CN109147820B - Vehicle-mounted sound control method and device, electronic equipment and storage medium - Google Patents
Vehicle-mounted sound control method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109147820B CN109147820B CN201811000936.9A CN201811000936A CN109147820B CN 109147820 B CN109147820 B CN 109147820B CN 201811000936 A CN201811000936 A CN 201811000936A CN 109147820 B CN109147820 B CN 109147820B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- playing
- voice
- sound
- content
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000005236 sound signal Effects 0.000 claims abstract description 57
- 230000001276 controlling effect Effects 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 9
- 230000001105 regulatory effect Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000003750 conditioning effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 229910001385 heavy metal Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/037—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for occupant comfort, e.g. for automatic adjustment of appliances according to personal settings, e.g. seats, mirrors, steering wheel
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Fittings On The Vehicle Exterior For Carrying Loads, And Devices For Holding Or Mounting Articles (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The application discloses a vehicle-mounted sound control method, a device, electronic equipment and a computer-readable storage medium, wherein the method comprises the following steps: when the vehicle-mounted sound box executes audio playing, collecting sound in a vehicle to obtain a sound signal; according to the audio played by the vehicle-mounted sound, eliminating a part corresponding to the audio in the sound signal to obtain a voice signal; recognizing semantic content of the voice signal, and determining a voice scene mapped by the semantic content; and adjusting the playing strategy of the vehicle-mounted sound according to the voice scene. The method and the device realize the automatic adjustment of the playing strategy of the vehicle-mounted sound according to the content spoken by the user in the vehicle, such as the adjustment of the playing content and the playing volume, and solve the problem that the volume adjustment and the playing content switching of the vehicle-mounted sound in the prior art are completely dependent on manual operation.
Description
Technical Field
The present disclosure relates to the field of vehicle control technologies, and in particular, to a method and an apparatus for controlling a car audio, an electronic device, and a computer-readable storage medium.
Background
Along with the continuous improvement of the living standard of people, automobiles are more and more popularized, and driving scenes are more and more diversified. Under different driving scenes, the requirements of users on the playing content and the volume of the car audio are different.
For example, when conducting business negotiation in a car, it is generally not suitable for playing heavy metal rock music, nor suitable for large volume; when the telephone is answered in the car, the volume is not suitable for large volume.
At present, the volume adjustment and the play content switching of the vehicle-mounted sound box are completely carried out manually, and are complex.
Content of application
In order to solve the technical problem that the volume adjustment and the playing content switching of the vehicle-mounted sound in the related technology completely depend on manual operation, the application provides a vehicle-mounted sound control method and device, an electronic device and a computer readable storage medium.
A method of controlling a car stereo, the method comprising:
when the vehicle-mounted sound box executes audio playing, collecting sound in a vehicle to obtain a sound signal;
according to the audio played by the vehicle-mounted sound, eliminating a part corresponding to the audio in the sound signal to obtain a voice signal;
recognizing semantic content of the voice signal, and determining a voice scene mapped by the semantic content;
and adjusting the playing strategy of the vehicle-mounted sound according to the voice scene.
In an exemplary embodiment, after the adjusting the play strategy of the car stereo according to the voice scene, the method further includes:
detecting user regulation and control operation of the vehicle-mounted sound equipment;
and adjusting the playing strategy of the vehicle-mounted sound according to the user regulation and control operation.
In an exemplary embodiment, after the adjusting the play strategy of the car stereo according to the voice scene, the method further includes:
detecting a stop duration of the voice signal;
and when the stop time length reaches the designated time length, controlling and restoring the playing strategy of the vehicle-mounted sound equipment.
In an exemplary embodiment, the sound signals include a near-field sound signal and a far-field sound signal, and the eliminating, according to audio played by the car audio, a portion of the sound signals corresponding to the audio to obtain a speech signal includes:
subtracting the near-field sound signal and the far-field sound signal to obtain a signal difference;
and amplifying the signal difference to obtain the voice signal.
