CN101840700B - Voice recognition method based on mobile terminal and mobile terminal - Google Patents
Voice recognition method based on mobile terminal and mobile terminal Download PDFInfo
- Publication number
- CN101840700B CN101840700B CN2010101629008A CN201010162900A CN101840700B CN 101840700 B CN101840700 B CN 101840700B CN 2010101629008 A CN2010101629008 A CN 2010101629008A CN 201010162900 A CN201010162900 A CN 201010162900A CN 101840700 B CN101840700 B CN 101840700B
- Authority
- CN
- China
- Prior art keywords
- sound signal
- preset
- identifying information
- portable terminal
- earphone
- 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
Images
Landscapes
- Telephone Function (AREA)
Abstract
The embodiment of the invention provides a voice recognition method based on a mobile terminal. The method comprises the following steps: collecting environmental sound signals; indentifying the environmental sound signals according to preset identification information; when the environmental sound signals contain special sound signals matching the preset identification information, judging whether the loudness of the special sound signals reach the preset threshold; and if so, controlling to output the special sound signals. Correspondingly, the embodiment of the invention also provides a mobile terminal. The mobile terminal of the invention utilizes the voice recognition technology, overcomes the application defects of the headset of the existing mobile terminal, eliminates the hidden danger caused by the reduced induction to the external environment sound when the user uses the headset of a mobile terminal and promotes the user experience.
Description
Technical field
The present invention relates to the communications field, relate in particular to sound identification method and portable terminal based on portable terminal.
Background technology
Speech recognition technology its essence is to let machine pass through identification and understanding process changes voice signal (or voice signal) into the technology of corresponding text or order.Along with development of Communication Technique, portable terminal is also constantly improving.Existing portable terminal generally all is equipped with earphone, comprise wired earphone and wireless headset (such as: bluetooth earphone), be user-friendly to (such as: listen song or vacate both hands and do other thing).The inventor finds that mainly there is following defective in existing portable terminal:
1, there is potential safety hazard.Because the use of earphone can weaken user's induction of ambient sound to external world,, the user uses earphone when going on a journey, possibly there is great potential safety hazard because the tucket of not hearing vehicle or dangerous alarm song when coming causes the event of traffic everything.
2, influence user experience.The user maybe be owing to not hearing that friend or other people greeting damage user's social networks, influence user's experience when using earphone.
Summary of the invention
The objective of the invention is to; Sound identification method and portable terminal based on portable terminal are provided, utilize speech recognition technology, eliminate the user when using the earphone of portable terminal; Because the induction of ambient sound weakens the potential safety hazard that is caused to external world, promote user experience.
To achieve these goals, the embodiment of the invention provides a kind of sound identification method based on portable terminal, and said portable terminal comprises earphone, and said method comprises:
Gather environmental sound signal;
According to preset identifying information, said environmental sound signal is discerned;
When comprising the particular sound signal that is complementary with said preset identifying information in the said environmental sound signal, whether the loudness of judging said particular sound signal reaches preset and the corresponding loudness threshold values of said preset identifying information;
When the loudness of said particular sound signal reaches the corresponding loudness threshold values of said preset and said preset identifying information, the said particular sound signal of control output.
Further, before the said collection environmental sound signal, also comprise: when said earphone is in the insertion state, trigger the collection of said environmental sound signal.
Further; It is said when said earphone is in the insertion state; Trigger before the collection of said environmental sound signal, also comprise: preestablish the loudness threshold values of multiple identifying information and each identifying information, said identifying information comprises non-speech recognition information and/or voice recognition information.
Further, said non-speech recognition information comprises: any one or more in honk, bicycle the tinkle of bells and the alarm song; Said voice recognition information comprises: any one or more in machine master name, nickname or the another name of the dialogue people's who is preserved when the contact person's who is preserved during the voice call of said portable terminal speech information, daily dialogue speech information and the said portable terminal preserved with text or speech form.
Further, said control is exported said particular sound signal and is comprised: control said earphone and export said particular sound signal; Or control said mobile terminal vibration, to export said particular sound signal; Or control the light flash of said portable terminal, to export said particular sound signal; Or control the said particular sound signal of said mobile terminal displays.
Correspondingly, the embodiment of the invention also provides a kind of portable terminal, comprises earphone, also comprises:
Acquisition module is used to gather environmental sound signal;
Identification module is used for according to preset identifying information the said environmental sound signal that said acquisition module collects being discerned;
Judge module; Be used for when said identification module identifies said environmental sound signal and comprises the particular sound signal that is complementary with said preset identifying information, whether the loudness of judging said particular sound signal reaches preset and the corresponding loudness threshold values of said preset identifying information;
Control module is used for when said judge module judges that the loudness of said particular sound signal reaches the corresponding loudness threshold values of said preset and said preset identifying information the said particular sound signal of control output.
Further, said portable terminal also comprises: trigger module, be used to detect the insertion signal of said earphone, and trigger the collection that said acquisition module carries out said environmental sound signal.
Further, said portable terminal also comprises: presetting module, be used to preestablish the loudness threshold values of multiple identifying information and each identifying information, and said identifying information comprises non-speech recognition information and/or voice recognition information.
Further, said identification module comprises: the non-speech recognition unit is used for according to preset non-speech recognition information the said environmental sound signal that said acquisition module collects being discerned; Voice recognition unit is used for according to preset voice recognition information the said environmental sound signal that said acquisition module collects being discerned.
