CN104575503B - Audio recognition method and device - Google Patents
Audio recognition method and device Download PDFInfo
- Publication number
- CN104575503B CN104575503B CN201510024583.6A CN201510024583A CN104575503B CN 104575503 B CN104575503 B CN 104575503B CN 201510024583 A CN201510024583 A CN 201510024583A CN 104575503 B CN104575503 B CN 104575503B
- Authority
- CN
- China
- Prior art keywords
- recognition
- identification
- recognition result
- server
- voice signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses a kind of audio recognition method, the audio recognition method comprises the following steps：When receiving voice signal, and when current network state is normal, the voice signal received is sent to default identification server and is identified, and obtains the recognition result of identification server feedback；Local terminal identification is carried out to the voice signal received, and obtains recognition result；Calculate recognition accuracy corresponding to each recognition result；Recognition result using the recognition result of recognition accuracy highest identification server feedback as the voice signal.The invention also discloses a kind of speech recognition equipment.The present invention improves the flexibility of speech recognition while accuracy of speech recognition is ensured.
Description
Technical field
The present invention relates to Voice command field, more particularly to audio recognition method and device.
Background technology
Traditional household electrical appliance carry out man-machine interaction with remote control, panel button, and speech recognition technology reaches machine to pass through
Voice-remote-control, turn into a kind of new man-machine interaction mode with Voice command terminal.Terminal speech identification includes two ways,
First way is identified off-line mode, will identify that engine is embedded on the CPU of local terminal, and identification is run on the CPU of local terminal
Algorithm, referred to as off-line type identify；Second is high in the clouds identification method, will identify engine-operated server beyond the clouds, terminal device
By network connection cloud server, the audio signal received is sent to cloud server, cloud server ties identification
Fruit returns to terminal, and this identification is referred to as online identification.Identified off-line needs not move through network transmission, therefore response speed
It hurry up, but influenceed due to being limited by equipment cpu performance, CPU disposal abilities are limited, and identification engine algorithms are simpler, therefore identify accurate
Exactness is general, and server is run ONLINE RECOGNITION engine beyond the clouds, more complicated using the powerful disposal ability of Cloud Server, operation
Identification engine algorithms so that recognition accuracy greatly improves, but is influenceed by network quality, limitation is higher.
The content of the invention
It is a primary object of the present invention to propose a kind of audio recognition method, it is intended to ensure the same of accuracy of speech recognition
When, improve the flexibility of speech recognition.
To achieve the above object, a kind of audio recognition method provided by the invention, the audio recognition method include following
Step：
When receiving voice signal, and when current network state is normal, the voice signal received is sent to pre-
If identification server be identified, and obtain identification server feedback recognition result；
Local terminal identification is carried out to the voice signal received, and obtains recognition result；
Calculate recognition accuracy corresponding to each recognition result；
Recognition result using the recognition result of recognition accuracy highest identification server feedback as the voice signal.
Preferably, the audio recognition method also includes：
In current network state exception, local terminal identification is carried out to the voice signal received, and obtain the voice
Recognition result corresponding to signal；
Recognition result using the recognition result as the voice signal.
Preferably, described the step of calculating recognition accuracy corresponding to each recognition result, includes：
Identification parameter corresponding to each server and local terminal identification is determined based on the recognition result；
Call recognition accuracy corresponding to the server and local terminal identification that terminal prestores；
The identification parameter and the recognition accuracy are weighted respectively according to default weight averagely, to determine
Recognition accuracy corresponding to each recognition result.
Preferably, the identification parameter includes response time, recognition result matching degree and the performance of server and local terminal
Parameter.
Preferably, it is described to identify the recognition result of server feedback as the voice signal recognition accuracy highest
Recognition result the step of after, the audio recognition method also includes：
Recognition accuracy to server or local terminal corresponding to the recognition result increases by a preset value.