In an exemplary embodiment, the recognizing semantic content of the speech signal and determining the speech scene mapped by the semantic content includes:
carrying out voice recognition on the voice signal to obtain semantic content;
searching keywords contained in the semantic content according to a plurality of preset keywords;
and determining the voice scene corresponding to the semantic content through mapping the keywords to the voice scene.
In an exemplary embodiment, the recognizing semantic content of the speech signal and determining the speech scene mapped by the semantic content includes:
transmitting the voice signal to a voice recognition background, wherein the voice recognition background is used for recognizing semantic content of the voice signal and determining a voice scene according to the semantic content;
and receiving the voice scene determined by the voice recognition background.
In an exemplary embodiment, the adjusting the play strategy of the car stereo according to the voice scene includes:
and calling the playing configuration information mapped by the voice scene, and adjusting the playing strategy of the vehicle-mounted sound.
An in-vehicle audio control apparatus, the apparatus comprising:
the sound acquisition module is used for acquiring sound in the vehicle to obtain a sound signal when the vehicle-mounted sound box executes audio playing;
the voice extraction module is used for eliminating a part corresponding to the audio frequency in the sound signal according to the audio frequency played by the vehicle-mounted sound equipment to obtain a voice signal;
the semantic recognition module is used for recognizing the semantic content of the voice signal and determining a voice scene mapped by the semantic content;
and the regulation and control module is used for regulating the playing strategy of the vehicle-mounted sound equipment according to the voice scene.
In an exemplary embodiment, the apparatus further comprises:
the operation detection module is used for detecting user regulation and control operation of the vehicle-mounted sound equipment;
and the secondary regulation and control module is used for regulating the playing strategy of the vehicle-mounted sound according to the user regulation and control operation.
In an exemplary embodiment, the apparatus further comprises:
the timing module is used for detecting the stop duration of the voice signal;
and the restoring module is used for controlling and restoring the playing strategy of the vehicle-mounted sound when the stop duration reaches the specified duration.
In an exemplary embodiment, the speech extraction module includes:
the difference unit subtracts the near-field sound signal and the far-field sound signal to obtain a signal difference;
and the amplifying unit is used for amplifying the signal difference to obtain the voice signal.
In an exemplary embodiment, the semantic recognition module includes:
the recognition unit is used for carrying out voice recognition on the voice signal to obtain semantic content;
the searching unit is used for searching the keywords contained in the semantic content according to a plurality of preset keywords;
and the mapping unit is used for determining the voice scene corresponding to the semantic content through mapping the keywords to the voice scene.
In an exemplary embodiment, the semantic recognition module includes:
the sending unit is used for transmitting the voice signal to a voice recognition background, and the voice recognition background is used for recognizing the semantic content of the voice signal and determining a voice scene according to the semantic content;
and the receiving unit is used for receiving the voice scene determined by the voice recognition background.
In an exemplary embodiment, the conditioning module is configured to perform:
and calling the playing configuration information mapped by the voice scene, and adjusting the playing strategy of the vehicle-mounted sound.
An electronic device, the electronic device comprising:
a processor;
a memory having stored thereon computer readable instructions which, when executed by the processor, implement the method as previously described.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method as set forth above.
The technical scheme provided by the embodiment of the application can have the following beneficial effects:
when the vehicle-mounted sound equipment executes audio playing, the sound in the vehicle is collected, the voice signal is extracted from the sound, then the corresponding playing configuration information is called according to the semantic content of the voice signal, and the playing strategy of the vehicle-mounted sound equipment is adjusted, so that the playing strategy of the vehicle-mounted sound equipment is automatically adjusted according to the content spoken by a user in the vehicle, for example, the playing content and the playing volume are adjusted, and the problem that the volume adjustment and the playing content switching of the vehicle-mounted sound equipment in the prior art completely depend on manual operation is solved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
Fig. 1 is a flowchart illustrating a car audio control method according to an exemplary embodiment;
fig. 2 is a flowchart of a car audio control method according to the corresponding embodiment of fig. 1;
fig. 3 is a flowchart of a car audio control method according to the corresponding embodiment of fig. 1;
FIG. 4 is a flowchart illustrating details of step 130 according to the corresponding embodiment of FIG. 1;
FIG. 5 is a flowchart illustrating details of step 150 according to a corresponding embodiment of FIG. 1;
FIG. 6 is a flowchart illustrating details of step 150 according to the corresponding embodiment of FIG. 1;
FIG. 7 is a flow diagram illustrating a method for controlling a car audio according to one embodiment;
FIG. 8 is a schematic diagram illustrating a speech extraction algorithm in accordance with an exemplary embodiment;
fig. 9 is a block diagram illustrating a car-audio control apparatus according to an exemplary embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as described in the appended claims.
Nowadays, most automobiles are equipped with a multimedia system, and are equipped with a sound box and a display screen, so that users can listen to music and watch videos in the automobiles. However, at present, switching of the played content is completely dependent on manual operations of a user, such as adjusting volume through a touch screen, and switching the played content. Therefore, the following provides a car audio control method, which realizes intelligent switching of playing contents and intelligent adjustment of playing volume.
Fig. 1 is a flowchart illustrating a car audio control method according to an exemplary embodiment. As shown in fig. 1, the method includes the following steps.
And step 110, acquiring sound in the vehicle to obtain a sound signal when the vehicle-mounted sound box executes audio playing.
The multimedia system of the automobile is realized based on hardware equipment comprising a processor and a memory, and the vehicle-mounted sound box is controlled by the processor to play audio and convert the audio into sound waves.
When the car audio performs audio playback, a user may speak in the car, and in order to obtain what the user speaks, the sound in the car is collected by a sound collection device (e.g., a microphone), and the sound waves are converted into electrical signals to obtain sound signals.
And step 130, eliminating a part corresponding to the audio frequency in the sound signal according to the audio frequency played by the vehicle-mounted sound equipment to obtain a voice signal.
The in-vehicle sound includes sound generated by a car audio, sound generated by a user speaking, and some noise (e.g., rain sound outside the vehicle). Of the above sounds, the sounds having a large volume are generally generated by the car audio and the user speaking. In order to identify the content spoken by the user, a speech signal is obtained by eliminating a portion of the sound signal corresponding to the audio played by the car stereo.
In an exemplary embodiment, sound signal collection is performed by sound collection devices (e.g., microphones) installed at various locations in the vehicle. The speaking sound signals collected by the collecting equipment far away from the speaking user are weaker, the speaking sound signals collected by the equipment near the speaking user are stronger, and the strength of the sound signals collected at different positions in the car is very close. Therefore, by amplifying the difference between the sound signals collected by the devices that are far from and near the speaking user, a speech signal can be obtained.
In an exemplary embodiment, after obtaining the voice signal, the voice signal is identified by the processor to obtain semantic content, and keywords in the semantic content are searched to determine a voice scene according to the keywords.
In another exemplary embodiment, after the voice signal is obtained, the voice signal is transmitted to a voice recognition background through a wireless network, the background recognizes semantic content of the voice signal, searches for keywords in the semantic content, and determines a voice scene according to the keywords.
Keywords and corresponding speech scenes such as:
1. telephone call scenario
Searching keywords such as "feed" and "hello" from the semantic content can determine that the in-vehicle user is making a call, and the voice scene mapped by the semantic content is a phone call scene.
2. Business negotiation scenario
Searching the semantic content for the business-related keywords such as "price", "cost" and "goods", it can be determined that the user in the vehicle is conducting business negotiation, and the voice scene mapped by the semantic content is the business negotiation scene.
3. Travel playing scene
Travel play related contents such as tourist attractions and scheduling are searched from the semantic contents, the current travel play state of the user can be determined, and the voice scene mapped by the semantic contents is a travel play scene.
4. Lovers' conversation scene
The keywords related to the lovers ' conversation are searched from the semantic content, so that the situation that the in-car user is in the lovers ' conversation can be determined, and the voice scene mapped by the semantic content is the lovers ' conversation scene.
The voice scene is not limited to the above scene, nor is the keyword limited to the above keyword.
And step 170, adjusting the playing strategy of the car audio according to the voice scene.
In an exemplary embodiment, the playing configuration information mapped by the voice scene is called, and the playing strategy of the car audio is adjusted. The playing configuration information may include playing content information and playing volume information, and accordingly, the vehicle-mounted audio playing volume may be increased/decreased to the volume indicated by the playing volume information by calling the playing configuration information, and the vehicle-mounted audio playing content may be switched to the audio content indicated by the playing content information.
For example:
1. telephone call scenario
After the in-vehicle user is determined to be calling according to keywords such as 'feeding' and 'hello', the playing strategy of the car audio is automatically adjusted to be in a pause state.
2. Business negotiation scenario
It is determined that the in-vehicle user is conducting business negotiation according to keywords such as "price", "cost", and "goods", and also, the played content is automatically switched to light music, which may be switched to a light music playlist or to a light music single song.
3. Travel playing scene
After determining that the user is currently in the travel play state according to travel play related contents such as tourist attractions and schedules, the playing volume is automatically reduced to facilitate the user to talk, and the playing content is switched to road music.
4. Lovers' conversation scene
After determining that the user in the vehicle is talking to the lovers according to the keywords related to the lovers talking, the playing volume is automatically reduced so as to facilitate the user to talk and the playing content is switched to the lovers.
In an exemplary embodiment, before the play strategy of the car audio is automatically adjusted, the current play content and the play volume information are saved, so that the current play content and the play volume information can be restored to the play state before the automatic adjustment is executed according to the saved information.
Before step 170, the speech scenes are stored in association with the corresponding playback configuration information in the aforementioned memory (see description of step 110). After the voice recognition background (see the description of step 150) determines the voice scene according to the keyword, the processor (see the description of step 110) invokes the playing configuration information according to the voice scene to adjust the playing strategy of the car audio.
In an exemplary embodiment, after step 170, as shown in fig. 2, the above method further comprises the following steps.
And step 210, detecting user regulation and control operation of the car audio.
The user adjustment and control operation of the car audio is a user operation for triggering the processor to adjust the playing strategy, for example, a HMI (Human Machine Interface) provided for a user through the multimedia system triggers the processor to adjust the touch operation of the car audio volume.
And step 230, adjusting the playing strategy of the car audio according to the user regulation and control operation.
In an actual scene, the user may temporarily have other requirements for the playing content and the playing volume, and for this reason, in an exemplary embodiment, after the step 230, the playing content and the playing volume adjusted by the user are maintained until the voice scene changes.
In an exemplary embodiment, after step 170, as shown in fig. 3, the above method further comprises the following steps.
As mentioned above, the reason for adjusting the play strategy of the car audio is that the play strategy of the car audio is adapted to the speaking content of the user in the car by automatically adjusting the play content and the play volume when the voice signal is detected, so that the switching and adjustment of the play content and the play volume are more intelligent.
Thus, in an exemplary embodiment, when the speech signal stops (i.e., the in-vehicle user stops speaking) in the current speech scenario, a timer is started to determine how long the speech signal has stopped.
And step 330, controlling to restore the playing strategy of the vehicle-mounted sound when the stop duration reaches the specified duration.
If the stop duration of the voice signal reaches the specified duration, it indicates that the user does not speak within the specified duration, and at the moment, the playing strategy of the vehicle-mounted sound is automatically restored to the state before the voice signal is detected. For example, the volume is automatically restored to the size before the decrease, and for example, the playback content is automatically restored to the content before the switching.
The volume is reduced to enable the user to distinguish the speaking voice from the voice of the car stereo, the switching of the played content is to enable the played music to adapt to the speaking content of the car user, in an exemplary embodiment, only the played volume is restored during the restoration, and the played content is not restored until the voice scene changes.
Fig. 4 is a flowchart illustrating details of step 130 according to a corresponding embodiment of fig. 1. In an exemplary embodiment, the sound signals in step 110 include near-field sound signals and far-field sound signals, and accordingly, as shown in fig. 4, step 130 specifically includes:
and step 131, subtracting the near-field sound signal and the far-field sound signal to obtain a signal difference.