Further, said acquisition module is located in the said earphone; Said acquisition module comprises at least one microphone.
The present invention is through presetting identifying information and threshold values at portable terminal; And gather environmental sound signal in real time; When certain particular sound signal in the environmental sound signal and preset identifying information are complementary and reach corresponding loudness threshold values; The output of control particular sound signal has promoted user's sensing capability of ambient sound to external world when earphone to notify the machine master; In addition; Through preset various identifying informations, such as: various dangerous information such as honk, eliminated the potential safety hazard the when user uses earphone; For another example: various address information such as preset machine master's name, nickname; When friend greets the machine master, can notify the machine master, promoted user experience; Simultaneously, can both can guarantee the operate as normal of earphone, can well extraneous effective environmental voice signal have been notified to the user again, promote user experience through the loudness threshold values of the preset various identifying informations of actual conditions.
Description of drawings
Fig. 1 is the structural representation of the embodiment of portable terminal of the present invention;
Fig. 2 is the structural representation of embodiment of the identification module of portable terminal of the present invention;
Fig. 3 is the process flow diagram of first embodiment of the sound identification method based on portable terminal of the present invention;
Fig. 4 is the process flow diagram of second embodiment of the sound identification method based on portable terminal of the present 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.
See also Fig. 1, be the structural representation of the embodiment of portable terminal of the present invention; As shown in Figure 1, said portable terminal comprises: acquisition module 40, identification module 50, judge module 60 and control module 70.
Said acquisition module 40 is used to gather environmental sound signal;
In concrete the realization, said acquisition module 40 is a sound pick up equipment, is used for gathering the voice signal in the external environment, and it can have the device of pickup function for microphone, sound transducer or other.Particularly, said environmental sound signal can refer to all voice signals that can pick up in the external environment, comprises honk, pedestrian's voice or cry, bicycle the tinkle of bells, the extraneous music of playing, tweedle or the like.Usually, said acquisition module 40 can adopt at least one common omni-directional microphone to carry out pickup.In the practical application; Because omni-directional microphone only can collected sound signal; But can not realize the location of ambient sound, preferably, said acquisition module 40 can adopt at least two unidirectivity microphones; This unidirectivity microphone has the environmental sound signal of optionally gathering certain orientation, can be good at realizing the location of environmental sound signal.
Said identification module 50 is used for according to preset identifying information the said environmental sound signal that said acquisition module 40 collects being discerned;
In concrete the realization; The environmental sound signal that said identification module 50 is used for is to external world discerned; Judge the particular sound signal that whether said environmental sound signal comprises and preset identifying information is complementary (same or similar), and its particular sound signal is identified.Such as: said acquisition module 40 collects the mixed environment voice signal; The sound that has wherein comprised environment non-voices such as honk; Suppose to have preset honk as non-speech recognition information; Said identification module 50 identifies the identical or similar particular sound signal of identifying information (honk) with preset that comprises in the mixed environment voice signal according to this preset identifying information; For another example: said acquisition module 40 collects the mixed environment voice signal; The sound such as ring tone that wherein comprised machine master name; Suppose to have preset machine master name as identifying information with textual form; Said identification module 50 converts the call sound of the machine master name that comprises in the mixed environment voice signal into text message; Compare with preset machine master name text information, if the two is identical or similar, then said identification module 50 identifies this particular sound signal (ring tone of machine master name); For another example: said acquisition module 40 collects the mixed environment voice signal; Wherein comprised the contact person's sound that carries out voice call with the machine master; The sound of having supposed to preset this contact person is as identifying information; Said identification module 50 identifies the identical or similar particular sound signal of identifying information (contact person's sound) with preset that comprises in the mixed environment voice signal according to this preset identifying information;
Said judge module 60 is used for when said identification module 50 identifies said environmental sound signal and comprises the particular sound signal that is complementary with said preset identifying information, judging whether the loudness of said particular sound signal reaches preset threshold values;
In concrete the realization, said threshold values is a threshold value of sound intensity, and it can be set according to actual needs.Such as: for the acoustic information of danger signals such as honk, bicycle the tinkle of bells, alarm song, can take the highest loudness threshold values, hear that with the user situation that this voice signal can in time avert danger sets; For another example: for the voice signal of friend's beeper master name, can take minimum loudness threshold values, with the sound that picks up of sensitivity, the inaudible phenomenon of avoiding greeting.Carry out the flexible setting of threshold values here according to actual needs; Both can avoid too sensitive collection ambient signal and disturb the operate as normal of earphone; Guarantee the operate as normal of earphone, again can be sensitive carry out picking up of sound, well extraneous effective environmental voice signal is notified to the user.
Particularly; When said identification module 50 identifies the particular sound signal that is complementary with preset identifying information from environmental sound signal; Such as: honk, said judge module 60 judge promptly whether the loudness of this honk that identifies reaches preset threshold values.
Said control module 70 is used for when said judge module 60 judges that the loudness of said particular sound signal reaches said preset threshold values the said particular sound signal of control output.
