test result, can comprehensively, objectively to tested side
Cloud platform is assessed；Meanwhile adjustment can also be optimized to the platform parameters of tested side's cloud platform according to test result.
According to one embodiment of present invention, the recording conditions include the group of any one or more in the following conditions
It closes: voice content, gender, speed, section information, password and vehicle.
According to one embodiment of present invention, the speech recognition parameter includes any one or more in following parameter
Combination: starting time, recognition time, CPU usage and memory usage.
According to one embodiment of present invention, the test result includes functional test results and/or the performance test results.
According to one embodiment of present invention, the functional test results include any one or more in following result
Combination: dialogue ability, function dimension, memory capability and learning ability；The performance test results include in following result
The combination of any one or more: discrimination, recognition speed, starting speed, memory consumption and CPU consumption.
According to one embodiment of present invention, voice recognition processing method further include: according to the speech recognition after optimization
As a result, determining user preference；Corresponding content-data is pushed to the user according to the user preference.
According to one embodiment of present invention, the content-data includes the group of any one or more in following data
Close: director data, voice data and picture indicate data.
In order to achieve the above object, second aspect of the present invention embodiment proposes a kind of voice recognition processing device, comprising:
First obtains module, for obtaining the voice data of different user under different recording conditions；
Input module, for the voice data to be input to tested square cloud platform；
Second obtains module, for obtain tested side's cloud platform to the speech recognition result of the voice data and
Speech recognition parameter；
Generation module is generated and is surveyed for carrying out analysis comparison to institute's speech recognition result and the speech recognition parameter
Test result；
Module is adjusted, for optimizing adjustment according to platform parameters of the test result to tested side's cloud platform,
And trigger the input module re-execute it is described the voice data is input to tested square cloud platform step, optimized
Speech recognition result afterwards.
The voice recognition processing device proposed according to embodiments of the present invention, obtains the language of different user under different recording conditions
Sound data；Voice data is input to tested square cloud platform；Obtain speech recognition of the tested square cloud platform to voice data
And speech recognition parameter as a result；Analysis comparison is carried out to speech recognition result and speech recognition parameter, generates test result；According to
Test result optimizes adjustment to the platform parameters of tested side's cloud platform, and return execution voice data is input to it is tested
Examination side's cloud platform step, the speech recognition result after being optimized.According to test result, can comprehensively, objectively to tested side
Cloud platform is assessed；Meanwhile adjustment can also be optimized to the platform parameters of tested side's cloud platform according to test result.
In order to achieve the above object, third aspect present invention embodiment proposes a kind of speech recognition processing system, comprising: vehicle device
Sound pick-up outfit and the voice recognition processing device as described in second aspect of the present invention embodiment；The voice recognition processing device is logical
It crosses the vehicle device sound pick-up outfit and obtains the voice data.
In order to achieve the above object, fourth aspect present invention embodiment proposes a kind of vehicle, comprising: such as third aspect present invention
Speech recognition processing system described in embodiment.
Detailed description of the invention
Fig. 1 is the flow chart of voice recognition processing method according to an embodiment of the invention；
Fig. 2 is the schematic diagram according to an embodiment of the invention for obtaining voice data；
Fig. 3 is the System Working Principle figure of voice recognition processing method according to an embodiment of the invention；
Fig. 4 is the flow chart of voice recognition processing method in accordance with another embodiment of the present invention；
Fig. 5 is the System Working Principle figure of voice recognition processing method in accordance with another embodiment of the present invention；
Fig. 6 is the structure chart of voice recognition processing device according to an embodiment of the invention；
Fig. 7 is the structure chart of speech recognition processing system according to an embodiment of the invention；
Fig. 8 is the structure chart of vehicle according to an embodiment of the invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to is used to explain the present invention, and is not considered as limiting the invention.
Voice recognition processing method, apparatus, system and the vehicle of the embodiment of the present invention described with reference to the accompanying drawing.
Fig. 1 is the flow chart of voice recognition processing method according to an embodiment of the invention, as shown in Figure 1, this method
Include:
S101 obtains the voice data of different user under different recording conditions.
, can be by vehicle device sound pick-up outfit in the embodiment of the present invention, such as microphone etc. obtains different under different recording conditions
The voice data of user.Wherein, recording conditions may include appointing in voice content, gender, speed, section information, password and vehicle
It anticipates one or more combinations.
Specifically, can as shown in Fig. 2, voice data can be speech database form, according to recording conditions, the way of recording and
Sound template generates.Wherein, the way of recording is recorded by the way of, for example, recorded using practical vehicle device microphone, and
Recording is carried out using same platform to go echo processing；Sound template inputs text, such as with function control or merely
The relevant text such as it.
Voice data is input to tested square cloud platform by S102.
In the embodiment of the present invention, voice data is input to tested square cloud platform.Specifically, can be as shown in figure 3, passing through
Voice data is input to tested square cloud platform by the voice input and output control interface in test platform.
S103 obtains tested square cloud platform to the speech recognition result and speech recognition parameter of voice data.
In the embodiment of the present invention, obtains tested square cloud platform and the speech recognition result of voice data and speech recognition are joined
Number obtains specifically, interface can be obtained by recognition result as shown in Figure 3.Wherein, speech recognition parameter includes following parameter
In the combination of any one or more: starting time, recognition time, CPU usage and memory usage.CPU usage and
Memory usage can pass through the third party software development kit (Software in test platform as shown in Figure 3
Development Kit, abbreviation SDK) it is calculated.
S104 carries out analysis comparison to speech recognition result and speech recognition parameter, generates test result.
In the embodiment of the present invention, analysis comparison is carried out to speech recognition result and speech recognition parameter, generates test result.
Wherein, test result may include functional test results and/or the performance test results, and functional test results may include following result again
In the combination of any one or more: dialogue ability, function dimension, memory capability and learning ability；The performance test results are again
It may include the combination of any one or more in following result: discrimination, recognition speed, starting speed, memory consumption and CPU
Consumption.
S105 optimizes adjustment according to platform parameters of the test result to tested side's cloud platform, and returns and execute general
Voice data is input to tested square cloud platform step, the speech recognition result after being optimized.
In the embodiment of the present invention, adjustment is optimized according to platform parameters of the test result to tested side's cloud platform, and
Return step S102 is executed voice data being input to tested square cloud platform step, the speech recognition result after being optimized.
For example, being optimized when the discrimination of some entry in test result is lower to the platform parameters of tested side's cloud platform
Adjustment, to improve the discrimination of the entry.
The voice recognition processing method proposed according to embodiments of the present invention, obtains the language of different user under different recording conditions
Sound data；Voice data is input to tested square cloud platform；Obtain speech recognition of the tested square cloud platform to voice data
And speech recognition parameter as a result；Analysis comparison is carried out to speech recognition result and speech recognition parameter, generates test result；According to
Test result optimizes adjustment to the platform parameters of tested side's cloud platform, and return execution voice data is input to it is tested
Examination side's cloud platform step, the speech recognition result after being optimized.According to test result, can comprehensively, objectively to tested side
Cloud platform is assessed；Meanwhile adjustment can also be optimized to the platform parameters of tested side's cloud platform according to test result.
Further, as shown in figure 4, Fig. 4 is the stream of voice recognition processing method in accordance with another embodiment of the present invention
Cheng Tu, this method may also include that
S201 determines user preference according to the speech recognition result after optimization.
In the embodiment of the present invention, according to the speech recognition result after optimization, user preference is determined.
S202 pushes corresponding content-data to user according to user preference.
In the embodiment of the present invention, corresponding content-data is pushed to user according to user preference.Wherein, content-data includes
The combination of any one or more in following data: director data, voice data and picture indicate data.
Specifically, can be as shown in figure 5, unified third party cloud platform, and vehicle manufacturer internal cloud platform, carshop is added
Cloud platform collects and stores user preference inside quotient, and vehicle manufacturer internal cloud platform obtains vehicle information and recording number from vehicle device
According to, and it is uploaded to third party cloud platform, recognition result, which is obtained, according to recognition result and user preference pushes corresponding content number
According to vehicle device.Meanwhile also any modification can not be made to vehicle device under the premise of, automatically switch identification engine company provide algorithm,
Reduce research and development cost.
The voice recognition processing method proposed according to embodiments of the present invention, can be according to the speech recognition result after optimization, really
User preference is made, and corresponding content-data is pushed to user according to user preference.
Fig. 6 is the structure chart of voice recognition processing device according to an embodiment of the invention, as shown in fig. 6, the device
Include:
First obtains module 21, for obtaining the voice data of different user under different recording conditions；
Input module 22, for voice data to be input to tested square cloud platform；
Second obtains module 23, knows for obtaining tested square cloud platform to the speech recognition result and voice of voice data
Other parameter；
Generation module 24 generates test result for carrying out analysis comparison to speech recognition result and speech recognition parameter；
Module 25 is adjusted, for optimizing adjustment according to platform parameters of the test result to tested side's cloud platform, and
Triggering input module 22 re-executes voice data being input to tested square cloud platform step, the speech recognition after being optimized
As a result.
It should be noted that the aforementioned explanation to voice recognition processing embodiment of the method is also applied for the embodiment
Voice recognition processing device, details are not described herein again.
The voice recognition processing device proposed according to embodiments of the present invention, obtains the language of different user under different recording conditions
Sound data；Voice data is input to tested square cloud platform；Obtain speech recognition of the tested square cloud platform to voice data
And speech recognition parameter as a result；Analysis comparison is carried out to speech recognition result and speech recognition parameter, generates test result；According to
Test result optimizes adjustment to the platform parameters of tested side's cloud platform, and return execution voice data is input to it is tested
Examination side's cloud platform step, the speech recognition result after being optimized.According to test result, can comprehensively, objectively to tested side
Cloud platform is assessed；Meanwhile adjustment can also be optimized to the platform parameters of tested side's cloud platform according to test result.
In order to realize above-described embodiment, the embodiment of the present invention also proposes a kind of speech recognition processing system 30, such as Fig. 7 institute
Show, comprising: vehicle device sound pick-up outfit 31 and the voice recognition processing device 32 as shown in above-described embodiment.
In order to realize above-described embodiment, the embodiment of the present invention also proposes a kind of vehicle 33, as shown in Figure 8, comprising: as above state
Speech recognition processing system 30 shown in embodiment.
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 spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
It can be combined in any suitable manner in a or multiple embodiment or examples.In addition, without conflicting with each other, the technology of this field
The feature of different embodiments or examples described in this specification and different embodiments or examples can be combined by personnel
And combination.
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (10)
1. a kind of voice recognition processing method characterized by comprising
Obtain the voice data of different user under different recording conditions；
The voice data is input to tested square cloud platform；
Tested side's cloud platform is obtained to the speech recognition result and speech recognition parameter of the voice data；
Analysis comparison is carried out to institute's speech recognition result and the speech recognition parameter, generates test result；
Adjustment is optimized according to platform parameters of the test result to tested side's cloud platform, and it is described by institute to return to execution
It states voice data and is input to tested square cloud platform step, the speech recognition result after being optimized.
2. voice recognition processing method according to claim 1, which is characterized in that the recording conditions include the following conditions
In the combination of any one or more:
Voice content, gender, speed, section information, password and vehicle.
3. voice recognition processing method according to claim 1, which is characterized in that the speech recognition parameter includes following
The combination of any one or more in parameter:
Start time, recognition time, CPU usage and memory usage.
4. voice recognition processing method according to claim 1, which is characterized in that the test result includes functional test
And/or the performance test results as a result.
5. voice recognition processing method according to claim 4, which is characterized in that the functional test results include following
As a result the combination of any one or more in: dialogue ability, function dimension, memory capability and learning ability；
The performance test results include the combination of any one or more in following result: discrimination, recognition speed, starting
Speed, memory consumption and CPU consumption.
6. voice recognition processing method according to claim 1, which is characterized in that further include:
According to the speech recognition result after optimization, user preference is determined；
Corresponding content-data is pushed to the user according to the user preference.
7. voice recognition processing method according to claim 6, which is characterized in that the content-data includes following data
In the combination of any one or more:
Director data, voice data and picture indicate data.
8. a kind of voice recognition processing device characterized by comprising
First obtains module, for obtaining the voice data of different user under different recording conditions；
Input module, for the voice data to be input to tested square cloud platform；
Second obtains module, for obtaining tested side's cloud platform to the speech recognition result and voice of the voice data
Identification parameter；
Generation module generates test knot for carrying out analysis comparison to institute's speech recognition result and the speech recognition parameter
Fruit；
Module is adjusted, for optimizing adjustment according to platform parameters of the test result to tested side's cloud platform, and is touched
Send out input module described and re-execute it is described the voice data is input to tested square cloud platform step, after being optimized
Speech recognition result.
9. a kind of speech recognition processing system characterized by comprising vehicle device sound pick-up outfit and language as claimed in claim 8
Sound recognition process unit；
The voice recognition processing device obtains the voice data by the vehicle device sound pick-up outfit.
10. a kind of vehicle characterized by comprising speech recognition processing system as claimed in claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910429228.5A CN110136717A (en) | 2019-05-22 | 2019-05-22 | Voice recognition processing method, apparatus, system and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910429228.5A CN110136717A (en) | 2019-05-22 | 2019-05-22 | Voice recognition processing method, apparatus, system and vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110136717A true CN110136717A (en) | 2019-08-16 |
Family
ID=67572404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910429228.5A Pending CN110136717A (en) | 2019-05-22 | 2019-05-22 | Voice recognition processing method, apparatus, system and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110136717A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113485914A (en) * | 2021-06-09 | 2021-10-08 | 镁佳(北京)科技有限公司 | Vehicle-mounted voice SDK testing method, device and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104538031A (en) * | 2014-12-15 | 2015-04-22 | 北京云知声信息技术有限公司 | Intelligent voice service development cloud platform and method |
| CN105161113A (en) * | 2015-09-23 | 2015-12-16 | 嘉通奥祺科技（天津）有限公司 | Speech recognition and management system based on cloud platform |
| CN105391730A (en) * | 2015-12-02 | 2016-03-09 | 北京云知声信息技术有限公司 | Information feedback method, device and system |
| US20180293973A1 (en) * | 2016-10-31 | 2018-10-11 | International Business Machines Corporation | System, method and computer program product for assessing the capabilities of a conversation agent via black box testing |
| CN109102797A (en) * | 2018-07-06 | 2018-12-28 | 平安科技（深圳）有限公司 | Speech recognition test method, device, computer equipment and storage medium |
| CN109688036A (en) * | 2019-02-20 | 2019-04-26 | 广州视源电子科技股份有限公司 | A kind of control method of intelligent appliance, device, intelligent appliance and storage medium |
-
2019
- 2019-05-22 CN CN201910429228.5A patent/CN110136717A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104538031A (en) * | 2014-12-15 | 2015-04-22 | 北京云知声信息技术有限公司 | Intelligent voice service development cloud platform and method |
| CN105161113A (en) * | 2015-09-23 | 2015-12-16 | 嘉通奥祺科技（天津）有限公司 | Speech recognition and management system based on cloud platform |
| CN105391730A (en) * | 2015-12-02 | 2016-03-09 | 北京云知声信息技术有限公司 | Information feedback method, device and system |
| US20180293973A1 (en) * | 2016-10-31 | 2018-10-11 | International Business Machines Corporation | System, method and computer program product for assessing the capabilities of a conversation agent via black box testing |
| CN109102797A (en) * | 2018-07-06 | 2018-12-28 | 平安科技（深圳）有限公司 | Speech recognition test method, device, computer equipment and storage medium |
| CN109688036A (en) * | 2019-02-20 | 2019-04-26 | 广州视源电子科技股份有限公司 | A kind of control method of intelligent appliance, device, intelligent appliance and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 牛可等: "智能家居语音识别通用语音AI云平台的设计与实现", 《物联网技术》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113485914A (en) * | 2021-06-09 | 2021-10-08 | 镁佳(北京)科技有限公司 | Vehicle-mounted voice SDK testing method, device and system |
| CN113485914B (en) * | 2021-06-09 | 2022-03-08 | 镁佳(北京)科技有限公司 | Vehicle-mounted voice SDK testing method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109243432B (en) | Voice processing method and electronic device supporting the same | |
| US11264013B2 (en) | Identifying digital private information and preventing privacy violations | |
| CN107657950B (en) | Automobile voice control method, system and device based on cloud and multi-command words | |
| CN103456299B (en) | A kind of method and device controlling speech recognition | |
| TWI412953B (en) | Controlling a document based on user behavioral signals detected from a 3d captured image stream | |
| CN109102802B (en) | System for processing user utterances | |
| CN110718223A (en) | Method, apparatus, device and medium for voice interaction control | |
| KR20190100334A (en) | Contextual Hotwords | |
| CN112970059B (en) | Electronic device for processing user utterance and control method thereof | |
| TWI456477B (en) | Computer-implemented interface, method, and computer-readable storage medium for speech recongnition | |
| CN104040620A (en) | Direct grammar access | |
| JP2009512881A (en) | Diagnosing recognition problems based on non-transscribed data | |
| US20200104124A1 (en) | Code quality evaluation and user interfaces | |
| US11568853B2 (en) | Voice recognition method using artificial intelligence and apparatus thereof | |
| KR20190008663A (en) | Voice data processing method and system supporting the same | |
| Hastie | Metrics and evaluation of spoken dialogue systems | |
| US10147424B1 (en) | Generating self-support metrics based on paralinguistic information | |
| US11762451B2 (en) | Methods and apparatus to add common sense reasoning to artificial intelligence in the context of human machine interfaces | |
| KR20230116886A (en) | Self-supervised speech representation for fake audio detection | |
| CN116670655A (en) | Evaluating an on-device machine learning model based on performance metrics of a client device and/or the on-device machine learning model | |
| KR20190068021A (en) | User adaptive conversation apparatus based on monitoring emotion and ethic and method for thereof | |
| KR102114273B1 (en) | Method for personal image diagnostic providing and computing device for executing the method | |
| CN110136717A (en) | Voice recognition processing method, apparatus, system and vehicle | |
| US10976997B2 (en) | Electronic device outputting hints in an offline state for providing service according to user context | |
| US10446138B2 (en) | System and method for assessing audio files for transcription services |
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: 20190816 |