The near-field sound signals are collected by equipment close to the speaking user and contain stronger speaking sound signals, and the far-field sound signals are collected by equipment far away from the speaking user and contain weaker speaking sound signals. Since the signal strengths of the acoustic signals included in the near-field sound signal and the far-field sound signal are very close to each other, the difference between the signals obtained by subtracting the near-field sound signal and the far-field sound signal is almost completely a speech sound signal.
Step 133 amplifies the signal difference to obtain a speech signal.
Since the intensity of the speech sound signal is weaker than that of the acoustic signal, the obtained signal difference is amplified and enhanced to obtain a speech signal. Since the obtained signal difference is almost completely a speech sound signal, the speech signal is also basically a speech sound signal, and contains less acoustic signals and noise signals.
Fig. 5 is a flowchart illustrating details of step 150 according to a corresponding embodiment of fig. 1. As shown in FIG. 5, in an exemplary embodiment, step 150 includes:
and step 151, performing voice recognition on the voice signals to obtain semantic contents.
The processor calls the computer readable instructions stored in the memory for recognizing the voice signal, and executes the recognition of the voice signal to obtain the semantic content.
In an exemplary embodiment, a database is pre-established, and the database contains keywords that may appear in different scenarios, for example, most "feeding" and "hello" appear in a phone call scenario. And after obtaining the semantic content through the speech recognition background, searching keywords in the semantic content according to the keywords in the database.
Besides establishing the database, keywords in the database are also associated with the voice scene in advance, for example, "feed" and "hello" are associated with the phone call scene, and when "feed" and "hello" are found from the semantic content, the voice scene is determined to be the phone call scene. For another example, "price", "cost", and "goods" are associated with the business negotiation scenario, and when "price", "cost", and "goods" are found from the semantic content, the voice scenario is determined as the business negotiation scenario.
Part of the scenes can be determined according to a single keyword, for example, a wedding scene, and can be determined according to the keyword 'married me'. Some scenarios need to be determined according to several keywords, such as business negotiation scenarios, and whether the user in the car is conducting business negotiation cannot be determined only according to the "cost", and keywords such as "price", "goods" and "delivery date" need to be supplemented.
In an exemplary embodiment, step 150 includes:
In order to guarantee the speed of voice recognition, the voice signals are transmitted to a voice recognition background through wireless networks such as 3G, 4G and 5G, and semantic contents corresponding to the voice signals are obtained through recognition of the voice recognition background. The speech recognition back-end may be, for example, a third party platform for ciobi, science fiction.
After the semantic content is identified by the speech identification background, the speech scene corresponding to the semantic content is determined according to the keywords in the semantic content, and the speech scene is returned to the automobile.
The present application is described below with reference to a specific embodiment.
Fig. 7 is a flowchart illustrating a car audio control method according to an embodiment. As shown in fig. 7, the execution flow of the method is as follows:
s1: in the process that people in the vehicle talk and play music are carried out simultaneously, the sound in the vehicle is collected in real time.
S2: and filtering the sound of the played music through a voice extraction algorithm, and extracting the audio stream of the person conversation.
The principle of the voice extraction algorithm is as follows: the method comprises the steps of collecting environmental sounds through two microphones, and then carrying out differential calculation through a sound control engine (such as Sibichi and Korea fly) to filter music sounds to obtain an audio stream of person conversation.
FIG. 8 is a schematic diagram illustrating a speech extraction algorithm in accordance with an exemplary embodiment.
S3: and uploading the audio stream to a speech recognition background for semantic analysis, and analyzing a speech scene (such as a telephone call scene, a business negotiation scene and a trip play scene) which the audio stream conforms to.
After the audio stream of the human conversation is extracted, the audio stream is transmitted to a speech recognition background through a 4G network, and the background is built by a speech recognition product provider such as cibye and science news.
S4: automatically adjusting to preset music content and volume for the voice scene.
S5: if the on-board personnel manually modify the playing content or the volume, the modified setting is maintained unchanged.
S6: if the on-board person has not modified the playback content or volume, the process goes to step S1.
S7: if the on-board person stops talking, the previous volume is restored.
The following is described with reference to specific scenarios:
1. telephone call scenario
Judging that the person in the vehicle is calling through keywords such as 'feeding' and 'hello', and automatically pausing the music playing; extracting keywords such as "bye", "bailey", or detecting no audio stream for a certain period of time, resumes the music playing.
2. Business negotiation scenario
Through the combination of the relevant keywords of the business such as price, cost, goods and delivery, the current business negotiation state is judged, the volume is automatically reduced, and the played music is switched into light music; if no audio stream is detected for a period of time, the previous volume is restored.
3. Travel playing scene
Judging the current travel playing state by extracting the tourist attractions and the schedule keywords in the conversation content, automatically reducing the volume and switching the played music into road music; if no audio stream is detected for a period of time, the previous volume is restored.
The following are embodiments of the apparatus of the present application that may be used to perform the method embodiments of the present application described above. For details which are not disclosed in the embodiments of the apparatus of the present application, reference is made to the embodiments of the method of the present application.
Fig. 9 is a block diagram illustrating a car-audio control apparatus according to an exemplary embodiment. As shown in fig. 9, the apparatus includes:
the sound collection module 610 is configured to collect sound in the vehicle to obtain a sound signal when the vehicle audio performs audio playing.
And the voice extraction module 630 is configured to eliminate a portion corresponding to the audio frequency in the sound signal according to the audio frequency played by the vehicle-mounted sound, so as to obtain a voice signal.
And the semantic recognition module 650 is configured to recognize semantic content of the voice signal, and determine a voice scene mapped by the semantic content.
And the regulation and control module 670 is configured to regulate a playing strategy of the car audio according to the voice scene.
In an exemplary embodiment, the apparatus further comprises:
and the operation detection module is used for detecting the user regulation and control operation of the vehicle-mounted sound equipment.
And the secondary regulation and control module is used for regulating the playing strategy of the vehicle-mounted sound according to the user regulation and control operation.
In an exemplary embodiment, the apparatus further comprises:
and the timing module is used for detecting the stop duration of the voice signal.
And the restoring module is used for controlling and restoring the playing strategy of the vehicle-mounted sound when the stop duration reaches the specified duration.
In an exemplary embodiment, the sound signals include a near-field sound signal and a far-field sound signal, and the voice extraction module 630 includes:
and the difference unit subtracts the near-field sound signal and the far-field sound signal to obtain a signal difference.
And the amplifying unit is used for amplifying the signal difference to obtain the voice signal.
In an exemplary embodiment, the semantic recognition module 650 includes:
and the recognition unit is used for carrying out voice recognition on the voice signal to obtain semantic content.
And the searching unit is used for searching the keywords contained in the semantic content according to a plurality of preset keywords.
And the mapping unit is used for determining the voice scene corresponding to the semantic content through mapping the keywords to the voice scene.
In an exemplary embodiment, the semantic recognition module 650 includes:
the sending unit is used for transmitting the voice signal to a voice recognition background, and the voice recognition background is used for recognizing the semantic content of the voice signal and determining a voice scene according to the semantic content;
and the receiving unit is used for receiving the voice scene determined by the voice recognition background.
In an exemplary embodiment, the conditioning module 670 is configured to perform:
and calling the playing configuration information mapped by the voice scene, and adjusting the playing strategy of the vehicle-mounted sound.
The present application further provides an electronic device, wherein the electronic device includes:
a processor;
a memory having stored thereon computer readable instructions which, when executed by the processor, implement the method as previously described.
The present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as set forth above.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (8)
1. A method for controlling a car audio, the method comprising:
when the vehicle-mounted sound box executes audio playing, collecting sound in a vehicle to obtain a sound signal;
according to the audio played by the vehicle-mounted sound, eliminating a part corresponding to the audio in the sound signal to obtain a voice signal;
recognizing semantic content of the voice signal, determining a target voice scene mapped by the semantic content, and storing the current playing content of the vehicle-mounted sound equipment;
calling target playing configuration information according to the target voice scene and the mapping relation between the voice scene and the playing configuration information, wherein the target playing configuration information comprises playing content information, and adjusting the playing strategy of the vehicle-mounted sound according to the target playing configuration information so as to switch the playing content of the vehicle-mounted sound to the playing content indicated by the playing content information;
and if the stop duration of the voice signal reaches the specified duration, controlling to restore the playing content of the vehicle-mounted sound to the stored current playing content.
2. The method according to claim 1, wherein after the adjusting the play strategy of the car stereo according to the voice scene, the method further comprises:
detecting user regulation and control operation of the vehicle-mounted sound equipment;
and adjusting the playing strategy of the vehicle-mounted sound according to the user regulation and control operation.
3. The method of claim 1, wherein the sound signals comprise near-field sound signals collected by a device closer to the speaking user and containing stronger spoken sounds and far-field sound signals collected by a device farther from the speaking user and containing weaker spoken sounds;
the eliminating a portion corresponding to the audio frequency in the sound signal according to the audio frequency played by the vehicle-mounted sound to obtain a voice signal includes:
subtracting the near-field sound signal and the far-field sound signal to obtain a signal difference;
and amplifying the signal difference to obtain the voice signal.
4. The method of claim 1, wherein the recognizing semantic content of the speech signal and determining the semantic content mapped speech scene comprises:
carrying out voice recognition on the voice signal to obtain semantic content;
searching keywords contained in the semantic content according to a plurality of preset keywords;
and determining the voice scene corresponding to the semantic content through mapping the keywords to the voice scene.
5. The method of claim 1, wherein the recognizing semantic content of the speech signal and determining a target speech scene to which the semantic content is mapped comprises:
transmitting the voice signal to a voice recognition background, wherein the voice recognition background is used for recognizing semantic content of the voice signal and determining a target voice scene according to the semantic content;
and receiving the target voice scene determined by the voice recognition background.
6. An in-vehicle audio control apparatus, characterized in that the apparatus comprises:
the sound acquisition module is used for acquiring sound in the vehicle to obtain a sound signal when the vehicle-mounted sound box executes audio playing;
the voice extraction module is used for eliminating a part corresponding to the audio frequency in the sound signal according to the audio frequency played by the vehicle-mounted sound equipment to obtain a voice signal;
the semantic recognition module is used for recognizing the semantic content of the voice signal, determining a target voice scene mapped by the semantic content and storing the current playing content of the vehicle-mounted sound;
the regulation and control module is used for calling target playing configuration information according to the target voice scene and the mapping relation between the voice scene and the playing configuration information, wherein the target playing configuration information comprises playing content information, and the playing strategy of the vehicle-mounted sound equipment is regulated according to the target playing configuration information so that the playing content of the vehicle-mounted sound equipment is switched to the playing content indicated by the playing content information;
the apparatus is further configured to: and if the stop duration of the voice signal reaches the specified duration, controlling to restore the playing content of the vehicle-mounted sound to the stored current playing content.
7. An electronic device, characterized in that the electronic device comprises:
a processor;
a memory having stored thereon computer readable instructions which, when executed by the processor, implement the method of any one of claims 1 to 5.
8. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811000936.9A CN109147820B (en) | 2018-08-30 | 2018-08-30 | Vehicle-mounted sound control method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811000936.9A CN109147820B (en) | 2018-08-30 | 2018-08-30 | Vehicle-mounted sound control method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109147820A CN109147820A (en) | 2019-01-04 |
| CN109147820B true CN109147820B (en) | 2021-09-10 |
Family
ID=64829240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811000936.9A Active CN109147820B (en) | 2018-08-30 | 2018-08-30 | Vehicle-mounted sound control method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109147820B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107484000A (en) * | 2017-09-29 | 2017-12-15 | 北京奇艺世纪科技有限公司 | A kind of volume adjusting method of terminal, device and voice remote controller |
| CN110704012B (en) * | 2019-09-29 | 2023-08-01 | 阿波罗智联(北京)科技有限公司 | Audio data processing method and device, electronic equipment and medium |
| CN111477206A (en) * | 2020-04-16 | 2020-07-31 | 北京百度网讯科技有限公司 | Noise reduction method and device for vehicle-mounted environment, electronic equipment and storage medium |
| CN113766285A (en) * | 2020-06-02 | 2021-12-07 | 云米互联科技(广东)有限公司 | Volume control method, television and storage medium |
| CN115243104A (en) * | 2021-11-30 | 2022-10-25 | 广州汽车集团股份有限公司 | Method and system for automatically adjusting vehicle-mounted multimedia volume |
| CN115604623B (en) * | 2022-10-25 | 2024-03-15 | 苏州井利电子股份有限公司 | Intelligent vehicle-mounted sound adjusting system and method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106671915A (en) * | 2016-12-06 | 2017-05-17 | 深圳市元征科技股份有限公司 | Automatic intra-vehicle environment adjustment method and device |
| CN107995360A (en) * | 2017-11-27 | 2018-05-04 | 广东欧珀移动通信有限公司 | Call handling method and Related product |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104954555B (en) * | 2015-05-18 | 2018-10-16 | 百度在线网络技术（北京）有限公司 | A kind of volume adjusting method 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 |
| CN105225662A (en) * | 2015-08-24 | 2016-01-06 | 深圳市冠旭电子有限公司 | Smart bluetooth earphone plays method and the smart bluetooth earphone of external voice automatically |
| CN108156550B (en) * | 2017-12-27 | 2020-03-31 | 上海传英信息技术有限公司 | Playing method and device of headset |
| CN108022591B (en) * | 2017-12-30 | 2021-03-16 | 北京百度网讯科技有限公司 | Processing method and device for voice recognition in-vehicle environment and electronic equipment |
-
2018
- 2018-08-30 CN CN201811000936.9A patent/CN109147820B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106671915A (en) * | 2016-12-06 | 2017-05-17 | 深圳市元征科技股份有限公司 | Automatic intra-vehicle environment adjustment method and device |
| CN107995360A (en) * | 2017-11-27 | 2018-05-04 | 广东欧珀移动通信有限公司 | Call handling method and Related product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109147820A (en) | 2019-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109147820B (en) | Vehicle-mounted sound control method and device, electronic equipment and storage medium | |
| CN107995360B (en) | Call processing method and related product | |
| KR101954550B1 (en) | Volume adjustment method, system and equipment, and computer storage medium | |
| CA2717992C (en) | Speech understanding method and system | |
| CN101459717B (en) | Wireless terminal and method for implementing multi-channel multiplexing | |
| CN110475170A (en) | Control method, device, mobile terminal and the storage medium of earphone broadcast state | |
| CN1391210A (en) | Method for training or adapting to phonetic recognizer | |
| CN112397065A (en) | Voice interaction method and device, computer readable storage medium and electronic equipment | |
| CN102739834B (en) | Voice call apparatus and vehicle mounted apparatus | |
| EP2362620A1 (en) | Method of editing a noise-database and computer device | |
| CN113840211A (en) | Method and device for automatically adjusting volume of Bluetooth headset and Bluetooth headset | |
| CN106231047A (en) | A kind of audio collection method based on intelligent terminal, system and intelligent terminal | |
| CN108597524B (en) | Automobile voice recognition prompting device and method | |
| CN105577943A (en) | Bus stop reporting prompting method and system and mobile terminal | |
| US20240096343A1 (en) | Voice quality enhancement method and related device | |
| CN106156036B (en) | Vehicle-mounted audio processing method and vehicle-mounted equipment | |
| CN113539260A (en) | Voice communication method and device based on vehicle | |
| CN111199751B (en) | Microphone shielding method and device and electronic equipment | |
| CN113779208A (en) | Method and device for man-machine conversation | |
| CN109830234A (en) | A kind of intelligent vehicle-carried information interaction device and exchange method | |
| KR20140067687A (en) | Car system for interactive voice recognition | |
| CN115482830A (en) | Speech enhancement method and related equipment | |
| KR102109186B1 (en) | Method ana apparatus for recommendation contents based on conversation of vehicle's occupant | |
| CN111464902A (en) | Information processing method, information processing device, earphone and storage medium | |
| EP4276818A1 (en) | Speech operation method for device, apparatus, and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |