CN102568473A - Method and device for recording voice signals - Google Patents
Method and device for recording voice signals Download PDFInfo
- Publication number
- CN102568473A CN102568473A CN2011104540838A CN201110454083A CN102568473A CN 102568473 A CN102568473 A CN 102568473A CN 2011104540838 A CN2011104540838 A CN 2011104540838A CN 201110454083 A CN201110454083 A CN 201110454083A CN 102568473 A CN102568473 A CN 102568473A
- Authority
- CN
- China
- Prior art keywords
- voice signal
- energy value
- average energy
- comparative result
- unit
- 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
Images
Landscapes
- Telephone Function (AREA)
Abstract
The invention discloses a method and a device for recording voice signals, and relates to the field of voice identification. The method and the device solve the problem about noise interference when the voice signals are recorded. The method comprises the following steps of: when a user starts a voice recording function, acquiring current input voice signals according to the preset first time window length; calculating the average energy value of the voice signals; comparing the average energy value of the voice signals with the preset average energy value of environmental noise to acquire a first comparison result; and determining whether to record the voice signals or not according to the first comparison result. According to the technical scheme provided by the embodiment, the method and the device can be applied in a voice identification system.
Description
Technical field
The present invention relates to field of speech recognition, relate in particular to a kind of method for recording and device of voice signal.
Background technology
Along with intelligent development of science and technology, the mankind no longer have been satisfied with through mode such as mouse, button and equipment and have carried out alternately, but hope and can carry out alternately through mode and the equipment of voice that realization is controlled the voice of equipment.Speech recognition technology reaches its maturity as one of core technology of interactive voice technology, and be applied in information processing gradually, fields such as education and business application, consumer electronics.
An important step of speech recognition is that the voice signal that the user sends is recorded, and speech recognition system adopts relevant speech recognition algorithm that the sound signal of recording generation is carried out speech recognition then.In the prior art, after the user started speech identifying function, microphone can begin recording automatically; Yet in the use of reality, the user not necessarily sends voice signal at once; Generally speaking, start speech identifying function and send the user and can have part free time between the voice signal, at this moment between in the section; Microphone can be recorded to the noise of surrounding environment, owing to there is noise, has reduced the recognition accuracy of speech recognition system.
Summary of the invention
Embodiments of the invention provide a kind of method for recording and device of voice signal, can improve the accuracy rate of speech recognition.
On the one hand, a kind of method for recording of voice signal is provided, has comprised: after the user starts the voice recording function, obtained the voice signal of current input according to the very first time window length that is provided with in advance; Calculate the average energy value of said voice signal; The average energy value of said voice signal the average energy value with the neighbourhood noise that is provided with is in advance compared, obtain first comparative result; Determine whether said voice signal is recorded according to said first comparative result.
On the other hand, a kind of record device of voice signal is provided, has comprised:
First acquiring unit is used for after the user starts the voice recording function, obtains the voice signal of current input according to the very first time window length that is provided with in advance;
First computing unit is used to calculate the average energy value of the voice signal that said first acquiring unit obtains;
First comparing unit, the average energy value of the voice signal that is used for said first computing unit is obtained compares with the average energy value of the neighbourhood noise that is provided with in advance, obtains first comparative result;
Confirm the unit, first comparative result that the user obtains according to said first comparing unit determines whether said voice signal is recorded.
The method for recording of the voice messaging that the embodiment of the invention provides and device; Comparative result according to the average energy value of the average energy value of neighbourhood noise and voice signal determines whether voice signal is recorded; Be recorded to the problem of simple neighbourhood noise when having avoided voice signal to record; Because technical scheme of the present invention is considered the influence that neighbourhood noise is recorded voice signal, make that the voice signal that adopts technical scheme provided by the invention to record is more accurate, thereby improved the accuracy of the voice signal of recording being carried out speech recognition; Further, save voice signal and recorded the storage resources and the communication resource that takies.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art; To do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art below; Obviously, the accompanying drawing in describing below only is some embodiments of the present invention, for those of ordinary skills; Under the prerequisite of not paying creative work, can also obtain other accompanying drawing according to these accompanying drawings.
The method for recording process flow diagram one of the voice signal that Fig. 1 provides for the embodiment of the invention;
The method for recording flowchart 2 of the voice signal that Fig. 2 provides for the embodiment of the invention;
The record device structural representation one of the voice signal that Fig. 3 provides for the embodiment of the invention;
The record device structural representation two of the voice signal that Fig. 4 provides for the embodiment of the invention;
The record device structural representation three of the voice signal that Fig. 5 provides for the embodiment of the invention;
The record device structural representation four of the voice signal that Fig. 6 provides for the embodiment of the invention.
Embodiment
To combine the accompanying drawing in the embodiment of the invention below, the technical scheme in the embodiment of the invention is carried out clear, intactly description, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills are not making the every other embodiment that is obtained under the creative work prerequisite, all belong to the scope of the present invention's protection.
The problem of noise when recording in order to solve voice signal, the embodiment of the invention provides a kind of method for recording and device of voice signal.
As shown in Figure 1, the method for recording of the voice signal that the real embodiment of the present invention provides comprises:
Present embodiment does not carry out concrete qualification to very first time window length, and in the use of reality, the user can not do here and give unnecessary details according to the self-defined setting of demand very first time window length.
In the present embodiment; The average energy value of neighbourhood noise can be to store in advance, for example: can neighbourhood noise be arranged to different state, as: quiet, generally perhaps noisy etc.; And the average energy value of different environment noise is set according to different state; The average energy value like the corresponding neighbourhood noise of rest state is 20dB, and the average energy value of the neighbourhood noise that general state is corresponding is 30dB, and the average energy value of the neighbourhood noise that noisy mode is corresponding is 50dB etc.
The average energy value of neighbourhood noise also can change detection acquisition in real time according to dynamic environment, then this moment, before step 103, can also comprise the step of obtaining the average energy value of current environment noise according to second time window length of setting in advance.Need to prove, ground identical with very first time window length, the embodiment of the invention is not carried out concrete qualification to second time window length yet, and the user can self-defined as required setting, does not do here and gives unnecessary details.
Alternatively; If the average energy value of neighbourhood noise is to detect in real time to obtain; For the convenience of follow-up use, to save and detect the resource that consumes, the method for recording of the voice signal that the embodiment of the invention provides can also comprise the step that the average energy value of current environment noise is stored.
Certainly, more than be merely two kinds of concrete giving an example, in the use of reality, the user can also obtain the average energy value of neighbourhood noise through other modes, gives unnecessary details no longer one by one here.
Particularly, if first comparative result is the average energy value of voice signal the average energy value greater than the neighbourhood noise that is provided with in advance, voice signal is recorded; Otherwise, voice signal is not recorded.
The method for recording of the voice messaging that the embodiment of the invention provides; Comparative result according to the average energy value of the average energy value of neighbourhood noise and voice signal determines whether voice signal is recorded; Be recorded to the problem of simple neighbourhood noise when having avoided voice signal to record; Because technical scheme of the present invention is considered the influence that neighbourhood noise is recorded voice signal, make that the voice signal that adopts technical scheme provided by the invention to record is more accurate, thereby improved the accuracy of the voice signal of recording being carried out speech recognition; Further, save voice signal and recorded the storage resources and the communication resource that takies.
For fear of the influence that transient noise is recorded voice signal, as shown in Figure 2, another embodiment of the present invention also provides a kind of method for recording of voice messaging, this method and as shown in Figure 1 basic identical, and its difference is: after step 101, also comprise:
In the present embodiment, step 105 specifically be positioned at after the step 101 and step 102 before, in the use of reality, step 105 also can be positioned at other positions, does not do here and gives unnecessary details.
Then this moment, step 104 replaces with: according to first comparative result and second comparative result, determine whether voice signal and next section voice signal are recorded.
The method for recording of the voice messaging that the embodiment of the invention provides; Comparative result according to the average energy value of the average energy value of neighbourhood noise and voice signal determines whether voice signal is recorded; Be recorded to the problem of simple neighbourhood noise when having avoided voice signal to record; Because technical scheme of the present invention is considered the influence that neighbourhood noise is recorded voice signal, make that the voice signal that adopts technical scheme provided by the invention to record is more accurate, thereby improved the accuracy of the voice signal of recording being carried out speech recognition; Further, save voice signal and recorded the storage resources and the communication resource that takies.
As shown in Figure 3, the embodiment of the invention also provides a kind of record device of voice signal, comprising:
First acquiring unit 301 is used for after the user starts the voice recording function, obtains the voice signal of current input according to the very first time window length that is provided with in advance;
First comparing unit 303, the average energy value of the voice signal that is used for first computing unit 302 is obtained compares with the average energy value of the neighbourhood noise that is provided with in advance, obtains first comparative result;
Confirm unit 304, the user determines whether voice signal is recorded according to first comparative result that first comparing unit 303 obtains.
Further, as shown in Figure 4, the record device of the voice signal that the embodiment of the invention provides can also comprise:
Then said first comparing unit 303, the average energy value of the voice signal that can also be used for first computing unit 302 is obtained and the average energy value of the current environment noise that second acquisition unit 305 obtains compare, and obtain first comparative result.
Further, as shown in Figure 5, the record device of the voice signal that the embodiment of the invention provides can also comprise:
Then said first comparing unit 303, the average energy value of the current environment noise of the average energy value of the voice signal that can also be used for first computing unit 302 is obtained and storage unit 306 storages compares, and obtains first comparative result.
Further, as shown in Figure 6, the record device of the voice signal that the embodiment of the invention provides can also comprise:
The 3rd acquiring unit 308; If being used for the comparative result that first comparing unit 303 obtains is the average energy value of voice signal the average energy value greater than the neighbourhood noise that is provided with in advance, obtain next section voice signal adjacent with voice signal according to very first time window length;
Second comparing unit 310, the average energy value that is used for the average energy value that second computing unit 309 is obtained and the neighbourhood noise that is provided with in advance compares, and obtains second comparative result;
Then said definite unit 304; Second comparative result that first comparative result that can also be used for obtaining according to first comparing unit 303 and second comparing unit 310 obtain determines whether that the voice signal that voice signal and the 3rd acquiring unit 308 to buffer unit 307 buffer memorys obtain records.
Need to prove that the method for recording of the voice signal that the concrete implementation method of the record device of the voice signal that the embodiment of the invention provides can provide referring to the embodiment of the invention is said, repeats no more here.
The record device of the voice messaging that the embodiment of the invention provides; Comparative result according to the average energy value of the average energy value of neighbourhood noise and voice signal determines whether voice signal is recorded; Be recorded to the problem of simple neighbourhood noise when having avoided voice signal to record; Because technical scheme of the present invention is considered the influence that neighbourhood noise is recorded voice signal, make that the voice signal that adopts technical scheme provided by the invention to record is more accurate, thereby improved the accuracy of the voice signal of recording being carried out speech recognition; Further, save voice signal and recorded the storage resources and the communication resource that takies.
The method for recording of the voice signal that the embodiment of the invention provides and device can be applied in the speech recognition system.
The above; Be merely embodiment of the present invention, but protection scope of the present invention is not limited thereto, any technician who is familiar with the present technique field is in the technical scope that the present invention discloses; Can expect easily changing or replacement, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion by said protection domain with claim.
Claims (9)
1. the method for recording of a voice signal is characterized in that, comprising:
After the user starts the voice recording function, obtain the voice signal of current input according to the very first time window length that is provided with in advance;
Calculate the average energy value of said voice signal;
The average energy value of said voice signal the average energy value with the neighbourhood noise that is provided with is in advance compared, obtain first comparative result;
Determine whether said voice signal is recorded according to said first comparative result.
2. method according to claim 1 is characterized in that, also comprises:
Obtain the average energy value of current environment noise according to second time window length that is provided with in advance;
Then said the average energy value of said voice signal the average energy value with the neighbourhood noise that is provided with is in advance compared, obtains first comparative result and be:
The average energy value of said voice signal and the average energy value of said current environment noise are compared, obtain first comparative result.
3. method according to claim 2 is characterized in that, also comprises:
The average energy value to said current environment noise is stored.
4. method according to claim 1 is characterized in that, said determine whether said voice signal recorded according to said first comparative result comprise:
If the average energy value that said first comparative result is said voice signal is recorded said voice signal greater than the average energy value of the said neighbourhood noise that is provided with in advance;
Otherwise, said voice signal is not recorded.
5. method according to claim 1 is characterized in that, also comprises:
Said voice signal is carried out buffer memory;
If the average energy value that said first comparative result is said voice signal obtains next section voice signal adjacent with said voice signal greater than the average energy value of the neighbourhood noise that is provided with in advance according to said very first time window length;
Calculate the average energy value of said next section voice signal;
The average energy value of said next section voice signal and the average energy value of the said neighbourhood noise that is provided with are in advance compared, obtain second comparative result;
Then said determine whether said voice signal recorded according to said first comparative result replace with:
According to said first comparative result and second comparative result, determine whether said voice signal and said next section voice signal are recorded.
6. the record device of a voice signal is characterized in that, comprising:
First acquiring unit is used for after the user starts the voice recording function, obtains the voice signal of current input according to the very first time window length that is provided with in advance;
First computing unit is used to calculate the average energy value of the voice signal that said first acquiring unit obtains;
First comparing unit, the average energy value of the voice signal that is used for said first computing unit is obtained compares with the average energy value of the neighbourhood noise that is provided with in advance, obtains first comparative result;
Confirm the unit, first comparative result that the user obtains according to said first comparing unit determines whether said voice signal is recorded.
7. device according to claim 6 is characterized in that, also comprises:
Second acquisition unit is used for obtaining according to second time window length that is provided with in advance the average energy value of current environment noise;
Then said first comparing unit, the average energy value of the voice signal that also is used for said first computing unit is obtained and the average energy value of the current environment noise that said second acquisition unit obtains compare, and obtain first comparative result.
8. device according to claim 7 is characterized in that, also comprises:
Storage unit, the average energy value of the current environment noise that is used for said second acquisition unit is obtained is stored;
Then said first comparing unit, the average energy value of the average energy value of the voice signal that also is used for said first computing unit is obtained and the current environment noise of said cell stores compares, and obtains first comparative result.
9. device according to claim 6 is characterized in that, also comprises:
Buffer unit is used for the voice signal that said first acquiring unit obtains is carried out buffer memory;
The 3rd acquiring unit; If being used for the comparative result that said first comparing unit obtains is the average energy value of said voice signal the average energy value greater than the neighbourhood noise that is provided with in advance, obtain next section voice signal adjacent with said voice signal according to said very first time window length;
Second computing unit is used to calculate the average energy value of next section voice signal that said the 3rd acquiring unit obtains;
Second comparing unit, the average energy value and said the average energy value of the neighbourhood noise of setting in advance of being used for said second computing unit is obtained compare, and obtain second comparative result;
Then said definite unit; Second comparative result that first comparative result that also is used for obtaining according to first comparing unit and said second comparing unit obtain determines whether that the voice signal that voice signal and said the 3rd acquiring unit to said buffer unit buffer memory obtain records.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104540838A CN102568473A (en) | 2011-12-30 | 2011-12-30 | Method and device for recording voice signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104540838A CN102568473A (en) | 2011-12-30 | 2011-12-30 | Method and device for recording voice signals |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102568473A true CN102568473A (en) | 2012-07-11 |
Family
ID=46413730
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011104540838A Pending CN102568473A (en) | 2011-12-30 | 2011-12-30 | Method and device for recording voice signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102568473A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103901782A (en) * | 2012-12-25 | 2014-07-02 | 联想(北京)有限公司 | Sound control method, electronic device and sound control apparatus |
| CN103903623A (en) * | 2014-03-31 | 2014-07-02 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN104202321A (en) * | 2014-09-02 | 2014-12-10 | 上海天脉聚源文化传媒有限公司 | Method and device for voice recording |
| CN107633854A (en) * | 2017-09-29 | 2018-01-26 | 联想(北京)有限公司 | The processing method and electronic equipment of a kind of speech data |
| CN110111816A (en) * | 2019-02-27 | 2019-08-09 | 咪咕数字传媒有限公司 | Method, the method for audio processing, electronic equipment and the server-side of recording audio |
| CN112233697A (en) * | 2020-12-09 | 2021-01-15 | 北京云测信息技术有限公司 | Audio data detection method and device and audio data detection equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1245376A (en) * | 1998-08-17 | 2000-02-23 | 英业达股份有限公司 | Method for detecting squelch of IP telephone |
| CN1912993A (en) * | 2005-08-08 | 2007-02-14 | 中国科学院声学研究所 | Voice end detection method based on energy and harmonic |
| US20090070106A1 (en) * | 2006-03-20 | 2009-03-12 | Mindspeed Technologies, Inc. | Method and system for reducing effects of noise producing artifacts in a speech signal |
| CN101458943A (en) * | 2008-12-31 | 2009-06-17 | 北京中星微电子有限公司 | Sound recording control method and sound recording device |
-
2011
- 2011-12-30 CN CN2011104540838A patent/CN102568473A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1245376A (en) * | 1998-08-17 | 2000-02-23 | 英业达股份有限公司 | Method for detecting squelch of IP telephone |
| CN1912993A (en) * | 2005-08-08 | 2007-02-14 | 中国科学院声学研究所 | Voice end detection method based on energy and harmonic |
| US20090070106A1 (en) * | 2006-03-20 | 2009-03-12 | Mindspeed Technologies, Inc. | Method and system for reducing effects of noise producing artifacts in a speech signal |
| CN101458943A (en) * | 2008-12-31 | 2009-06-17 | 北京中星微电子有限公司 | Sound recording control method and sound recording device |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103901782A (en) * | 2012-12-25 | 2014-07-02 | 联想(北京)有限公司 | Sound control method, electronic device and sound control apparatus |
| CN103901782B (en) * | 2012-12-25 | 2017-08-29 | 联想(北京)有限公司 | A kind of acoustic-controlled method, electronic equipment and sound-controlled apparatus |
| CN103903623A (en) * | 2014-03-31 | 2014-07-02 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN103903623B (en) * | 2014-03-31 | 2017-09-29 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN104202321A (en) * | 2014-09-02 | 2014-12-10 | 上海天脉聚源文化传媒有限公司 | Method and device for voice recording |
| CN107633854A (en) * | 2017-09-29 | 2018-01-26 | 联想(北京)有限公司 | The processing method and electronic equipment of a kind of speech data |
| CN110111816A (en) * | 2019-02-27 | 2019-08-09 | 咪咕数字传媒有限公司 | Method, the method for audio processing, electronic equipment and the server-side of recording audio |
| CN112233697A (en) * | 2020-12-09 | 2021-01-15 | 北京云测信息技术有限公司 | Audio data detection method and device and audio data detection equipment |
| CN112233697B (en) * | 2020-12-09 | 2021-04-13 | 北京云测信息技术有限公司 | Audio data detection method and device and audio data detection equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102568473A (en) | Method and device for recording voice signals | |
| CN108564966B (en) | Voice test method and device with storage function | |
| US10522164B2 (en) | Method and device for improving audio processing performance | |
| CN107527630B (en) | Voice endpoint detection method and device and computer equipment | |
| CN108922564B (en) | Emotion recognition method and device, computer equipment and storage medium | |
| CN110288997A (en) | Equipment awakening method and system for acoustics networking | |
| JP6999012B2 (en) | Audio signal detection method and equipment | |
| CN108664472B (en) | Natural language processing method, device and equipment | |
| CN107516510A (en) | A kind of smart machine automated voice method of testing and device | |
| CN108446322A (en) | A kind of implementation method and device of intelligent Answer System | |
| US20210067470A1 (en) | Methods and systems for improving chatbot intent training | |
| CN110780741B (en) | Model training method, application running method, device, medium and electronic equipment | |
| CN109036412A (en) | voice awakening method and system | |
| CN103902963A (en) | Method and electronic equipment for recognizing orientation and identification | |
| CN104123950A (en) | Sound recording method and device | |
| CN110379410A (en) | Voice response speed automatic analysis method and system | |
| CN103646654A (en) | Recording data sharing method and terminal | |
| CN105118522A (en) | Noise detection method and device | |
| CN101778333B (en) | Detection method and device of microphone state | |
| US9978383B2 (en) | Method for processing speech/audio signal and apparatus | |
| CN113259832B (en) | Microphone array detection method and device, electronic equipment and storage medium | |
| CN104423543A (en) | Information processing method and device | |
| CN105355197A (en) | Gain processing method and device for speech recognition system | |
| CN104599679A (en) | Speech signal based focus covariance matrix construction method and device | |
| CN108900959B (en) | Method, device, equipment and computer readable medium for testing voice interaction equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120711 |