In concrete the realization, when said particular sound signal reached said preset threshold values, said control module 70 promptly control and is exported said particular sound signal, to notify the user.Particularly, the mode of said control module 70 control particular sound signal outputs can have multiple, includes but not limited to:
One of which: the earphone of control portable terminal is exported said particular sound signal; Particularly, can suspend the content of former earphone output, and only play this environmental sound signal; Maybe can content and this particular sound signal of the output of former earphone be carried out audio mixing, export the voice signal behind the audio mixing then;
Its two: control said mobile terminal vibration, to export said particular sound signal; This way of output belongs to a kind of aid prompting, is careful external environment by mobile terminal vibration with the prompting user;
Its three: control the light flash of said portable terminal, to export said particular sound signal; This way of output also belongs to a kind of aid prompting, by the light flash of portable terminal, such as: LED (Light EmittingDisplay, light emitting diode) flicker, or the keyboard light flicker of portable terminal etc., be careful external environment with the prompting user;
Its four: control the said particular sound signal of said mobile terminal displays; The prerequisite of this way of output does; This mobile terminal stores the relevant information of this particular sound signal; Such as: friend's beeper master name; Its prerequisite is to have stored this information of friends in the portable terminal, comprises acoustic information, name, contact method etc., the corresponding information of the above-mentioned storage of the said said mobile terminal displays of control module 70 may command.
See also Fig. 1 again, said portable terminal also comprises: earphone 10, trigger module 20 and presetting module 30.
Said earphone 10, its can for wired earphone or wireless headset (such as: bluetooth earphone).
Because the instability of portable terminal (such as: the hand-holdable portable terminal of user rotates), therefore, the acquisition module 40 of said portable terminal adopts at least two unidirectivity microphones can not well carry out the location of environmental sound signal; Therefore, preferably, said acquisition module 40 can encapsulate to be located in the said earphone 10; Preferably; Said acquisition module 40 can comprise two unidirectivity microphones, and its left and right sides earphone respectively is provided with one, can well realize the location of environmental sound signal; Such as: when the microphone picking up surrounding sounds signal of left earphone, the control module 70 may command particular sound signal of portable terminal are from said left earphone output, note the external environment in the orientation that the microphone of said left ear is pointed with the prompting user; For another example: when the microphone picking up surrounding sounds signal of right earphone, the control module 70 may command particular sound signal of portable terminal are exported from said right earphone, note the external environment in the orientation that the microphone of said auris dextra is pointed with the prompting user; Preferably, in order to reach the better more omnibearing voice signal that picks up, can make the sensing of the microphone in the earphone of the left and right sides different, concrete processing is similar with above-mentioned situation, does not give unnecessary details at this.
Said trigger module 20 is used to detect the insertion signal of said earphone 10, triggers said acquisition module 40 and carries out the collection of said environmental sound signal.
In concrete the realization, when said earphone 10 was wired earphone, said trigger module 20 can adopt hardware, such as chip or CPU etc., utilized the plug state of hardware detection wired earphone; When said earphone 10 is wireless headset (bluetooth earphone); Said trigger module 20 can adopt software to detect the plug state of said wireless headset; When detecting said earphone 10 and insert, trigger said acquisition module 40 and carry out the collection of said environmental sound signal.
Said presetting module 30 is used to preestablish the loudness threshold values of multiple identifying information and each identifying information, and said identifying information comprises non-speech recognition information and/or voice recognition information.
In concrete the realization; Said presetting module 30 can be an identification storehouse; This identification library storage various predefined identifying information and the pairing loudness threshold values of various identifying information that are used for sound recognition; Wherein, the non-speech recognition information in this identifying information includes but not limited to: honk, bicycle the tinkle of bells and alarm song; Text message in this identifying information includes but not limited to: said voice recognition information includes but not limited to: any one or more in machine master name, nickname or the another name of the dialogue people's who is preserved when the contact person's who is preserved during the voice call of said portable terminal speech information, daily dialogue speech information and the said portable terminal preserved with text or speech form.Particularly, the form that said presetting module 30 can be shown provides an identification storehouse, like following table:
Table one: identification storehouse
It is understandable that above-mentioned table one is merely for example, the user can preset other identifying information and corresponding threshold values according to actual needs, such as: predeterminable contact person's speech recognition library or other identification storehouses, but various situation similar analysis is not given unnecessary details at this.
As above-mentioned; When said identification module 50 identifies when including the particular sound signal (honk) that is complementary with preset identifying information in the environmental sound signal; Said judge module 60 judges promptly according to the threshold values of honk in the said presetting module 30 whether the loudness of this particular sound signal reaches this threshold values.
The present invention is through presetting identifying information and threshold values at portable terminal; And gather environmental sound signal in real time; When certain particular sound signal in the environmental sound signal and preset identifying information are complementary and reach corresponding loudness threshold values; The output of control particular sound signal has promoted user's sensing capability of ambient sound to external world when earphone to notify the machine master; In addition; Through preset various identifying informations, such as: various dangerous information such as honk, eliminated the potential safety hazard the when user uses earphone; For another example: various address information such as preset machine master's name, nickname; When friend greets the machine master, can notify the machine master, promoted user experience; Simultaneously, can both can guarantee the operate as normal of earphone, can well extraneous effective environmental voice signal have been notified to the user again, promote user experience through the loudness threshold values of the preset various identifying informations of actual conditions.
For clearer explanation the present invention, will the identification module 50 of portable terminal of the present invention be described in detail below.
See also Fig. 2, be the structural representation of the embodiment of the identification module of portable terminal of the present invention; As shown in Figure 2, said identification module 50 comprises: non-speech recognition unit 501 and voice recognition unit 502.
Said non-speech recognition unit 501 is used for according to preset non-speech recognition information the said environmental sound signal that said acquisition module 40 collects being discerned;
In concrete the realization; The environmental sound signal that said non-speech recognition unit 501 is used for is to external world discerned; Judge the particular sound signal that whether said environmental sound signal comprises and preset non-speech recognition information is complementary (same or similar), and its particular sound signal is identified.Such as: said acquisition module 40 collects the mixed environment voice signal; Sound such as honk have wherein been comprised; Supposed to preset the identifying information of honk as sound (environment non-voice); Said non-speech recognition unit 501 identifies the identical or similar particular sound signal of non-speech recognition information (honk) with preset that comprises in the mixed environment voice signal according to this preset non-speech recognition information.
Said voice recognition unit 502 is used for according to preset voice recognition information the said environmental sound signal that said acquisition module 40 collects being discerned;
In concrete the realization; The environmental sound signal that said voice recognition unit 502 is used for is to external world discerned; Judge the particular sound signal that whether said environmental sound signal comprises and preset voice recognition information is complementary (same or similar), and its particular sound signal is identified.Such as: said acquisition module 40 collects the mixed environment voice signal; The sound such as ring tone that wherein comprised machine master name; Suppose to have preset machine master name as identifying information with textual form; Said voice recognition unit 502 converts the call sound of the machine master name that comprises in the mixed environment voice signal into text message; Compare with preset machine master name text information, if the two is identical or similar, then said voice recognition unit 502 identifies this particular sound signal (ring tone of machine master name); For another example: said acquisition module 40 collects the mixed environment voice signal; Wherein comprised the contact person's sound that carries out voice call with the machine master; The sound of having supposed to preset this contact person is as identifying information (preserving this contact person's speech information) when mobile terminal sound is conversed; Said voice recognition unit 502 identifies the identical or similar particular sound signal of identifying information (contact person's sound) with preset that comprises in the mixed environment voice signal according to this preset identifying information;
The present invention utilizes speech recognition technology, eliminates the user when using the earphone of portable terminal, because the induction of ambient sound weakens the potential safety hazard that is caused to external world, promotes user experience.
For clearer explanation the present invention, will the sound identification method that the present invention is based on portable terminal be described in detail below.
See also Fig. 3, be the process flow diagram of first embodiment of the sound identification method based on portable terminal of the present invention; As shown in Figure 3, said method comprises:
S101 gathers environmental sound signal;
In concrete the realization, said S101 adopts sound pick up equipment to gather the voice signal in the external environment, and it can adopt microphone, sound transducer or other to have the device of pickup function.Particularly, said environmental sound signal can refer to all voice signals that can pick up in the external environment, comprises honk, pedestrian's voice or cry, bicycle the tinkle of bells, the extraneous music of playing, tweedle or the like.Usually, said S101 can adopt at least one common omni-directional microphone to carry out pickup.In the practical application; Because omni-directional microphone only can collected sound signal; But can not realize the location of ambient sound, preferably, said S101 can adopt at least two unidirectivity microphones; This unidirectivity microphone has the environmental sound signal of optionally gathering certain orientation, can be good at realizing the location of environmental sound signal.
S102 according to preset identifying information, discerns said environmental sound signal;
In concrete the realization, the environmental sound signal that said S102 is used for is to external world discerned, and judges the particular sound signal that whether said environmental sound signal comprises and preset identifying information is complementary (same or similar), and its particular sound signal is identified.Such as: said S101 collects the mixed environment voice signal; Sound such as honk have wherein been comprised; Suppose to have preset honk as identifying information; Said S102 identifies the identical or similar particular sound signal of identifying information (honk) with preset that comprises in the mixed environment voice signal according to this preset identifying information; For another example: said S101 collects the mixed environment voice signal; The sound such as ring tone that wherein comprised machine master name; Suppose to have preset machine master name as identifying information with textual form, said S102 converts the call sound of the machine master name that comprises in the mixed environment voice signal into text message, compares with preset machine master name text information; If the two is identical or similar, then said S102 identifies this particular sound signal (ring tone of machine master name); For another example: said S101 collects the mixed environment voice signal; Wherein comprised the contact person's sound that carries out voice call with the machine master; The sound of having supposed to preset this contact person is as identifying information; Said S102 identifies the identical or similar particular sound signal of identifying information (contact person's sound) with preset that comprises in the mixed environment voice signal according to this preset identifying information;
S103 when comprising the particular sound signal that is complementary with said preset identifying information in the said environmental sound signal, judges whether the loudness of said particular sound signal reaches preset threshold values;
In concrete the realization, said threshold values is a threshold value of sound intensity, and it can be set according to actual needs.Such as: for the acoustic information of danger signals such as honk, bicycle the tinkle of bells, alarm song, can take the highest loudness threshold values, hear that with the user situation that this voice signal can in time avert danger sets; For another example: for the voice signal of friend's beeper master name, can take minimum loudness threshold values, with the sound that picks up of sensitivity, the inaudible phenomenon of avoiding greeting.Carry out the flexible setting of threshold values here according to actual needs; Both can avoid too sensitive collection ambient signal and disturb the operate as normal of earphone; Guarantee the operate as normal of earphone, again can be sensitive carry out picking up of sound, well extraneous effective environmental voice signal is notified to the user.
Particularly, when said S102 identifies the particular sound signal that is complementary with preset identifying information from environmental sound signal, such as: honk, said S103 judge promptly whether the loudness of this honk that identifies reaches preset threshold values.
S104, when the loudness of said particular sound signal reaches said preset threshold values, the said particular sound signal of control output.
In concrete the realization, when said particular sound signal reached said preset threshold values, the said particular sound signal of said S104 control output was to notify the user.Particularly, the mode of said S104 control particular sound signal output can have multiple, includes but not limited to:
One of which: the earphone of control portable terminal is exported said particular sound signal; Particularly, can suspend the content of former earphone output, and only play this environmental sound signal; Maybe can content and this particular sound signal of the output of former earphone be carried out audio mixing, export the voice signal behind the audio mixing then;
Its two: control said mobile terminal vibration, to export said particular sound signal; This way of output belongs to a kind of aid prompting, is careful external environment by mobile terminal vibration with the prompting user;
Its three: control the light flash of said portable terminal, to export said particular sound signal; This way of output also belongs to a kind of aid prompting, by the light flash of portable terminal, such as: LED (Light EmittingDisplay, light emitting diode) flicker, or the keyboard light flicker of portable terminal etc., be careful external environment with the prompting user;
Its four: control the said particular sound signal of said mobile terminal displays; The prerequisite of this way of output does; This mobile terminal stores the relevant information of this particular sound signal; Such as: friend's beeper master name; Its prerequisite is to have stored this information of friends in the portable terminal, comprises acoustic information, name, contact method etc., the corresponding information of the above-mentioned storage of the said mobile terminal displays of said S104 may command.
The present invention is through presetting identifying information and threshold values at portable terminal; And gather environmental sound signal in real time; When certain particular sound signal in the environmental sound signal and preset identifying information are complementary and reach corresponding loudness threshold values; The output of control particular sound signal has promoted user's sensing capability of ambient sound to external world when earphone to notify the machine master; In addition; Through preset various identifying informations, such as: various dangerous information such as honk, eliminated the potential safety hazard the when user uses earphone; For another example: various address information such as preset machine master's name, nickname; When friend greets the machine master, can notify the machine master, promoted user experience; Simultaneously, can both can guarantee the operate as normal of earphone, can well extraneous effective environmental voice signal have been notified to the user again, promote user experience through the loudness threshold values of the preset various identifying informations of actual conditions.
See also Fig. 4, be the process flow diagram of second embodiment of the sound identification method based on portable terminal of the present invention; As shown in Figure 4, said method comprises:
S201 preestablishes the loudness threshold values of multiple identifying information and each identifying information, and said identifying information comprises non-speech recognition information and/or voice recognition information;
In concrete the realization; Said S201 can be provided with an identification storehouse in advance; This identification library storage various predefined identifying information and the pairing loudness threshold values of various identifying information that are used for sound recognition; Wherein, the non-speech recognition information in this identifying information includes but not limited to: honk, bicycle the tinkle of bells and alarm song; Text message in this identifying information includes but not limited to: said voice recognition information includes but not limited to: any one or more in machine master name, nickname or the another name of the dialogue people's who is preserved when the contact person's who is preserved during the voice call of said portable terminal speech information, daily dialogue speech information and the said portable terminal preserved with text or speech form.Particularly, the form that said S201 can show provides an identification storehouse, like above-mentioned table one, does not give unnecessary details at this.
Whether S202 detects earphone and inserts, if testing result is for being execution S203; Otherwise, finish;
In concrete the realization, when said earphone was wired earphone, said S202 can adopt hardware, such as chip or CPU etc., utilized the plug state of hardware detection wired earphone; When said earphone is wireless headset (bluetooth earphone), said S202 can adopt software to detect the plug state of said wireless headset, when detecting said earphone and insert, triggers and carries out S203.
S203 gathers environmental sound signal;
S204 judges whether said environmental sound signal comprises the particular sound signal that is complementary with preset non-speech recognition information, if judged result is for being execution S206; Otherwise, carry out S205;
S205 judges whether said environmental voice information comprises the particular sound signal that is complementary with preset voice recognition information, if judged result is carried out S206 for being, otherwise, finish;
S206 judges whether the loudness of said particular sound signal reaches preset threshold values, if judged result is for being execution S207; Otherwise, finish;
S207, the said particular sound signal of control output.
In concrete the realization, above-mentioned S205 can also be positioned at before the S204, also can take place simultaneously with S204; S201 also can be positioned at after the S202, but need guarantee to carry out taking place before the environmental sound signal identification at S204 (S205).
The present invention utilizes speech recognition technology, eliminates the user when using the earphone of portable terminal, because the induction of ambient sound weakens the potential safety hazard that is caused to external world, promotes user experience.
Description through above-mentioned each embodiment; The present invention is through presetting identifying information and threshold values at portable terminal; And gather environmental sound signal in real time; When certain particular sound signal in the environmental sound signal and preset identifying information were complementary and reach corresponding loudness threshold values, the output of control particular sound signal to be to notify the machine master, promoted user's sensing capability of ambient sound to external world when earphone; In addition; Through preset various identifying informations, such as: various dangerous information such as honk, eliminated the potential safety hazard the when user uses earphone; For another example: various address information such as preset machine master's name, nickname; When friend greets the machine master, can notify the machine master, promoted user experience; Simultaneously, can both can guarantee the operate as normal of earphone, can well extraneous effective environmental voice signal have been notified to the user again, promote user experience through the loudness threshold values of the preset various identifying informations of actual conditions.
Above disclosedly be merely preferred embodiment of the present invention; Certainly can not limit the present invention's interest field with this; One of ordinary skill in the art will appreciate that all or part of flow process that realizes the foregoing description; And, still belong to the scope that invention is contained according to the equivalent variations that claim of the present invention is done.
Claims (10)
1. sound identification method based on portable terminal, said portable terminal comprises earphone, it is characterized in that, said method comprises:
Gather environmental sound signal;
According to preset identifying information, said environmental sound signal is discerned;
When comprising the particular sound signal that is complementary with said preset identifying information in the said environmental sound signal, whether the loudness of judging said particular sound signal reaches preset and the corresponding loudness threshold values of said preset identifying information;
When the loudness of said particular sound signal reaches the corresponding loudness threshold values of said preset and said preset identifying information, the said particular sound signal of control output.
2. the method for claim 1 is characterized in that, before the said collection environmental sound signal, also comprises:
When said earphone is in the insertion state, trigger the collection of said environmental sound signal.
3. method as claimed in claim 2 is characterized in that, and is said when said earphone is in the insertion state, triggers before the collection of said environmental sound signal, also comprises:
Preestablish the loudness threshold values of multiple identifying information and each identifying information, said identifying information comprises non-speech recognition information and/or voice recognition information.
4. method as claimed in claim 3 is characterized in that,
Said non-speech recognition information comprises: any one or more in honk, bicycle the tinkle of bells and the alarm song;
Said voice recognition information comprises: any one or more in machine master name, nickname or the another name of the dialogue people's who is preserved when the contact person's who is preserved during the voice call of said portable terminal speech information, daily dialogue speech information and the said portable terminal preserved with text or speech form.
5. like each described method of claim 1-4, it is characterized in that said control is exported said particular sound signal and comprised:
Control said earphone and export said particular sound signal; Or,
Control said mobile terminal vibration, to export said particular sound signal; Or,
Control the light flash of said portable terminal, to export said particular sound signal; Or,
Control the said particular sound signal of said mobile terminal displays.
6. a portable terminal comprises earphone, it is characterized in that, also comprises:
Acquisition module is used to gather environmental sound signal;
Identification module is used for according to preset identifying information the said environmental sound signal that said acquisition module collects being discerned;
Judge module; Be used for when said identification module identifies said environmental sound signal and comprises the particular sound signal that is complementary with said preset identifying information, whether the loudness of judging said particular sound signal reaches preset and the corresponding loudness threshold values of said preset identifying information;
Control module is used for when said judge module judges that the loudness of said particular sound signal reaches the corresponding loudness threshold values of said preset and said preset identifying information the said particular sound signal of control output.
7. portable terminal as claimed in claim 6 is characterized in that, also comprises:
Trigger module is used to detect the insertion signal of said earphone, triggers the collection that said acquisition module carries out said environmental sound signal.
8. portable terminal as claimed in claim 7 is characterized in that, also comprises:
Presetting module is used to preestablish the loudness threshold values of multiple identifying information and each identifying information, and said identifying information comprises non-speech recognition information and/or voice recognition information.
9. portable terminal as claimed in claim 8 is characterized in that, said identification module comprises:
The non-speech recognition unit is used for according to preset non-speech recognition information the said environmental sound signal that said acquisition module collects being discerned;
Voice recognition unit is used for according to preset voice recognition information the said environmental sound signal that said acquisition module collects being discerned.
10. like each described portable terminal of claim 6-9, it is characterized in that:
Said acquisition module is located in the said earphone;
Said acquisition module comprises at least one microphone.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101629008A CN101840700B (en) | 2010-04-28 | 2010-04-28 | Voice recognition method based on mobile terminal and mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101629008A CN101840700B (en) | 2010-04-28 | 2010-04-28 | Voice recognition method based on mobile terminal and mobile terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101840700A CN101840700A (en) | 2010-09-22 |
| CN101840700B true CN101840700B (en) | 2012-05-23 |
Family
ID=42744038
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010101629008A Active CN101840700B (en) | 2010-04-28 | 2010-04-28 | Voice recognition method based on mobile terminal and mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101840700B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107147795A (en) * | 2017-05-24 | 2017-09-08 | 上海与德科技有限公司 | A kind of reminding method and mobile terminal |
Families Citing this family (52)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101790000B (en) * | 2010-02-20 | 2014-08-13 | 华为终端有限公司 | Environmental sound reminding method and mobile terminal |
| CN103178878B (en) * | 2011-12-21 | 2015-07-22 | 国际商业机器公司 | Method and system for connection of wireless devices |
| DE102012202232A1 (en) * | 2012-02-14 | 2013-08-14 | Lufthansa Systems Ag | Method for making announcements in a means of transport |
| CN102624980A (en) * | 2012-03-06 | 2012-08-01 | 惠州Tcl移动通信有限公司 | Method for detecting abrupt environment and prompting based on earphone of mobile phone and mobile phone |
| CN102710819B (en) * | 2012-03-22 | 2017-07-21 | 博立码杰通讯(深圳)有限公司 | A kind of phone |
| CN103456301B (en) * | 2012-05-28 | 2019-02-12 | 中兴通讯股份有限公司 | A kind of scene recognition method and device and mobile terminal based on ambient sound |
| CN102780653B (en) * | 2012-08-09 | 2016-03-09 | 上海量明科技发展有限公司 | Quick method, client and the system communicated in instant messaging |
| US9736587B2 (en) * | 2012-08-31 | 2017-08-15 | Qualcomm Incorporated | Smart tool for headphones |
| CN103841248A (en) * | 2012-11-20 | 2014-06-04 | 联想(北京)有限公司 | Method and electronic equipment for information processing |
| US9959865B2 (en) | 2012-11-13 | 2018-05-01 | Beijing Lenovo Software Ltd. | Information processing method with voice recognition |
| CN103024177A (en) * | 2012-12-13 | 2013-04-03 | 广东欧珀移动通信有限公司 | Mobile terminal driving mode operation method and mobile terminal |
| CN103905956B (en) * | 2012-12-28 | 2019-06-25 | 联想(北京)有限公司 | Audio control method, electronic equipment and audio output apparatus |
| US9691382B2 (en) | 2013-03-01 | 2017-06-27 | Mediatek Inc. | Voice control device and method for deciding response of voice control according to recognized speech command and detection output derived from processing sensor data |
| CN103414982B (en) * | 2013-07-31 | 2018-02-13 | 小米科技有限责任公司 | A kind of method and apparatus that sound is provided |
| CN103475967B (en) * | 2013-08-19 | 2017-01-25 | 宇龙计算机通信科技(深圳)有限公司 | Headphone sound mixing system and method |
| CN103594088A (en) * | 2013-11-11 | 2014-02-19 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| WO2015127194A1 (en) * | 2014-02-20 | 2015-08-27 | Harman International Industries, Inc. | Environment sensing intelligent apparatus |
| CN103825993B (en) * | 2014-03-11 | 2017-05-17 | 宇龙计算机通信科技(深圳)有限公司 | Method and device for treating environment sound during conversation |
| CN104978956A (en) * | 2014-04-14 | 2015-10-14 | 美的集团股份有限公司 | Voice control method and system |
| CN105262879A (en) * | 2014-07-16 | 2016-01-20 | 宇龙计算机通信科技(深圳)有限公司 | Volume gain control method and device and terminal |
| CN106211009A (en) * | 2014-09-23 | 2016-12-07 | 博世汽车部件(苏州)有限公司 | Distinguish sound auxiliary device |
| CN105759948A (en) * | 2014-12-18 | 2016-07-13 | 联想(北京)有限公司 | Information processing method and electronic device |
| CN104869505B (en) * | 2015-03-23 | 2018-05-29 | 广东欧珀移动通信有限公司 | A kind of method for controlling volume, playback equipment, mobile terminal and system |
| CN105100356B (en) * | 2015-07-07 | 2018-04-06 | 上海斐讯数据通信技术有限公司 | The method and system that a kind of volume automatically adjusts |
| CN106550294A (en) * | 2015-09-18 | 2017-03-29 | 丰唐物联技术（深圳）有限公司 | Monitor method and device based on earphone |
| CN105205955B (en) * | 2015-09-25 | 2018-07-31 | 小米科技有限责任公司 | A kind of method and apparatus sending out standby signal |
| CN105469794B (en) * | 2015-12-08 | 2019-09-24 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN105554664A (en) * | 2015-12-22 | 2016-05-04 | 王晓晖 | Headset based sound processing method and apparatus, and headset |
| CN105681950B (en) * | 2016-01-15 | 2019-01-22 | 宇龙计算机通信科技(深圳)有限公司 | Reminding method, suggestion device, earphone and terminal |
| CN107197431A (en) * | 2016-03-15 | 2017-09-22 | 西安中兴新软件有限责任公司 | A kind of multi-medium play method and device |
| CN106412225A (en) * | 2016-05-20 | 2017-02-15 | 惠州Tcl移动通信有限公司 | Mobile terminal and safety instruction method |
| CN106057198B (en) * | 2016-05-27 | 2019-08-16 | 北京云知声信息技术有限公司 | A kind of method and apparatus controlling intelligent transportation tool |
| CN106254641A (en) * | 2016-07-29 | 2016-12-21 | 宇龙计算机通信科技(深圳)有限公司 | The earphone monitoring method and system of smart machine |
| CN106375554B (en) * | 2016-08-25 | 2020-02-11 | 维沃移动通信有限公司 | Audio output control method and mobile terminal |
| CN108605073B (en) | 2016-09-08 | 2021-01-05 | 华为技术有限公司 | Sound signal processing method, terminal and earphone |
| CN106445459A (en) * | 2016-10-12 | 2017-02-22 | 深圳市金立通信设备有限公司 | Method for controlling audio playing of earphones and terminal |
| CN106648526A (en) * | 2016-10-20 | 2017-05-10 | 北京小米移动软件有限公司 | Sound wave transmission method and apparatus |
| WO2018227560A1 (en) * | 2017-06-16 | 2018-12-20 | 深圳市柔宇科技有限公司 | Method and system for controlling earphone |
| CN107333199A (en) * | 2017-07-21 | 2017-11-07 | 京东方科技集团股份有限公司 | Earphone control device, earphone and headset control method |
| CN109671444B (en) * | 2017-10-16 | 2020-08-14 | 腾讯科技（深圳）有限公司 | Voice processing method and device |
| CN108551604B (en) * | 2018-04-26 | 2021-05-07 | 海尔优家智能科技（北京）有限公司 | Noise reduction method, noise reduction device and noise reduction earphone |
| CN108833675A (en) * | 2018-05-18 | 2018-11-16 | 出门问问信息科技有限公司 | The reminding method and device of extraneous voice messaging |
| CN112150778A (en) * | 2019-06-29 | 2020-12-29 | 华为技术有限公司 | Environmental sound processing method and related device |
| CN110619890A (en) * | 2019-08-23 | 2019-12-27 | 苏宁智能终端有限公司 | Method and system for recognizing external sound under earphone wearing state |
| CN111050244A (en) * | 2019-12-11 | 2020-04-21 | 佳禾智能科技股份有限公司 | Method for monitoring ambient sound of earphone, electronic device and computer readable storage medium |
| CN111385701A (en) * | 2020-04-03 | 2020-07-07 | 西安极蜂天下信息科技有限公司 | Sound playing control method and device of earphone |
| US11620895B2 (en) | 2020-08-05 | 2023-04-04 | Allstate Insurance Company | Systems and methods for disturbance detection and identification based on disturbance analysis |
| CN112102829A (en) * | 2020-09-04 | 2020-12-18 | 刘耀 | Player control system and method based on voice recognition |
| CN112954105A (en) * | 2021-02-18 | 2021-06-11 | 立讯智造(浙江)有限公司 | Wireless earphone and sound mixing method thereof |
| CN113194383A (en) * | 2021-04-29 | 2021-07-30 | 歌尔科技有限公司 | Sound playing method and device, electronic equipment and readable storage medium |
| CN113793625A (en) * | 2021-08-04 | 2021-12-14 | 维沃移动通信有限公司 | Audio playing method and device |
| CN113593610A (en) * | 2021-08-11 | 2021-11-02 | 深圳市威视达康科技有限公司 | Smoke alarm sound identification method and system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1168912A (en) * | 1997-08-18 | 1999-03-09 | N T T Hokkaido Ido Tsushinmo Kk | Interface device |
| CN101110217B (en) * | 2007-07-25 | 2010-10-13 | 北京中星微电子有限公司 | Automatic gain control method for audio signal and apparatus thereof |
| CN101197889A (en) * | 2007-12-03 | 2008-06-11 | 中兴通讯股份有限公司 | Method and mobile terminal for voice-control alarm through mobile terminal |
| CN101453535A (en) * | 2007-12-07 | 2009-06-10 | 希姆通信息技术（上海）有限公司 | Mobile phone alarming method |
| JP2009300915A (en) * | 2008-06-17 | 2009-12-24 | Fujitsu Ltd | Mobile terminal with music playback function |
-
2010
- 2010-04-28 CN CN2010101629008A patent/CN101840700B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 赵鹤鸣.基于听觉模型的语音识别研究.《数据采集与处理》.1992,第07卷(第02期),95-99. * |
| 魏艳等.噪声条件下的语音特征PLP参数的提取.《太原理工大学学报》.2009,第40卷(第03期),222-224. * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107147795A (en) * | 2017-05-24 | 2017-09-08 | 上海与德科技有限公司 | A kind of reminding method and mobile terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101840700A (en) | 2010-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101840700B (en) | Voice recognition method based on mobile terminal and mobile terminal | |
| US11569789B2 (en) | Compensation for ambient sound signals to facilitate adjustment of an audio volume | |
| CN103945062B (en) | User terminal volume adjusting method, device and terminal | |
| CN103825993B (en) | Method and device for treating environment sound during conversation | |
| JP6031761B2 (en) | Speech analysis apparatus and speech analysis system | |
| US9818423B2 (en) | Method of improving sound quality and headset thereof | |
| WO2018095035A1 (en) | Earphone and speech recognition method therefor | |
| CN101227759A (en) | Earphone device with automatic volume control function | |
| CN103796125A (en) | Earphone playing-based sound adjustment method | |
| CN106210323A (en) | A kind of speech playing method and terminal unit | |
| CN107863110A (en) | Safety prompt function method, intelligent earphone and storage medium based on intelligent earphone | |
| CN108540660B (en) | Voice signal processing method and device, readable storage medium and terminal | |
| CN102333157A (en) | Mobile terminal and conversation voice recording method and device used for mobile terminal | |
| CN113194383A (en) | Sound playing method and device, electronic equipment and readable storage medium | |
| CN107613113A (en) | A kind of headset mode control method, device and computer-readable recording medium | |
| CN102752454B (en) | Mobile phone warning method based on voice recognition | |
| CN106293601A (en) | A kind of audio frequency playing method and device | |
| CN111491236A (en) | Active noise reduction earphone, awakening method and device thereof and readable storage medium | |
| CN111081275B (en) | Terminal processing method and device based on sound analysis, storage medium and terminal | |
| CN106162446A (en) | Audio frequency playing method, device and earphone | |
| CN105812585A (en) | Method for switching conversation modes and mobile terminal | |
| CN103942507A (en) | Information processing method and electronic device | |
| CN109039355B (en) | Voice prompt method and related product | |
| CN103095916A (en) | Incidence prompt method and user terminal | |
| CN114360546A (en) | Electronic equipment and awakening method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |