CN104780263A - Method and device for voice breakpoint extension judgment - Google Patents
Method and device for voice breakpoint extension judgment Download PDFInfo
- Publication number
- CN104780263A CN104780263A CN201510111271.9A CN201510111271A CN104780263A CN 104780263 A CN104780263 A CN 104780263A CN 201510111271 A CN201510111271 A CN 201510111271A CN 104780263 A CN104780263 A CN 104780263A
- Authority
- CN
- China
- Prior art keywords
- speech message
- duration
- recording
- voice
- setting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000001514 detection method Methods 0.000 claims abstract description 13
- 230000005540 biological transmission Effects 0.000 claims abstract description 10
- 238000012360 testing method Methods 0.000 claims description 12
- 230000015572 biosynthetic process Effects 0.000 claims description 7
- 238000003786 synthesis reaction Methods 0.000 claims description 7
- 230000008034 disappearance Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000011897 real-time detection Methods 0.000 claims description 6
- 230000002045 lasting effect Effects 0.000 claims description 3
- 230000006641 stabilisation Effects 0.000 description 4
- 238000011105 stabilization Methods 0.000 description 4
- 206010002953 Aphonia Diseases 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 206010003830 Automatism Diseases 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001131 transforming effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
Landscapes
- Telephone Function (AREA)
Abstract
The invention relates to a method and a device for judging voice breakpoint extension, which can be used for education electronic products. The method comprises the steps of detecting whether a voice message trigger signal is received in real time; if yes, starting recording; judging the duration of the voice message trigger signal; if the duration time meets the set duration time, playing the received voice message and abandoning the recording message; if the duration time meets the set duration, continuing recording to realize the transmission of the voice message; detecting whether the voice message trigger signal disappears in real time; if yes, starting a voice endpoint energy detection function to detect whether a voice message exists; if yes, continuing recording to realize sending the complete voice message. The intelligent voice message sending method is mainly used for sending voice messages of electronic products for children, intelligently judges the head and the tail of voice sending according to the mode of combining key (touch screen) triggering and voice energy endpoint detection, intelligently prevents shaking, prolongs the input voice tail point and helps children send complete voice.
Description
Technical field
The present invention relates to speech communication technical field, particularly relate to a kind of voice breakpoint and extend the method and device that judge.
Background technology
Along with the development of the communication technology, transmission speech message also becomes a kind of communication way that people commonly use, existing scheme mainly two kinds, a kind of voice starting point and end point for being decided record by a screen or button, or according to the end-point detection of voice own, detect that speech pause duration exceedes certain hour, then automatically terminate.Two kinds of modes problem on adult uses is little, if but allowed child use, sometimes could produce shake because of finger long-time button, touch screen etc., one section of voice is sent intermittently, or in short only have sent first half sentence voice, should be optimized for child.
Due to the volume of the children such as Intelligent worn device or smart mobile phone electronic product and button fewer, one by key control speech play and input when, short in playing voice, long by recording.When record voice, child often loquiturs under button does not reach long according to condition startup recording prerequisite, causes front half loss of voice, has only kept later half sentence here, need to improve this problem.
Summary of the invention
The object of the invention is to propose a kind of voice breakpoint and extend the method and device that judge, this patent is for children's electronic product, trigger according to button (touch screen), combine with speech energy end-point detection mode, to the mode of carrying out intelligent decision end to end that voice send, intelligent stabilization extends input voice tail point, helps child to send complete speech, ensure that the speech message sent is more complete clear, promote Consumer's Experience.
For reaching this object, the present invention by the following technical solutions:
Voice breakpoint extends the method judged, comprising:
Whether real-time detection receives speech message triggering signal;
If so, recording is then started;
Judge the duration of described speech message triggering signal;
If the duration meets short in setting duration, then play the speech message that received and give up described record messages;
If the duration meets long by setting duration, then continue recording to realize sending speech message.
Wherein, if the described duration meets long by setting duration, then continue recording to realize sending speech message, comprise further:
To described short by setting time grow to described length by setting the duration time period in record messages carry out sound end energy measuring;
If testing result is that in this time period, user does not speak, then abandon the record messages in this time period;
If testing result is that in this time period, user speaks, then intercept and preserve the record messages from the place that loquiturs, all the other abandon.
Wherein, described short by setting duration be 0.1 ~ 0.2s, described length by setting duration be 0.3 ~ 0.5s;
The triggering mode of described speech message triggering signal, comprises button and triggers and touch screen triggering;
Described sound end energy measuring is that average energy, last or end syllable energy synthesis has judged based on recording starting point speech energy.
Voice breakpoint extends the device judged, comprising:
Whether the first triggering signal detecting unit, receive speech message triggering signal for detecting in real time;
Recoding unit, if for receiving speech message triggering signal, then starts recording;
Triggering signal timing unit, for judging the duration of described speech message triggering signal;
Play message elements, if meet for the duration short in setting duration, then play the speech message that received and give up described record messages;
Send message elements, if meet for the duration long by setting duration, then continue recording to realize sending speech message.
Wherein, described transmission message elements also comprises:
First speech energy detecting unit, for described short by setting time grow to described length by setting the duration time period in record messages carry out sound end energy measuring;
First processing unit, if for testing result for user in this time period does not speak, then abandon the record messages in this time period;
Second processing unit, if for testing result for user in this time period speaks, then intercept and preserve the record messages from the place that loquiturs, all the other abandon.
Wherein, described short by setting duration be 0.1 ~ 0.2s, described length by setting duration be 0.3 ~ 0.5s;
The triggering mode of described speech message triggering signal, comprises button and triggers and touch screen triggering;
Described sound end energy measuring is that average energy, last or end syllable energy synthesis has judged based on recording starting point speech energy.
Voice breakpoint extends the method judged, comprising:
Whether real-time detection speech message triggering signal disappears;
If so, then start sound end energy measuring Function detection and whether also have speech message;
If have, then continue recording to realize sending complete speech message.
Wherein, have if described, then continue recording to realize sending complete speech message, be specially:
If speech message in addition detected, then continue recording;
After speech message disappearance reaches preset duration, stop recording to realize sending complete speech message.
Wherein, described method, also comprises:
If detect, speech message triggering signal disappears, then continue the interval duration that recording continues to setting.
Wherein, the interval duration of described setting is 0.4 ~ 0.6s.
Voice breakpoint extends the device judged, comprising:
Whether the second triggering signal detecting unit, disappear for detecting speech message triggering signal in real time;
Second speech energy detecting unit, if disappear for speech message triggering signal, then starts sound end energy measuring Function detection and whether also has speech message;
First continues recoding unit, if for also having speech message, then continues recording to realize sending complete speech message.
Wherein, described lasting recoding unit, if specifically for speech message in addition being detected, then continue recording; After speech message disappearance reaches preset duration, stop recording to realize sending complete speech message.
Wherein, described device, also comprises:
Second continues recoding unit, if for detecting that speech message triggering signal disappears, then continues the interval duration that recording continues to setting.
Wherein, the interval duration of described setting is 0.4 ~ 0.6s.
Beneficial effect:
A kind of voice breakpoint of the present invention extends the method and device that judge, this patent is mainly used in the speech message transmission that child intelligence dresses the children such as wrist-watch or mobile phone electronic product, trigger according to button (touch screen), combine with speech energy end-point detection mode, to the mode of carrying out intelligent decision end to end that voice send, intelligent stabilization extends input voice tail point, helps child to send complete speech, ensure that the speech message sent is more complete clear, promote Consumer's Experience.
Accompanying drawing explanation
Fig. 1 is the flow chart of the method for a kind of voice breakpoint prolongation judgement that the specific embodiment of the invention provides.
Fig. 2 is the structural representation of the device of a kind of voice breakpoint prolongation judgement that the specific embodiment of the invention provides.
Fig. 3 is the flow chart of the method for the another kind of voice breakpoint prolongation judgement that the specific embodiment of the invention provides.
Fig. 4 is the structural representation of the device of the another kind of voice breakpoint prolongation judgement that the specific embodiment of the invention provides.
Embodiment
Technical scheme of the present invention is further illustrated by embodiment below in conjunction with accompanying drawing.
Embodiment 1:
Fig. 1 is the flow chart of the method for a kind of voice breakpoint prolongation judgement that the specific embodiment of the invention provides.As shown in Figure 1, a kind of voice breakpoint of the present invention extends the method judged, comprising:
Whether real-time detection receives speech message triggering signal;
If so, recording is then started;
Judge the duration of described speech message triggering signal;
If the duration meets short in setting duration, then play the speech message that received and give up described record messages;
If the duration meets long by setting duration, then continue recording to realize sending speech message.
This patent is mainly used in the speech message transmission that child intelligence dresses the children such as wrist-watch or mobile phone electronic product, and realize under a button short in playing the voice received, long by recording, loose one's grip and send the multiplex mode of voice, and front and back do not have loss of voice.Here when button is pressed, namely when detection is to speech message triggering signal, do not judge short in under long prerequisite of pressing, preferentially open recording to record, long shorter upon pressing the key, be judged as on time short, then abandon the recording in process, play-over the voice received, complete the function that speech message is play; Length exceedes certain hour upon pressing the key, when reaching the long condition by recording, then continue to keep recording, last when lifting button, whole recording is sent to receipts information Man, the restriction just can recorded when must grow and start recording without the need to user by certain time length like this, improves Consumer's Experience, and especially child is not easy to understand when just calculate the experience of opening and recording and can speak.
If the described duration meets long by setting duration, then continue recording to realize sending speech message, comprise further:
To described short by setting time grow to described length by setting the duration time period in record messages carry out sound end energy measuring;
If testing result is that in this time period, user does not speak, then abandon the record messages in this time period;
If testing result is that in this time period, user speaks, then intercept and preserve the record messages from the place that loquiturs, all the other abandon.
When long by when lifting button, by sound end energy measuring, short by the inside recording to the long time period by transforming, detect, if user does not speak during this period of time, then automatically help user that this section of recording is lost, if spoken in process, then automatically intercept the place's of loquituring voice backward, front end voice are abandoned.Ensure that user is according to growing the voice experience just carrying out in by certain time length situation recording, and can not allow the other side listen very long invalid sound.
Preferably, described short by setting duration be 0.1 ~ 0.2s, described length by setting duration be 0.3 ~ 0.5s.
The triggering mode of described speech message triggering signal, includes but not limited to that button triggers and touch screen triggers;
Described sound end energy measuring is that average energy, last or end syllable energy synthesis has judged based on recording starting point speech energy.Here sound end energy measuring, be for whole recording starting point speech energy, average energy, last or end syllable energy synthesis has judged, prevents the erroneous judgement under noisy environment, cannot terminate speech message always.
Embodiment 2:
The present embodiment 2 and embodiment 1 belong to the embodiment of same technical conceive, and the content of not detailed description in example 2, refers to embodiment 1.
Fig. 2 is the structural representation of the device of a kind of voice breakpoint prolongation judgement that the specific embodiment of the invention provides.As shown in Figure 2, a kind of voice breakpoint of the present invention extends the device judged, comprising:
Whether the first triggering signal detecting unit, receive speech message triggering signal for detecting in real time;
Recoding unit, if for receiving speech message triggering signal, then starts recording;
Triggering signal timing unit, for judging the duration of described speech message triggering signal;
Play message elements, if meet for the duration short in setting duration, then play the speech message that received and give up described record messages;
Send message elements, if meet for the duration long by setting duration, then continue recording to realize sending speech message.
This patent is mainly used in the speech message transmission that child intelligence dresses the children such as wrist-watch or mobile phone electronic product, and realize under a button short in playing the voice received, long by recording, loose one's grip and send the multiplex mode of voice, and front and back do not have loss of voice.Here when button is pressed, namely when detection is to speech message triggering signal, do not judge short in under long prerequisite of pressing, preferentially open recording to record, long shorter upon pressing the key, be judged as on time short, then abandon the recording in process, play-over the voice received, complete the function that speech message is play; Length exceedes certain hour upon pressing the key, when reaching the long condition by recording, then continue to keep recording, last when lifting button, whole recording is sent to receipts information Man, the restriction just can recorded when must grow and start recording without the need to user by certain time length like this, improves Consumer's Experience, and especially child is not easy to understand when just calculate the experience of opening and recording and can speak.
Described transmission message elements, also comprises:
First speech energy detecting unit, for described short by setting time grow to described length by setting the duration time period in record messages carry out sound end energy measuring;
First processing unit, if for testing result for user in this time period does not speak, then abandon the record messages in this time period;
Second processing unit, if for testing result for user in this time period speaks, then intercept and preserve the record messages from the place that loquiturs, all the other abandon.
When long by when lifting button, by sound end energy measuring, short by the inside recording to the long time period by transforming, detect, if user does not speak during this period of time, then automatically help user that this section of recording is lost, if spoken in process, then automatically intercept the place's of loquituring voice backward, front end voice are abandoned.Ensure that user is according to growing the voice experience just carrying out in by certain time length situation recording, and can not allow the other side listen very long invalid sound.
Preferably, described short by setting duration be 0.1 ~ 0.2s, described length by setting duration be 0.3 ~ 0.5s;
The triggering mode of described speech message triggering signal, includes but not limited to that button triggers and touch screen triggers;
Described sound end energy measuring is that average energy, last or end syllable energy synthesis has judged based on recording starting point speech energy.
Embodiment 3:
Fig. 3 is the flow chart of the method for the another kind of voice breakpoint prolongation judgement that the specific embodiment of the invention provides.As shown in Figure 3, a kind of voice breakpoint of the present invention extends the method judged, comprising:
Whether real-time detection speech message triggering signal disappears;
If so, then start sound end energy measuring Function detection and whether also have speech message;
If have, then continue recording to realize sending complete speech message.
This patent triggers according to button (touch screen), combine with sound end energy measuring mode, the mode that sound end energy measuring carries out intelligent decision is continued through after speech message triggering signal is disappeared, intelligence stabilization extends input voice tail point, child is helped to send complete speech, ensure that the speech message sent is more complete clear, promote Consumer's Experience.
In this programme, have if described, then continue recording to realize sending complete speech message, be specially:
If speech message in addition detected, then continue recording;
After speech message disappearance reaches preset duration, stop recording to realize sending complete speech message.
When voice terminate, speech often can occur and also do not terminate, hand has unclamped button or button screen; last or end syllable is caused comparatively early to terminate; sound like unexpected disconnection, here after button lifts, start sound end energy measuring function; when button lifts; detect that voice exist in addition, then continue recording, until end points pause certain time length detected; then be judged as that voice terminate, the whole voice of complete transmission.
Described method, also comprises:
If detect, speech message triggering signal disappears, then continue the interval duration that recording continues to setting.
In voice process; if the hand of user key-press shake or touch screen slips off to return again; according to both interval durations; automatically user's continued access is helped to remain valid; and non-immediate terminates; help user in time longer Recording Process, because automatism breaks in recording, especially child often can occur in use Recording Process.In this programme, preferably, the interval duration of described setting is 0.4 ~ 0.6s.If exceed the interval duration of described setting, then terminate recording.
Embodiment 4:
The present embodiment 4 and embodiment 3 belong to the embodiment of same technical conceive, and the content of not detailed description in example 4, refers to embodiment 3.
Fig. 4 is the structural representation of the device of the another kind of voice breakpoint prolongation judgement that the specific embodiment of the invention provides.As shown in Figure 4, a kind of voice breakpoint of the present invention extends the device judged, comprising:
Whether the second triggering signal detecting unit, disappear for detecting speech message triggering signal in real time;
Second speech energy detecting unit, if disappear for speech message triggering signal, then starts sound end energy measuring Function detection and whether also has speech message;
First continues recoding unit, if for also having speech message, then continues recording to realize sending complete speech message.
This patent triggers according to button (touch screen), combine with sound end energy measuring mode, the mode that sound end energy measuring carries out intelligent decision is continued through after speech message triggering signal is disappeared, intelligence stabilization extends input voice tail point, child is helped to send complete speech, ensure that the speech message sent is more complete clear, promote Consumer's Experience.
Described lasting recoding unit, if specifically for speech message in addition being detected, then continue recording; After speech message disappearance reaches preset duration, stop recording to realize sending complete speech message.When voice terminate, speech often can occur and also do not terminate, hand has unclamped button or button screen; last or end syllable is caused comparatively early to terminate; sound like unexpected disconnection, here after button lifts, start sound end energy measuring function; when button lifts; detect that voice exist in addition, then continue recording, until end points pause certain time length detected; then be judged as that voice terminate, the whole voice of complete transmission.
Described device, also comprises:
Second continues recoding unit, if for detecting that speech message triggering signal disappears, then continues the interval duration that recording continues to setting.In voice process; if the hand of user key-press shake or touch screen slips off to return again; according to both interval durations; automatically user's continued access is helped to remain valid; and non-immediate terminates; help user in time longer Recording Process, because automatism breaks in recording, especially child often can occur in use Recording Process.In this programme, preferably, the interval duration of described setting is 0.4 ~ 0.6s.If exceed the interval duration of described setting, then terminate recording.
The above; be only the present invention's preferably embodiment; but protection scope of the present invention is not limited thereto; anyly be familiar with those skilled in the art in the technical scope that the present invention discloses; be equal to according to technical scheme of the present invention and inventive concept thereof and replace or change, all should be encompassed within protection scope of the present invention.
Claims (14)
1. voice breakpoint extends the method judged, it is characterized in that, comprising:
Whether real-time detection receives speech message triggering signal;
If so, recording is then started;
Judge the duration of described speech message triggering signal;
If the duration meets short in setting duration, then play the speech message that received and give up described record messages;
If the duration meets long by setting duration, then continue recording to realize sending speech message.
2. method according to claim 1, is characterized in that, if the described duration meets long by setting duration, then continues recording to realize sending speech message, comprises further:
To described short by setting time grow to described length by setting the duration time period in record messages carry out sound end energy measuring;
If testing result is that in this time period, user does not speak, then abandon the record messages in this time period;
If testing result is that in this time period, user speaks, then intercept and preserve the record messages from the place that loquiturs, all the other abandon.
3. method according to claim 2, is characterized in that, described short by setting duration be 0.1 ~ 0.2s, described length by setting duration be 0.3 ~ 0.5s;
The triggering mode of described speech message triggering signal, comprises button and triggers and touch screen triggering;
Described sound end energy measuring is that average energy, last or end syllable energy synthesis has judged based on recording starting point speech energy.
4. voice breakpoint extends the device judged, it is characterized in that, comprising:
Whether the first triggering signal detecting unit, receive speech message triggering signal for detecting in real time;
Recoding unit, if for receiving speech message triggering signal, then starts recording;
Triggering signal timing unit, for judging the duration of described speech message triggering signal;
Play message elements, if meet for the duration short in setting duration, then play the speech message that received and give up described record messages;
Send message elements, if meet for the duration long by setting duration, then continue recording to realize sending speech message.
5. device according to claim 4, is characterized in that, described transmission message elements also comprises:
First speech energy detecting unit, for described short by setting time grow to described length by setting the duration time period in record messages carry out sound end energy measuring;
First processing unit, if for testing result for user in this time period does not speak, then abandon the record messages in this time period;
Second processing unit, if for testing result for user in this time period speaks, then intercept and preserve the record messages from the place that loquiturs, all the other abandon.
6. device according to claim 5, is characterized in that, described short by setting duration be 0.1 ~ 0.2s, described length by setting duration be 0.3 ~ 0.5s;
The triggering mode of described speech message triggering signal, comprises button and triggers and touch screen triggering;
Described sound end energy measuring is that average energy, last or end syllable energy synthesis has judged based on recording starting point speech energy.
7. voice breakpoint extends the method judged, it is characterized in that, comprising:
Whether real-time detection speech message triggering signal disappears;
If so, then start sound end energy measuring Function detection and whether also have speech message;
If have, then continue recording to realize sending complete speech message.
8. method according to claim 7, is characterized in that, has if described, then continue recording to realize sending complete speech message, be specially:
If speech message in addition detected, then continue recording;
After speech message disappearance reaches preset duration, stop recording to realize sending complete speech message.
9. method according to claim 7, is characterized in that, described method, also comprises:
If detect, speech message triggering signal disappears, then continue the interval duration that recording continues to setting.
10. method according to claim 9, is characterized in that, the interval duration of described setting is 0.4 ~ 0.6s.
11. 1 kinds of voice breakpoints extend the device judged, it is characterized in that, comprising:
Whether the second triggering signal detecting unit, disappear for detecting speech message triggering signal in real time;
Second speech energy detecting unit, if disappear for speech message triggering signal, then starts sound end energy measuring Function detection and whether also has speech message;
First continues recoding unit, if for also having speech message, then continues recording to realize sending complete speech message.
12. devices according to claim 11, is characterized in that, described lasting recoding unit, if specifically for speech message in addition being detected, then continue recording; After speech message disappearance reaches preset duration, stop recording to realize sending complete speech message.
13. devices according to claim 11, is characterized in that, described device, also comprises:
Second continues recoding unit, if for detecting that speech message triggering signal disappears, then continues the interval duration that recording continues to setting.
14. devices according to claim 13, is characterized in that, the interval duration of described setting is 0.4 ~ 0.6s.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510111271.9A CN104780263A (en) | 2015-03-10 | 2015-03-10 | Method and device for voice breakpoint extension judgment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510111271.9A CN104780263A (en) | 2015-03-10 | 2015-03-10 | Method and device for voice breakpoint extension judgment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104780263A true CN104780263A (en) | 2015-07-15 |
Family
ID=53621491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510111271.9A Pending CN104780263A (en) | 2015-03-10 | 2015-03-10 | Method and device for voice breakpoint extension judgment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104780263A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106101094A (en) * | 2016-06-08 | 2016-11-09 | 联想(北京)有限公司 | Audio-frequency processing method, sending ending equipment, receiving device and audio frequency processing system |
| CN106686255A (en) * | 2017-03-01 | 2017-05-17 | 广东小天才科技有限公司 | Mobile terminal and voice message sending method thereof |
| CN107170451A (en) * | 2017-06-27 | 2017-09-15 | 乐视致新电子科技（天津）有限公司 | Audio signal processing method and device |
| CN108470571A (en) * | 2018-03-08 | 2018-08-31 | 腾讯音乐娱乐科技（深圳）有限公司 | A kind of audio-frequency detection, device and storage medium |
| CN109344411A (en) * | 2018-09-19 | 2019-02-15 | 深圳市合言信息科技有限公司 | A kind of interpretation method for listening to formula simultaneous interpretation automatically |
| CN109859773A (en) * | 2019-02-14 | 2019-06-07 | 北京儒博科技有限公司 | A kind of method for recording of sound, device, storage medium and electronic equipment |
| WO2019114255A1 (en) * | 2017-12-14 | 2019-06-20 | 深圳Tcl新技术有限公司 | Voice acquisition method, remote control and computer readable storage medium |
| CN110199350A (en) * | 2017-01-17 | 2019-09-03 | 三星电子株式会社 | The electronic equipment of the method and realization this method that terminate for sense speech |
| CN110322885A (en) * | 2018-03-28 | 2019-10-11 | 塞舌尔商元鼎音讯股份有限公司 | Method, computer program product and its proximal end electronic device of artificial intelligent voice interaction |
| CN110914828A (en) * | 2018-09-19 | 2020-03-24 | 深圳市合言信息科技有限公司 | Speech translation method and translation device |
| CN110971739A (en) * | 2018-09-29 | 2020-04-07 | 中兴通讯股份有限公司 | Call voice display method, terminal and computer readable storage medium |
| CN111934705A (en) * | 2020-07-29 | 2020-11-13 | 杭州叙简科技股份有限公司 | Voice anti-loss method and device for interphone, electronic equipment and medium |
| CN112420036A (en) * | 2020-10-10 | 2021-02-26 | 深圳Tcl新技术有限公司 | Voice recognition method, device, terminal equipment and computer readable storage medium |
| CN112735422A (en) * | 2015-09-03 | 2021-04-30 | 谷歌有限责任公司 | Enhanced speech endpoint determination |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6727830B2 (en) * | 1999-01-05 | 2004-04-27 | Microsoft Corporation | Time based hardware button for application launch |
| CN101764882A (en) * | 2009-12-31 | 2010-06-30 | 深圳市戴文科技有限公司 | PTT conversation device and method for realizing PTT conversation |
| CN103152488A (en) * | 2013-03-25 | 2013-06-12 | 成都西可科技有限公司 | Method for realizing voice communication of feature phone by one key |
| US20140024324A1 (en) * | 2012-07-19 | 2014-01-23 | Kirusa, Inc. | Adaptive Communication Mode For Recording A Media Message |
| CN103713876A (en) * | 2014-01-16 | 2014-04-09 | 联想(北京)有限公司 | Data processing method and electronic equipment |
-
2015
- 2015-03-10 CN CN201510111271.9A patent/CN104780263A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6727830B2 (en) * | 1999-01-05 | 2004-04-27 | Microsoft Corporation | Time based hardware button for application launch |
| CN101764882A (en) * | 2009-12-31 | 2010-06-30 | 深圳市戴文科技有限公司 | PTT conversation device and method for realizing PTT conversation |
| US20140024324A1 (en) * | 2012-07-19 | 2014-01-23 | Kirusa, Inc. | Adaptive Communication Mode For Recording A Media Message |
| CN103152488A (en) * | 2013-03-25 | 2013-06-12 | 成都西可科技有限公司 | Method for realizing voice communication of feature phone by one key |
| CN103713876A (en) * | 2014-01-16 | 2014-04-09 | 联想(北京)有限公司 | Data processing method and electronic equipment |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112735422A (en) * | 2015-09-03 | 2021-04-30 | 谷歌有限责任公司 | Enhanced speech endpoint determination |
| CN106101094A (en) * | 2016-06-08 | 2016-11-09 | 联想(北京)有限公司 | Audio-frequency processing method, sending ending equipment, receiving device and audio frequency processing system |
| CN110199350A (en) * | 2017-01-17 | 2019-09-03 | 三星电子株式会社 | The electronic equipment of the method and realization this method that terminate for sense speech |
| CN110199350B (en) * | 2017-01-17 | 2023-09-26 | 三星电子株式会社 | Method for sensing end of speech and electronic device implementing the method |
| CN106686255A (en) * | 2017-03-01 | 2017-05-17 | 广东小天才科技有限公司 | Mobile terminal and voice message sending method thereof |
| CN107170451A (en) * | 2017-06-27 | 2017-09-15 | 乐视致新电子科技（天津）有限公司 | Audio signal processing method and device |
| WO2019114255A1 (en) * | 2017-12-14 | 2019-06-20 | 深圳Tcl新技术有限公司 | Voice acquisition method, remote control and computer readable storage medium |
| CN108470571B (en) * | 2018-03-08 | 2020-09-08 | 腾讯音乐娱乐科技（深圳）有限公司 | Audio detection method and device and storage medium |
| CN108470571A (en) * | 2018-03-08 | 2018-08-31 | 腾讯音乐娱乐科技（深圳）有限公司 | A kind of audio-frequency detection, device and storage medium |
| CN110322885B (en) * | 2018-03-28 | 2023-11-28 | 达发科技股份有限公司 | Artificial intelligent voice interaction method, computer program product and near-end electronic device thereof |
| CN110322885A (en) * | 2018-03-28 | 2019-10-11 | 塞舌尔商元鼎音讯股份有限公司 | Method, computer program product and its proximal end electronic device of artificial intelligent voice interaction |
| CN109344411A (en) * | 2018-09-19 | 2019-02-15 | 深圳市合言信息科技有限公司 | A kind of interpretation method for listening to formula simultaneous interpretation automatically |
| CN110914828A (en) * | 2018-09-19 | 2020-03-24 | 深圳市合言信息科技有限公司 | Speech translation method and translation device |
| CN110971739A (en) * | 2018-09-29 | 2020-04-07 | 中兴通讯股份有限公司 | Call voice display method, terminal and computer readable storage medium |
| CN109859773A (en) * | 2019-02-14 | 2019-06-07 | 北京儒博科技有限公司 | A kind of method for recording of sound, device, storage medium and electronic equipment |
| CN111934705A (en) * | 2020-07-29 | 2020-11-13 | 杭州叙简科技股份有限公司 | Voice anti-loss method and device for interphone, electronic equipment and medium |
| CN112420036A (en) * | 2020-10-10 | 2021-02-26 | 深圳Tcl新技术有限公司 | Voice recognition method, device, terminal equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104780263A (en) | Method and device for voice breakpoint extension judgment | |
| US10474420B2 (en) | Gesture-controlled tabletop speaker system | |
| KR101422020B1 (en) | Method for recognizing voice, and apparatus for implementing the same | |
| WO2001030047A8 (en) | Audio prompted, binary sensors user interface for a consumer electronic device | |
| CN106686494A (en) | Voice input control method of wearable device and wearable device | |
| CN102404455A (en) | Alarm clock control method and system | |
| CN106020510B (en) | The control method and device of terminal | |
| CN107743178B (en) | Message playing method and mobile terminal | |
| CN105771243B (en) | Method and system for realizing multi-user voice interaction in mobile terminal game | |
| EP3413304A3 (en) | Method for operating home appliance and voice recognition server system | |
| CN103886236A (en) | Acoustic control screen unlocking method and mobile terminal | |
| JP2019507404A (en) | Immediate communication apparatus and method | |
| CN107070474A (en) | Switching control method for playing modes of wearable device and wearable device | |
| TW200601144A (en) | A fn-key control system and method | |
| CN106686186B (en) | Playing control method of wearable device and wearable device | |
| CN106686496B (en) | Play mode control method of wearable device and wearable device | |
| CN103744317A (en) | Intelligent control method and control system thereof | |
| WO2016157993A1 (en) | Information processing device, information processing method, and program | |
| CN108513216A (en) | A kind of method of information processing and a kind of line control earphone | |
| CN106788539B (en) | Play mode control method of wearable device and wearable device | |
| CN104796550A (en) | Method for controlling intelligent hardware by aid of bodies during incoming phone call answering | |
| MX2020003097A (en) | Utilization of infant activated audio player. | |
| CN113835807A (en) | Reminding method and device and electronic equipment | |
| CN107170451A (en) | Audio signal processing method and device | |
| JP6023955B2 (en) | COMMUNICATION SYSTEM, COMMUNICATION DEVICE, PROGRAM, AND COMMUNICATION CONTROL METHOD |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150715 |
|
| RJ01 | Rejection of invention patent application after publication |