In addition, to achieve the above object, the present invention also proposes a kind of speech recognition equipment, the speech recognition equipment bag
Include：
Long-range identification module, for when receiving voice signal, and when current network state is normal, by what is received
Voice signal sends to default identification server and is identified, and obtains the recognition result of identification server feedback；
Local terminal identification module, for carrying out local terminal identification to the voice signal received, and obtain recognition result；
Degree of accuracy computing module, for calculating recognition accuracy corresponding to each recognition result；
Processing module, for recognition accuracy highest to be identified to, the recognition result of server feedback is believed as the voice
Number recognition result.
Preferably, the local terminal identification module, it is additionally operable in current network state exception, the voice received is believed
Number local terminal identification is carried out, and obtain recognition result corresponding to the voice signal；The processing module, it is additionally operable to the identification
As a result the recognition result as the voice signal
Preferably, the degree of accuracy computing module includes：
Determining unit, for determining identification ginseng corresponding to each server and local terminal identification based on the recognition result
Number；
Call unit, for calling recognition accuracy corresponding to the server and local terminal identification that terminal prestores；
The determining unit, it is additionally operable to according to default weight respectively to the identification parameter and the recognition accuracy
It is weighted averagely, to determine recognition accuracy corresponding to each recognition result.
Preferably, the identification parameter includes response time, recognition result matching degree and the performance of server and local terminal
Parameter.
Preferably, the speech recognition equipment also includes：Adjusting module, for server corresponding to the recognition result
Or the recognition accuracy of local terminal increases by a preset value.
Audio recognition method and device proposed by the present invention, when receiving voice signal, and current network state is just
Chang Shi, the voice signal received is sent to default identification server and is identified, and obtain identification server feedback
Recognition result；Local terminal identification is carried out to the voice signal received, and obtains recognition result；Calculate corresponding to each recognition result
Recognition accuracy；Identification knot using the recognition result of recognition accuracy highest identification server feedback as the voice signal
Fruit, improve accuracy rate and flexibility ratio to voice signal identification.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of audio recognition method preferred embodiment of the present invention；
Fig. 2 is the refinement schematic flow sheet of step S30 in Fig. 1；
Fig. 3 is the high-level schematic functional block diagram of speech recognition equipment preferred embodiment of the present invention；
Fig. 4 is the refinement high-level schematic functional block diagram of degree of accuracy computing module in Fig. 3.
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
Embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present invention provides a kind of audio recognition method.
Reference picture 1, Fig. 1 are the schematic flow sheet of audio recognition method preferred embodiment of the present invention.
The present embodiment proposes a kind of audio recognition method, and the audio recognition method comprises the following steps：
Step S10, when receiving voice signal, and when current network state is normal, the voice signal that will receive
Send to default identification server and be identified, and obtain the recognition result of identification server feedback；
In the present embodiment, when receiving voice signal, current network state is can determine whether, can have been connected in terminal
Network and can proper communication be to judge that current network state is normal.Identify server to the identification of the voice signal received
Process is as follows, obtains waveform corresponding to the voice signal received, and determines control routine corresponding to the waveform, by the control generation
Recognition result of the code as voice signal.
It will be appreciated by persons skilled in the art that be the accuracy rate for improving voice signal identification, can be to the language that receives
After sound signal carries out noise reduction and filtering process, the voice signal after processing is sent to server.It can be not to identify server
The server of diverse location is placed on the server of producer, or same producer.
Step S20, local terminal identification is carried out to the voice signal received, and obtain recognition result；
In the present embodiment, local terminal identification process is similar to the identification process of server, will not be repeated here.This area skill
Art personnel between step S10 and step S20 it is understood that do not have sequencing.
Step S30, calculate recognition accuracy corresponding to each recognition result；
In the present embodiment, the detailed process of recognition accuracy corresponding to each recognition result is calculated as shown in Fig. 2 described
Step S30 includes：
Step S31, identification parameter corresponding to each server and local terminal identification is determined based on the recognition result；
Step S33, call recognition accuracy corresponding to the server and local terminal identification that terminal prestores；
Step S34, the identification parameter and the recognition accuracy are weighted respectively according to default weight flat
, to determine recognition accuracy corresponding to each recognition result.
The identification parameter includes response time, recognition result matching degree and the performance parameter of server and local terminal；Or
Person, the identification parameter may also comprise the response time and recognition result matching degree of server and local terminal.Those skilled in the art
It is understood that the identification parameter includes response time, recognition result matching degree and the performance ginseng of server and local terminal
Outside number, other parameters are may also comprise, those skilled in the art can be according to the requirement increase to the final recognition result degree of accuracy
Or reduce the feature included in identification parameter.The calculating process of response time, recognition result matching degree and performance parameter is such as
Under：
The specific calculating process of response time is, when that will receive speech recognition signal and send to identification server,
Current point in time can be recorded as to first time point, and the speech recognition signal received is sent to identification server, connect
When receiving the recognition result of identification server feedback, current point in time was recorded as the second time point, and by first time point with
Difference before second time point is that similarly, record will receive for the calculating of local terminal response time as server response time
Speech recognition signal send the first time point being identified to identification module, and get the recognition result of voice signal
The second time point, and be as local terminal response time using the difference before first time point and the second time point.The identification
As a result matching degree can be the matching between the waveform corresponding to recognition result and the waveform corresponding to the voice signal that receives
Degree, when the matching degree calculates, matching degree between waveform is calculated as prior art, will not be repeated here, the recognition result
In the recognition result that the identification module feedback in server and terminal can be added with degree.Performance parameter can by server or
MIPS (Million Instructions Per Second, the long fixed point instruction of list averagely perform speed), the internal memory of terminal hold
Amount etc. is calculated, and the performance parameter can be included in recognition result.Response time, recognition result matching degree and performance parameter
Weight can be set as needed by developer, the weight sums of parameters is 1.
It will be appreciated by persons skilled in the art that because identification server is likely to occur failure, in prefixed time interval
When inside receiving recognition result corresponding to speech recognition signal, the identification parameter corresponding to each recognition result is determined.
Step S40, identify the recognition result of server feedback as the voice signal recognition accuracy highest
Recognition result.
The degree of accuracy of each recognition result can be ranked up, extract the identification of degree of accuracy highest and tied as final identification
Fruit.It will be appreciated by persons skilled in the art that to improve the accuracy of speech recognition, also include step after the step S40
Suddenly：Recognition accuracy to server or local terminal corresponding to the recognition result increases by a preset value.The preset value is preferably 1.
To improve the flexibility to voice signal identification, the audio recognition method also includes step：In current network
During abnormal state, local terminal identification is carried out to the voice signal received, and obtain recognition result corresponding to the voice signal；Will
Recognition result of the recognition result as the voice signal.In the present embodiment, in the case of Network Abnormal, the knowledge of local terminal
The other degree of accuracy is constant.The Network Abnormal refers to not connected network or has connected network but can not proper communication.
To improve the accuracy rate of speech recognition, the audio recognition method also includes：Terminal current network state is obtained, is based on
Mapping relations between network state and prompt message, export the prompt message corresponding to current network state.The prompting is believed
Breath is preferably light prompt message, is realized by warning light.
The audio recognition method that the present embodiment proposes, when receiving voice signal, and when current network state is normal,
The voice signal received is sent to default identification server and is identified, and obtains the identification knot of identification server feedback
Fruit；Local terminal identification is carried out to the voice signal received, and obtains recognition result；It is accurate to calculate identification corresponding to each recognition result
Exactness；Using the recognition result of recognition accuracy highest identification server feedback as the recognition result of the voice signal, carry
The high accuracy rate to voice signal identification.
The present invention further provides a kind of speech recognition equipment.
Reference picture 3, Fig. 3 are the high-level schematic functional block diagram of speech recognition equipment preferred embodiment of the present invention.
It is emphasized that it will be apparent to those skilled in the art that functional block diagram shown in Fig. 3 is only one preferably real
The exemplary plot of example is applied, those skilled in the art can be carried out new easily around the functional module of the speech recognition equipment shown in Fig. 3
Functional module supplement；The title of each functional module is self-defined title, is only used for auxiliary and understands the speech recognition equipment
Each program function block, restriction technical scheme is not used in, the core of technical solution of the present invention is each self-defined title
The function to be reached of functional module.
The present embodiment proposes a kind of speech recognition equipment, and the speech recognition equipment includes：
Long-range identification module 10, for when receiving voice signal, and when current network state is normal, it will receive
Voice signal send to it is default identification server be identified, and obtain identification server feedback recognition result；
In the present embodiment, when receiving voice signal, current network state is can determine whether, can have been connected in terminal
Network and can proper communication be to judge that current network state is normal.Identify server to the identification of the voice signal received
Process is as follows, obtains waveform corresponding to the voice signal received, and determines control routine corresponding to the waveform, by the control generation
Recognition result of the code as voice signal.
It will be appreciated by persons skilled in the art that be the accuracy rate for improving voice signal identification, can be to the language that receives
After sound signal carries out noise reduction and filtering process, the voice signal after processing is sent to server.It can be not to identify server
The server of diverse location is placed on the server of producer, or same producer.
Local terminal identification module 20, for carrying out local terminal identification to the voice signal received, and obtain recognition result；
In the present embodiment, local terminal identification process is similar to the identification process of server, will not be repeated here.
Degree of accuracy computing module 30, for calculating recognition accuracy corresponding to each recognition result；
In the present embodiment, the detailed process of recognition accuracy corresponding to each recognition result is calculated as shown in figure 4, described
Degree of accuracy computing module 30 includes：
Determining unit 31, for determining identification ginseng corresponding to each server and local terminal identification based on the recognition result
Number；
Call unit 32, for calling recognition accuracy corresponding to the server and local terminal identification that terminal prestores；
The determining unit 31, it is accurate to the identification parameter and the identification respectively according to default weight to be additionally operable to
Degree is weighted averagely, to determine recognition accuracy corresponding to each recognition result.
The identification parameter includes response time, recognition result matching degree and the performance parameter of server and local terminal；Or
Person, the identification parameter may also comprise the response time and recognition result matching degree of server and local terminal.Those skilled in the art
It is understood that the identification parameter includes response time, recognition result matching degree and the performance ginseng of server and local terminal
Outside number, other parameters are may also comprise, those skilled in the art can be according to the requirement increase to the final recognition result degree of accuracy
Or reduce the feature included in identification parameter.The calculating process of response time, recognition result matching degree and performance parameter is such as
Under：
The specific calculating process of response time is, when that will receive speech recognition signal and send to identification server,
Current point in time can be recorded as to first time point, and the speech recognition signal received is sent to identification server, connect
When receiving the recognition result of identification server feedback, current point in time was recorded as the second time point, and by first time point with
Difference before second time point is that similarly, record will receive for the calculating of local terminal response time as server response time
Speech recognition signal send the first time point being identified to identification module, and get the recognition result of voice signal
The second time point, and be as local terminal response time using the difference before first time point and the second time point.The identification
As a result matching degree can be the matching between the waveform corresponding to recognition result and the waveform corresponding to the voice signal that receives
Degree, when the matching degree calculates, matching degree between waveform is calculated as prior art, will not be repeated here, the recognition result
In the recognition result that the identification module feedback in server and terminal can be added with degree.Performance parameter can by server or
MIPS (Million Instructions Per Second, the long fixed point instruction of list averagely perform speed), the internal memory of terminal hold
Amount etc. is calculated, and the performance parameter can be included in recognition result.Response time, recognition result matching degree and performance parameter
Weight can be set as needed by developer, the weight sums of parameters is 1.
It will be appreciated by persons skilled in the art that because identification server is likely to occur failure, in prefixed time interval
When inside receiving recognition result corresponding to speech recognition signal, the identification parameter corresponding to each recognition result is determined.
Processing module 40, for identifying recognition accuracy highest the recognition result of server feedback as the voice
The recognition result of signal.
The degree of accuracy of each recognition result can be ranked up, extract the identification of degree of accuracy highest and tied as final identification
Fruit.It will be appreciated by persons skilled in the art that to improve the accuracy of speech recognition, the speech recognition equipment also includes：
Adjusting module, increase by a preset value for the recognition accuracy to server or local terminal corresponding to the recognition result.This is default
Value is preferably 1.
To improve the flexibility to voice signal identification, the audio recognition method also includes step：In current network
During abnormal state, local terminal identification is carried out to the voice signal received, and obtain recognition result corresponding to the voice signal；Will
Recognition result of the recognition result as the voice signal.In the present embodiment, in the case of Network Abnormal, the knowledge of local terminal
The other degree of accuracy is constant.The Network Abnormal refers to not connected network or has connected network but can not proper communication.
To improve the accuracy rate of speech recognition, the speech recognition equipment also includes：Acquisition module obtains terminal current network
State；Output module, for right based on the mapping relations between network state and prompt message, output current network state institute
The prompt message answered.The prompt message is preferably light prompt message, is realized by warning light.
The speech recognition equipment that the present embodiment proposes, when receiving voice signal, and when current network state is normal,
The voice signal of reception is sent to default identification server and is identified, and obtains the identification knot of identification server feedback
Fruit；Local terminal identification is carried out to the voice signal received, and obtains recognition result；It is accurate to calculate identification corresponding to each recognition result
Exactness；Using the recognition result of recognition accuracy highest identification server feedback as the recognition result of the voice signal, carry
The high accuracy rate to voice signal identification.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, method, article or system including a series of elements not only include those key elements, and
And also include the other element being not expressly set out, or also include for this process, method, article or system institute inherently
Key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including this
Other identical element also be present in the process of key element, method, article or system.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme is substantially done to prior art in other words
Going out the part of contribution can be embodied in the form of software product, and the computer software product is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), including some instructions to cause a station terminal equipment (can be mobile phone, computer, clothes
Be engaged in device, air conditioner, or network equipment etc.) perform method described in each embodiment of the present invention.
The preferred embodiments of the present invention are these are only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of audio recognition method, it is characterised in that the audio recognition method comprises the following steps：
When receiving voice signal, and when current network state is normal, at the voice signal noise reduction received and filtering
Send to default identification server and be identified after reason, and obtain the recognition result of identification server feedback；The identification clothes
Business device includes multiple servers；
To carrying out local terminal identification after the voice signal noise reduction and filtering process that receive, and obtain recognition result；
Recognition accuracy corresponding to each recognition result is calculated, the recognition accuracy is based on local terminal and each server identifies
Identification parameter corresponding to each recognition result determines；
Recognition accuracy to each recognition result is ranked up, and recognition accuracy highest is identified to the identification of server feedback
As a result the recognition result as the voice signal.
2. audio recognition method as claimed in claim 1, it is characterised in that the audio recognition method also includes：
In current network state exception, local terminal identification is carried out to the voice signal received, and obtain the voice signal
Corresponding recognition result；
Recognition result using the recognition result as the voice signal.
3. audio recognition method as claimed in claim 1 or 2, it is characterised in that described to calculate corresponding to each recognition result
The step of recognition accuracy, includes：
Identification parameter corresponding to each server and local terminal identification is determined based on the recognition result；
Call recognition accuracy corresponding to the server and local terminal identification that terminal prestores；
The identification parameter and the recognition accuracy are weighted respectively according to default weight averagely, it is each to determine
Recognition accuracy corresponding to recognition result.
4. audio recognition method as claimed in claim 3, it is characterised in that the identification parameter includes server and local terminal
Response time, recognition result matching degree and performance parameter.
5. audio recognition method as claimed in claim 4, it is characterised in that described identify recognition accuracy highest services
After the step of recognition result of the recognition result as the voice signal of device feedback, the audio recognition method also includes：
Recognition accuracy to server or local terminal corresponding to the recognition result increases by a preset value.
6. a kind of speech recognition equipment, it is characterised in that the speech recognition equipment includes：
Long-range identification module, for when receiving voice signal, and when current network state is normal, the voice that will receive
Send to default identification server and be identified after signal de-noising and filtering process, and obtain the identification of identification server feedback
As a result；The identification server includes multiple servers；
Local terminal identification module, for carrying out local terminal identification after the voice signal noise reduction and filtering process to receiving, and obtain knowledge
Other result；
Degree of accuracy computing module, for calculating recognition accuracy corresponding to each recognition result, the recognition accuracy is based on this
End and each server identify that identification parameter determines corresponding to each recognition result；
Processing module, it is ranked up for the recognition accuracy to each recognition result, recognition accuracy highest is identified and taken
Recognition result of the recognition result for device feedback of being engaged in as the voice signal.
7. speech recognition equipment as claimed in claim 6, it is characterised in that the local terminal identification module, be additionally operable to current
Network state exception when, local terminal identification is carried out to the voice signal that receives, and obtain and identified corresponding to the voice signal
As a result；The processing module, it is additionally operable to the recognition result using the recognition result as the voice signal.
8. speech recognition equipment as claimed in claims 6 or 7, it is characterised in that the degree of accuracy computing module includes：
Determining unit, for determining identification parameter corresponding to each server and local terminal identification based on the recognition result；
Call unit, for calling recognition accuracy corresponding to the server and local terminal identification that terminal prestores；
The determining unit, it is additionally operable to respectively carry out the identification parameter and the recognition accuracy according to default weight
Weighted average, to determine recognition accuracy corresponding to each recognition result.
9. speech recognition equipment as claimed in claim 8, it is characterised in that the identification parameter includes server and local terminal
Response time, recognition result matching degree and performance parameter.
10. speech recognition equipment as claimed in claim 9, it is characterised in that the speech recognition equipment also includes：Adjust mould
Block, increase by a preset value for the recognition accuracy to server or local terminal corresponding to the recognition result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510024583.6A CN104575503B (en) | 2015-01-16 | 2015-01-16 | Audio recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510024583.6A CN104575503B (en) | 2015-01-16 | 2015-01-16 | Audio recognition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104575503A CN104575503A (en) | 2015-04-29 |
| CN104575503B true CN104575503B (en) | 2018-04-10 |
Family
ID=53091403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510024583.6A Active CN104575503B (en) | 2015-01-16 | 2015-01-16 | Audio recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104575503B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105183081A (en) * | 2015-09-07 | 2015-12-23 | 北京君正集成电路股份有限公司 | Voice control method of intelligent glasses and intelligent glasses |
| CN106782546A (en) * | 2015-11-17 | 2017-05-31 | 深圳市北科瑞声科技有限公司 | Audio recognition method and device |
| CN105931633A (en) * | 2016-05-30 | 2016-09-07 | 深圳市鼎盛智能科技有限公司 | Speech recognition method and system |
| CN106373565A (en) * | 2016-08-24 | 2017-02-01 | 安徽咪鼠科技有限公司 | Method for automatically switching speech recognition engines |
| CN106531151B (en) * | 2016-11-16 | 2019-10-11 | 北京云知声信息技术有限公司 | Audio recognition method and device |
| CN106682590B (en) * | 2016-12-07 | 2023-08-22 | 浙江宇视科技有限公司 | Processing method of monitoring service and server |
| CN108806682B (en) * | 2018-06-12 | 2020-12-01 | 奇瑞汽车股份有限公司 | Method and device for acquiring weather information |
| CN111627431B (en) * | 2020-05-13 | 2022-08-09 | 广州国音智能科技有限公司 | Voice recognition method, device, terminal and storage medium |
| CN112702231B (en) * | 2020-12-21 | 2022-12-16 | 交控科技股份有限公司 | Network delay measuring method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101436405A (en) * | 2008-12-25 | 2009-05-20 | 北京中星微电子有限公司 | Method and system for recognizing speaking people |
| CN103079258A (en) * | 2013-01-09 | 2013-05-01 | 广东欧珀移动通信有限公司 | Method for improving speech recognition accuracy and mobile intelligent terminal |
| WO2014121234A2 (en) * | 2013-02-03 | 2014-08-07 | Study Outloud Llc | Method and apparatus for contextual text to speech conversion |
| CN103247291B (en) * | 2013-05-07 | 2016-01-13 | 华为终端有限公司 | A kind of update method of speech recognition apparatus, Apparatus and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030144837A1 (en) * | 2002-01-29 | 2003-07-31 | Basson Sara H. | Collaboration of multiple automatic speech recognition (ASR) systems |
| US20080228493A1 (en) * | 2007-03-12 | 2008-09-18 | Chih-Lin Hu | Determining voice commands with cooperative voice recognition |
-
2015
- 2015-01-16 CN CN201510024583.6A patent/CN104575503B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101436405A (en) * | 2008-12-25 | 2009-05-20 | 北京中星微电子有限公司 | Method and system for recognizing speaking people |
| CN103079258A (en) * | 2013-01-09 | 2013-05-01 | 广东欧珀移动通信有限公司 | Method for improving speech recognition accuracy and mobile intelligent terminal |
| WO2014121234A2 (en) * | 2013-02-03 | 2014-08-07 | Study Outloud Llc | Method and apparatus for contextual text to speech conversion |
| CN103247291B (en) * | 2013-05-07 | 2016-01-13 | 华为终端有限公司 | A kind of update method of speech recognition apparatus, Apparatus and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104575503A (en) | 2015-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104575503B (en) | Audio recognition method and device | |
| CN104506886B (en) | A kind of fault handling method and cloud server | |
| CN109087669B (en) | Audio similarity detection method and device, storage medium and computer equipment | |
| CN104978957A (en) | Voice control method and system based on voiceprint identification | |
| CN108083042B (en) | Elevator recommended method and device | |
| CN109413480A (en) | Picture processing method, device, terminal and storage medium | |
| CN110798718B (en) | Video recommendation method and device | |
| CN110347863B (en) | Speaking recommendation method and device and storage medium | |
| CN107580237A (en) | Operating method, device, system and the storage medium of TV | |
| CN104078045B (en) | Identifying method and electronic device | |
| CN109062715B (en) | Method and device for determining memory clock frequency and terminal | |
| CN108418981A (en) | The method and device of dialogue service is provided for client | |
| CN105091208B (en) | Air conditioner wind speed control method and system | |
| CN108986810A (en) | A kind of method and device for realizing interactive voice by earphone | |
| CN103916511B (en) | The method and electronic equipment of information processing | |
| CN107623830A (en) | A kind of video call method and electronic equipment | |
| CN108648142A (en) | Image processing method and device | |
| CN108644969A (en) | Control the method, apparatus and system, air-conditioning of compressor | |
| CN113299306B (en) | Echo cancellation method, echo cancellation device, electronic equipment and computer-readable storage medium | |
| CN109346102B (en) | Method and device for detecting audio beginning crackle and storage medium | |
| CN105529025A (en) | Voice operation input method and electronic device | |
| CN106356056A (en) | Speech recognition method and device | |
| CN104735389A (en) | Information processing method and equipment | |
| CN103941868B (en) | Voice command accuracy rate method of adjustment and system | |
| CN113593535A (en) | Voice data processing method and device, storage medium and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |