CN109830249A - Data processing method, device and storage medium - Google Patents
Data processing method, device and storage medium Download PDFInfo
- Publication number
- CN109830249A CN109830249A CN201811632710.0A CN201811632710A CN109830249A CN 109830249 A CN109830249 A CN 109830249A CN 201811632710 A CN201811632710 A CN 201811632710A CN 109830249 A CN109830249 A CN 109830249A
- Authority
- CN
- China
- Prior art keywords
- buffer storage
- storage container
- data buffer
- data
- sound area
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B20/00—Signal processing not specific to the method of recording or reproducing; Circuits therefor
- G11B20/10—Digital recording or reproducing
- G11B20/10527—Audio or video recording; Data buffering arrangements
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B20/00—Signal processing not specific to the method of recording or reproducing; Circuits therefor
- G11B20/10—Digital recording or reproducing
- G11B20/10527—Audio or video recording; Data buffering arrangements
- G11B2020/1062—Data buffering arrangements, e.g. recording or playback buffers
- G11B2020/10629—Data buffering arrangements, e.g. recording or playback buffers the buffer having a specific structure
- G11B2020/10657—Cache memories for random data access, e.g. buffers wherein the data output is controlled by a priority parameter other than retention time
Abstract
The present invention provides a kind of data processing method, device and storage medium, this method is applied to electronic equipment, electronic equipment includes the audio input device that each sound area is arranged in, this method comprises: obtaining the voice data of the audio input device acquisition at least two sound areas；Judge in the corresponding data buffer storage container in each sound area with the presence or absence of available space；Calling first thread, successively there are the data buffer storage containers of available space, and corresponding voice data is written to each, and abandons the corresponding voice data of data buffer storage container that available space is not present.The technical issues of present invention is able to solve the write-in obstruction of the recording pipeline because of car-mounted terminal, and leading to the speech engine of car-mounted terminal can not work.
Description
Technical field
The present invention relates to technical field of intelligent equipment more particularly to a kind of data processing methods, device and storage medium.
Background technique
Car-mounted terminal can be interacted by voice and user, provided navigation for user, broadcasting music, made a phone call
Service.The microphone of existing car-mounted terminal is in alignment with main driving position to design, and can provide voice for the driver of vehicle
Service.This design method makes car-mounted terminal that can not provide service for the member of other on vehicle.It can be with currently, being proposed one kind
Meet the vehicle-mounted four sounds area scheme that vehicle crew uses, in the program, the space of vehicle interior is divided into four sounds all around
Area, a position on each sound area covering vehicle, car-mounted terminal are provided with independent microphone array in each sound area, can be with
Interactive voice is carried out with the user of the sound area corresponding position.
Since the space of vehicle interior is smaller, although can be to four position manufactures one by microphone array mould group algorithm
Fixed sound isolation, but the user of any position still understands some sound by it when voice wakes up car-mounted terminal
The microphone array in its sound area acquires, and causes the microphone array in multiple sound areas that can collect the voice number from identical sound source
According to.Therefore, in order to identify which sound area is waken up by user on earth, car-mounted terminal can call the line for executing write operation
The recording in the sound area is written by the way of serial process in the microphone array voice data collected in four areas Ge Yin by journey
In pipeline.Then, car-mounted terminal can be collected by the microphone array in each sound area by the corresponding recording pipeline in each sound area
Voice data, which synchronizes, passes to wake-up thread corresponding with each sound area in speech engine.In this way, car-mounted terminal can pass through language
Wake-up thread corresponding with each sound area in sound engine, it is synchronous to identify whether the corresponding sound area of the wake-up thread is waken up.
The cache size of the corresponding pipeline of recording in above-mentioned each sound area is limited, when voice data write-in is more than recording pipeline
When cache size, the write-in obstruction of the recording pipeline can be triggered.However, since car-mounted terminal is called for executing write operation
Thread, when the microphone array voice data collected in each sound area is written in the recording pipeline in the sound area, using
The mode of serial process.Therefore, if wherein write-in obstruction occurs in a certain recording pipeline, it will lead to car-mounted terminal and call for holding
When the thread of row write operation executes write operation, the recording pipeline of appearance write-in obstruction can not be skipped, to other sound areas
Data are written in pipeline of recording, and then cause the corresponding wake-up thread in all sound areas can not be from the corresponding recording pipeline in respective sound area
The voice data for reading caching, causes the speech engine of car-mounted terminal that can not work.
Summary of the invention
The present invention provides a kind of data processing method, device and storage medium, for solving the recording pipe because of car-mounted terminal
The technical issues of write-in in road is blocked, and leading to the speech engine of car-mounted terminal can not work.
The first aspect of the present invention provides a kind of data processing method, and the method is applied to electronic equipment, the electronics
Equipment includes the audio input device that each sound area is arranged in, which comprises
Obtain the voice data of the audio input device acquisition at least two sound areas；
Judge in the corresponding data buffer storage container in each sound area with the presence or absence of available space；
Call first thread that the voice in corresponding sound area is successively written to each data buffer storage container there are available space
Data, and abandon and the corresponding voice data of available space is not present.
Optionally, it whether there is available space, packet in the corresponding data buffer storage container in each sound area of judgement
It includes:
Judge the remaining space of the corresponding data buffer storage container in the sound area, if more than or equal to the audio in the sound area
The size of the voice data of input equipment acquisition；
If so, determining the corresponding data buffer storage container in the sound area, there are available spaces；
If not, it is determined that available space is not present in the corresponding data buffer storage container in the sound area.
Optionally, the voice data of the audio input device acquisition for obtaining at least two sound areas, comprising:
The interface of audio input device is called, obtains VoP, the VoP includes described at least two
The voice data of the audio input device acquisition in sound area；
The voice data of the audio input device acquisition in each sound area is isolated from the VoP.
Optionally, the method also includes:
If calling corresponding second thread of the first data buffer storage container, from the first data buffer storage container it is unread to
The voice data of caching, then by corresponding second thread suspension of the first data buffer storage container, first data buffer storage holds
Device is the uncached data buffer storage container for having voice data.
Optionally, the method also includes:
When the duration of corresponding second thread suspension of the first data buffer storage container is greater than preset duration, restore institute
State corresponding second thread of the first data buffer storage container.
The second aspect of the present invention provides a kind of data processing equipment, and described device is applied to electronic equipment, the electronics
Equipment includes the audio input device that each sound area is arranged in, and described device includes:
Module is obtained, the voice data that the audio input device for obtaining at least two sound areas acquires；
First processing module, for judging in the corresponding data buffer storage container in each sound area with the presence or absence of available sky
Between；
Writing module, for call first thread successively to it is each there are the data buffer storage container of available space write-in it is corresponding
Voice data, and abandon the corresponding voice data of data buffer storage container that available space is not present.
Optionally, the first processing module, specifically for judging the residue of the corresponding data buffer storage container in the sound area
Space, if more than or equal to the size of the voice data of the audio input device acquisition in the sound area；If so, described in determining
There are available spaces for the corresponding data buffer storage container in sound area；If not, it is determined that the corresponding data buffer storage container in the sound area is not deposited
In available space.
Optionally, the acquisition module obtains VoP specifically for the interface of calling audio input device, and
The voice data of the audio input device acquisition in each sound area is isolated from the VoP；The voice data
Packet includes the voice data that the audio input device at least two sound area acquires.
Optionally, described device, further includes:
Read module holds for calling corresponding second thread of the first data buffer storage container from first data buffer storage
The voice data of caching is read in device, the first data buffer storage container is the uncached data buffer storage container for having voice data；
Second processing module, for calling corresponding second thread of the first data buffer storage container in the read module, from
In the first data buffer storage container when the unread voice data to caching, by the first data buffer storage container corresponding the
Two thread suspensions.
Optionally, the Second processing module is also used to by corresponding second thread of the first data buffer storage container
When the duration of hang-up is greater than preset duration, restore corresponding second thread of the first data buffer storage container.
The third aspect of the present invention provides a kind of data processing equipment, comprising: at least one processor and memory；
The memory stores computer executed instructions；
At least one described processor executes the computer executed instructions of the memory storage, so that the data processing
Device executes above-mentioned data processing method.
The fourth aspect of the present invention provides a kind of computer readable storage medium, deposits on the computer readable storage medium
Computer executed instructions are contained, when the computer executed instructions are executed by processor, realize above-mentioned data processing method.
Data processing method, device and storage medium provided by the invention, electronic equipment can call first thread according to
Before the corresponding data buffer storage container in the area Ci Xianggeyin executes data write operation, first judge that the corresponding data buffer storage in each sound area holds
Device whether there is available space, and then only execute write operation to the data buffer storage container with available space.Pass through this side
Formula can cause to avoid electronic equipment because calling first thread to execute write operation to the data buffer storage container of no available space
There is the case where write-in obstruction, so as to avoid occurring the data buffer storage container of write-in obstruction because that can not skip, to other sounds
Data are written in the data buffer storage container in area, and cause the corresponding wake-up thread in all sound areas slow from the corresponding data in sound area
The voice data that container reads caching is deposited, the problem of causing the speech engine of car-mounted terminal can not work.In this way, in a certain number
When there is write-in obstruction according to caching container, electronic equipment still can call first thread that language is written to other data buffer storage containers
Sound data, so as to so that speech engine works normally.
Detailed description of the invention
Fig. 1 is the application scenarios schematic diagram of car-mounted terminal provided by the invention；
Fig. 2 shows the signals that a kind of voice data that the microphone array by each sound area acquires passes to speech engine
Figure；
Fig. 3 is a kind of flow diagram of data processing method provided by the invention；
Fig. 4 is a kind of structural schematic diagram of data processing equipment provided by the invention；
Fig. 5 is the structural schematic diagram of another data processing equipment provided by the invention；
Fig. 6 is the structural schematic diagram of another data processing equipment provided by the invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with the embodiment of the present invention, to this
Technical solution in inventive embodiments is clearly and completely described, it is clear that described embodiment is that a part of the invention is real
Example is applied, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creation
Property labour under the premise of every other embodiment obtained, shall fall within the protection scope of the present invention.
Fig. 1 is the application scenarios schematic diagram of car-mounted terminal provided by the invention.As shown in Figure 1, in order to meet vehicle crew
Car-mounted terminal can be used, be proposed a kind of vehicle-mounted four sounds area scheme at present.In the program, the space of vehicle interior is divided into four
The area Ge Yin, each sound area cover a position on vehicle, and each sound area is provided with independent microphone array, can acquire this
The voice signal of the user of sound area corresponding position.The microphone array can be set in any voice signal convenient for acquisition user
Position, such as at the top roof of the sound area corresponding position.
For example, sound area 1 covers vehicle main driving position, the microphone array in sound area 1 is for acquiring vehicle main driving position
User issue voice signal；Sound area 2 covers vehicle copilot position, and the microphone array in sound area 2 is for acquiring vehicle auxiliary
The voice signal that the user of steering position issues；Sound area 3 includes the position on the vehicle heel row left side, and the microphone array in sound area 3 is used
The voice signal that user in the position on acquisition vehicle player No.5 side issues；Sound area 4 includes the position on the vehicle heel row left side, sound area
4 microphone array is used to acquire the voice signal that the user of the position on vehicle player No.5 side issues.
It is appreciated that Fig. 1 illustrates only the position of the microphone array of car-mounted terminal, the present invention couple for the ease of example
The composition of car-mounted terminal, and, the position of car-mounted terminal in the car, and, the position of microphone array does not limit.
Since the space of vehicle interior is smaller, although can be to four position manufactures one by microphone array mould group algorithm
Fixed sound isolation, but the user of any position still understands some sound by it when voice wakes up car-mounted terminal
The microphone array in its sound area acquires, and causes the microphone array in multiple sound areas that can collect the voice number from identical sound source
According to.In order to ensure the recognition accuracy of speech engine, the speech engine of car-mounted terminal needs the synchronous microphone for identifying each sound area
Array voice data collected.
Fig. 2 shows the signals that a kind of voice data that the microphone array by each sound area acquires passes to speech engine
Figure.As shown in Fig. 2, it is illustrative, 4 recording pipelines are provided in car-mounted terminal, each recording pipeline is corresponding with an area Ge Yin,
Microphone array voice data collected for caching the sound area.
It is assumed that recording pipeline 1 is the corresponding recording pipeline in sound area 1, recording pipeline 2 is the corresponding recording pipeline in sound area 2, record
Sound tube road 3 is the corresponding recording pipeline in sound area 3, and recording pipeline 4 is the corresponding recording pipeline in sound area 4.When the microphone in each sound area
After array acquisition to the voice data of user, car-mounted terminal can call the thread for executing write operation, using serial process
Mode, successively by the microphone array in sound area 1 voice data collected write-in recording pipeline 1, by the microphone in sound area 2
It is recorded in array voice data write-in recording pipeline 2 collected, by the voice data write-in collected of the microphone array in sound area 3
It is written in recording pipeline 4 in sound tube road 3, by the microphone array in sound area 4 voice data collected.
Correspondingly, speech engine also includes 4 wake-up threads, the corresponding recording pipeline of each wake-up thread.Vehicle-mounted end
The thread for executing write operation is called at end, by the way of serial process, successively by the microphone array institute in four areas Ge Yin
After the voice data of acquisition is written in the recording pipeline in the sound area, each wake-up thread of the speech engine of car-mounted terminal can be synchronized
The voice data of caching is read from corresponding recording pipeline, and the voice data based on reading identifies the recording pipeline pair
Whether the sound area answered is waken up.To wake up the corresponding recording pipeline 1 of thread 1, the corresponding recording pipeline 2 of wake-up thread 2, wake up thread 3
For corresponding recording pipeline 3, the corresponding recording pipeline 4 of wake-up thread 4.Thread 1 is waken up for reading and identifying in recording pipeline 1
The voice data of caching, to judge to record, whether the corresponding sound area 1 of pipeline 1 is waken up.Thread 2 is waken up for reading and identifying record
The voice data cached in sound tube road 2, to judge to record, whether the corresponding sound area 2 of pipeline 2 is waken up.Thread 3 is waken up for reading
Take and identify the voice data cached in recording pipeline 3, whether the corresponding sound area 3 of pipeline 3 is waken up to judge to record.Wake up line
Journey 4 is used to read and identify the voice data cached in recording pipeline 4, and to judge to record, whether the corresponding sound area 4 of pipeline 4 is called out
It wakes up.
By way of the voice data that the microphone array in each sound area of above-mentioned transmitting acquires, car-mounted terminal can be made to pass through
Wake-up thread corresponding with each sound area in speech engine, it is synchronous to identify whether the corresponding sound area of the wake-up thread is waken up.
However, when transmitting voice data through the above way, since the caching of the corresponding recording pipeline in each sound area is big
It is small limited, when voice data write-in is more than the cache size of recording pipeline, the write-in obstruction of the recording pipeline can be triggered.So
And since car-mounted terminal calls the thread for executing write operation, by the microphone array voice collected in each sound area
When data are written in the recording pipeline in the sound area, using the mode of serial process.Therefore, if wherein a certain recording pipeline goes out
Now write-in obstruction can not be skipped when then will lead to car-mounted terminal calling for executing the thread execution write operation of write operation
The recording pipeline of appearance write-in obstruction, is written data to the recording pipeline in other sound areas, and then cause all sound areas corresponding
The voice data of caching can not be read from the corresponding recording pipeline in respective sound area by waking up thread, cause the voice of car-mounted terminal
Engine can not work.
Illustratively, by taking the caching of pipeline 2 of recording has been expired as an example, when car-mounted terminal calls the line for executing write operation
Journey when voice data successively is written to recording pipeline, is then being gone to the recording write-in of pipeline 2 by the way of serial process
When the microphone array in sound area 2 voice data collected, it can ceaselessly attempt that data are written to recording pipeline 2, can not execute
Subsequent operation can not read caching so as to cause the corresponding wake-up thread in all sound areas from the corresponding recording pipeline in respective sound area
Voice data, cause the speech engine of car-mounted terminal that can not work.
In view of the above problem, the present invention provides a kind of data processing methods, to solve the recording because of car-mounted terminal
The technical issues of write-in of pipeline is blocked, and leading to the speech engine of car-mounted terminal can not work.
It is appreciated that data processing method provided by the invention can be adapted for any to mention for the user in multiple sound areas
For the electronic equipment of voice service.For example, car-mounted terminal, smart home etc..Illustratively, when electronic equipment is car-mounted terminal
When, an above-mentioned described area Ge Yin can cover a position on vehicle.It is above-mentioned described when electronic equipment is smart home
An area Ge Yin can correspond to the region etc. in space where smart home.
Technical solution of the present invention is described in detail below with reference to specifically embodiment.These are specific real below
Applying example can be combined with each other, and the same or similar concept or process may be repeated no more in some embodiments.
Fig. 3 is a kind of flow diagram of data processing method provided by the invention.Executing subject of the invention can be
Data processing equipment can also be and be integrated with the electronic equipment of data processing equipment, following to be integrated with data processing equipment
For electronic equipment (referred to as: electronic equipment), data processing method provided by the invention is illustrated and is introduced.In this implementation
In example, electronic equipment includes the audio input device that each sound area is arranged in.Audio input device mentioned here can be to appoint
One equipment with audio collection function, for example, microphone array.
As shown in figure 3, this method may include:
The voice data that S101, the audio input device for obtaining at least two sound areas acquire.
Above-mentioned at least two described sound areas may include all sound areas, may also mean that part sound area, specifically can root
It is determined according to the acquisition situation of the audio input device in each sound area.
Optionally, after the audio input device at least two sound areas of electronic equipment collects voice data, electronics is set
The standby interface that can call audio input device, obtains VoP, the VoP may include this at least two
The voice data of the audio input device acquisition in sound area.Then, electronic equipment can isolate each sound from VoP
The voice data of the audio input device acquisition in area.
For example, the voice data in VoP carries the mark of audio input device, then electronic equipment can root
According to the mark (such as index number, id etc.) according to the audio input device in each sound area, isolated from VoP every
The voice data of the audio input device acquisition in the area Ge Yin.Alternatively, the voice data in VoP carries the mark in sound area
Know (such as index number, id etc.), then electronic equipment can be separated from VoP according to the mark according to each sound area
The voice data of the audio input device acquisition in each sound area out.Alternatively, the audio input device in the area VoP Zhong Geyin
Voice data collected puts in order fixation, then electronic equipment can be according to according to putting in order, from VoP point
Separate out the voice data of the audio input device acquisition in each sound area.
Optionally, after the audio input device at least two sound areas of electronic equipment collects voice data, electronics is set
The interface of the standby audio input device that can also call the area Zhong Geyin, at least two sounds area, obtains the audio input in each sound area
The voice data of equipment acquisition.
It is appreciated that the voice data of the audio input device acquisition in above-mentioned at least two described sound areas: can be and
From same user, it is also possible to the user from not unisonance area.It is defeated with the audio of the audio input device of sound area A and sound area B
For entering equipment, the voice number of the audio input device acquisition of the voice data and sound area B of the audio input device acquisition of sound area A
According to can be from same user, alternatively, the voice data that the audio input device of sound area A acquires is the use from sound area A
Family, the voice data that the audio input device of sound area B acquires are the users from sound area B.
S102, judge in the corresponding data buffer storage container in each sound area with the presence or absence of available space.
Wherein, above-mentioned described data buffer storage container can be any container with caching function, for example, aforementioned described
Recording pipeline.
In the present embodiment, above-mentioned electronic equipment call first thread by the audio input in accessed each sound area
When corresponding data buffer storage container is written in equipment voice data collected, it can be determined that the corresponding data buffer storage in each sound area holds
It whether there is available space in device.Since the speed of reading data is faster than the speed of data write-in, if data buffer storage container is not deposited
In available space, illustrate new data can be written to the data buffer storage container.If there are available spaces for data buffer storage container, say
New data are written in the bright no normal direction data buffer storage container.
Optionally, electronic equipment can judge the corresponding data buffer storage in each sound area according to preset voice data size
Container whether there is available space.If the remaining space of the corresponding data buffer storage container in a certain sound area can accommodate preset voice
Size of data, it is determined that there are available spaces for the corresponding data buffer storage container in the sound area.If the corresponding data buffer storage in a certain sound area
The remaining space of container can not accommodate the space of preset voice data size, it is determined that the corresponding data buffer storage container in the sound area
There is no available spaces.Wherein, above-mentioned described preset voice data size specifically can be defeated according to the audio in all sound areas
Enter equipment can the size of collected voice data determine.For example, the preset voice data size can be all sound areas
Audio input device institute can the corresponding size of collected maximum voice data.
Optionally, the size for the voice data that electronic equipment can be acquired according to the audio input device in each sound area, judgement
The corresponding data buffer storage container in each sound area whether there is available space.For example, electronic equipment may determine that each sound area is corresponding
Data buffer storage container remaining space whether be greater than or equal to the sound area audio input device acquisition voice data it is big
It is small.What if the audio input device that the remaining space of the corresponding data buffer storage container in a certain sound area is greater than or equal to the sound area acquired
The size of voice data, it is determined that there are available spaces for the corresponding data buffer storage container in the sound area.If the corresponding number in a certain sound area
According to the size for the voice data that the audio input device that the remaining space of caching container is less than the sound area acquires, it is determined that the sound area
Available space is not present in corresponding data buffer storage container.
For there are the data buffer storage container of available space, electronic equipment can execute S103, for there is no available skies
Between data buffer storage container, electronic equipment can execute S104.
S103, calling first thread, successively there are the data buffer storage containers of available space, and corresponding voice number is written to each
According to.
S104, the corresponding voice data of data buffer storage container that available space is not present is abandoned.
Above-mentioned first thread can have the thread for executing write operation function to be any.
Specifically, above-mentioned electronic equipment whether there is available space in judging the corresponding data buffer storage container in each sound area
Afterwards, first thread can be called using serial manner, successively to each there are the data buffer storage container of available space, write-in should
The voice data of the audio data input equipment acquisition in the corresponding sound area of data buffer storage container.And the data for space is not present
Caching container, above-mentioned electronic equipment can abandon the data for preparing to be written in these data buffer storage containers, not recall First Line
Journey executes write operation to these data buffer storage containers.
It in this way, can be to avoid electronic equipment because calling data buffer storage container of the first thread to no available space
Write operation is executed, leads to the case where write-in obstruction occur, so as to avoid occurring the data of write-in obstruction because that can not skip
Data are written to the data buffer storage container in other sound areas in caching container, and cause the corresponding wake-up thread in all sound areas can not be from
The corresponding data buffer storage container in the sound area reads the voice data of caching, causes the speech engine of car-mounted terminal that can not work
Problem.In this way, a certain data buffer storage container occur write-in obstruction when, electronic equipment still can call first thread to other
Voice data is written in data buffer storage container, so as to so that speech engine works normally.
With continued reference to Fig. 2, by taking vehicle-mounted four sounds area scheme shown in Fig. 2 as an example, it is assumed that for the recording caching of pipeline 2 has been expired,
Then car-mounted terminal through this embodiment shown in method, can be that the recording pipeline be written to the recording pipeline in each sound area be corresponding
Sound area microphone array voice data collected when, can first judge whether the caching of the recording pipeline has expired, if so,
The data that the recording pipeline is written then are abandoned, write-in no longer is executed to the recording pipeline.
In this example, then car-mounted terminal through this embodiment shown in method, by judgement recording pipeline 2 whether there is
Available space when identifying the caching of recording pipeline 2 has expired, then directly abandons the data that the recording pipeline 2 is written, no longer right
The recording pipeline 2 executes write operation.Recording pipeline 2 is skipped, Xiang Luyin pipeline 3 executes write operation.In this way,
When the thread for executing write operation can be called to execute write operation to avoid car-mounted terminal, be written because this can not be skipped
The recording pipeline of obstruction is written data to the recording pipeline in other sound areas, causes the corresponding wake-up thread in all sound areas can not be from
The voice data that caching is read in the corresponding recording pipeline in respective sound area causes what the speech engine of car-mounted terminal can not work to ask
Topic.
Optionally, above-mentioned steps S101 and step S102 can call first thread to realize by electronic equipment, that is, above-mentioned
First thread not only has write-in functions, can also have voice data separation function, processing function etc., repeats no more to this.
It is appreciated that above-mentioned electronic equipment may call upon the other function that first thread realizes electronic equipment, to this without limiting.
Data processing method provided by the invention, electronic equipment can call first thread successively corresponding to each sound area
Before data buffer storage container executes data write operation, first judge the corresponding data buffer storage container in each sound area with the presence or absence of available sky
Between, and then only write operation is executed to the data buffer storage container with available space.In this way, it can be set to avoid electronics
It is standby to execute write operation to the data buffer storage container of no available space because of calling first thread, lead to the feelings for write-in obstruction occur
Condition, so as to avoid occurring the data buffer storage container of write-in obstruction because that can not skip, to the data buffer storage container in other sound areas
Data are written, and cause the corresponding wake-up thread in all sound areas that can not read caching from the corresponding data buffer storage container in the sound area
Voice data, the problem of causing the speech engine of car-mounted terminal can not work.In this way, being write in a certain data buffer storage container
When entering to block, electronic equipment still can call first thread that voice data is written to other data buffer storage containers, so as to
Work normally speech engine.
Previous embodiment describes the process how electronic equipment handles data buffer storage container write-in obstruction, implements below
How example handles the process that data buffer storage container reads obstruction what is involved is electronic equipment.Reading mentioned here obstruction refer to because
Data buffer storage container is sky, i.e. no data in data buffer storage container, leads to correspond to the of the data buffer storage container in speech engine
Two threads can not read data from the data buffer storage container.Specifically:
Electronic equipment can call corresponding second thread of data buffer storage container, and caching is read from data buffer storage container
Voice data, and speech recognition is carried out to the voice data that reads, with determine the corresponding sound area of data buffer storage container whether by
It wakes up.Wherein, above-mentioned the second described thread can be any thread with reading, function.For example, involved in the prior art
And speech engine in wake-up thread.
For example, electronic equipment can identify whether read voice data includes preset wake-up word, to determine caching
Whether the corresponding sound area of the data buffer storage container of the voice data is waken up.Alternatively, electronic equipment can also using it is existing its
His mode, identifies the voice data read, to judge whether corresponding sound area is waken up, repeats no more to this.
Optionally, electronic equipment can be with corresponding second thread of each data buffer storage container of synchronization call, from second line
The voice data of caching is read in the corresponding data buffer storage container of journey.By this way, when electronic equipment is in because of multiple sound areas
Because sound isolation is insufficient, when causing the audio input device in multiple sound areas that can collect from the voice data of identical sound source,
It can make electronic equipment is synchronous to identify which sound area is waken up.
There is data instance with uncached in the first data buffer storage container, then under the scene, electronic equipment is calling first
Corresponding second thread of data buffer storage container, when reading the voice data of caching from the first data buffer storage container, it may appear that read
The case where taking obstruction.
It is slow from the first data if electronic equipment calls corresponding second thread of the first data buffer storage container under the scene
The unread voice data to caching in container is deposited, then electronic equipment can be by corresponding second thread of the first data buffer storage container
It hangs up.In this way, the second thread that can not read data can be persistently called to avoid electronic equipment, executed and read behaviour
Make.
Further, when the duration of corresponding second thread suspension of the first data buffer storage container is greater than preset duration,
Electronic equipment can restore corresponding second thread of the first data buffer storage container automatically, to continue to call first data buffer storage to hold
Corresponding second thread of device executes the operation that data are read from the first data buffer storage container.Wherein, which can root
It is adjusted according to demand.
Data processing method provided by the invention, electronic equipment can be when data buffer storage container occur reading obstruction, can
With by corresponding second thread suspension of the data buffer storage container, the second of data can not be read by avoiding electronic equipment from persistently calling
Thread executes read operation.
Although being appreciated that above-described embodiment is executing subject to data processing side provided by the invention using electronic equipment
Method is illustrated and introduces.But it will be appreciated by persons skilled in the art that specific implementation when, above-mentioned electronic equipment
Above method embodiment can be realized, to this by the voice interactive system installed on electronic equipment or application program etc.
It repeats no more.In addition, there is write-in obstruction to the above-mentioned data buffer storage container for leading to electronic equipment and reads obstruction in the present invention
Reason is without limitation.
Fig. 4 is a kind of structural schematic diagram of data processing equipment provided by the invention, which can apply
In aforementioned described electronic equipment.For example, the data processing equipment can be for applied to the chip in above-mentioned electronic equipment, it can also
Think above-mentioned electronic equipment.As shown in figure 4, the device includes: to obtain module 11, first processing module 12 and writing module 13.Its
In,
Module 11 is obtained, the voice data that the audio input device for obtaining at least two sound areas acquires；
First processing module 12, for judging in the corresponding data buffer storage container in each sound area with the presence or absence of available sky
Between；
Writing module 13, for calling first thread successively to correspond to each be written there are the data buffer storage container of available space
Voice data, and abandon be not present available space the corresponding voice data of data buffer storage container.
Optionally, the first processing module 12, specifically for judging the surplus of the corresponding data buffer storage container in the sound area
Complementary space, if more than or equal to the size of the voice data of the audio input device acquisition in the sound area；If so, determining institute
There are available spaces for the corresponding data buffer storage container in the area Shu Yin；If not, it is determined that the corresponding data buffer storage container in the sound area is not
There are available spaces.
Optionally, the acquisition module 11 obtains VoP specifically for the interface of calling audio input device,
And the voice data of the audio input device acquisition in each sound area is isolated from the VoP；The voice number
The voice data acquired according to the audio input device that packet includes at least two sound area.
Optionally, the electronic equipment is car-mounted terminal.
Fig. 5 is the structural schematic diagram of another data processing equipment provided by the invention, as shown in figure 5, in above-mentioned Fig. 4 institute
On the basis of the block diagram shown, above-mentioned apparatus can also include:
Read module 14, for calling corresponding second thread of the data buffer storage container, from the data buffer storage container
The middle voice data for reading caching, the first data buffer storage container are the uncached data buffer storage container for having voice data；
Second processing module 15, for calling corresponding second line of the first data buffer storage container in the read module 14
Journey, from the first data buffer storage container when the unread voice data to caching, by the first data buffer storage container pair
The second thread suspension answered.
Optionally, the Second processing module 15 is also used to by corresponding second line of the first data buffer storage container
When the duration that journey is hung up is greater than preset duration, restore corresponding second thread of the first data buffer storage container.
Data processing processing provided by the invention, can execute the movement of electronic equipment in above method embodiment, in fact
Existing principle is similar with technical effect, and details are not described herein.
It should be noted that it should be understood that can be realized by way of processing element calls with software with upper module；It can also
To realize in the form of hardware.For example, obtaining module can be the processing element individually set up, also can integrate in above-mentioned apparatus
Some chip in realize, in addition it is also possible to be stored in the form of program code in the memory of above-mentioned apparatus, by above-mentioned
Some processing element of device calls and executes the function of the above processing unit.Furthermore these units can completely or partially collect
At together, can also independently realize.Processing element described here can be a kind of integrated circuit, the processing energy with signal
Power.During realization, each step or above each unit of the above method can pass through the collection of the hardware in processor elements
It is completed at the instruction of logic circuit or software form.
For example, the above unit can be arranged to implement one or more integrated circuits of above method, such as:
One or more specific integrated circuits (application specific integrated circuit, ASIC), or, one
Or multi-microprocessor (digital signal processor, DSP), or, one or more field programmable gate array
(field programmable gate array, FPGA) etc..For another example, when some above unit dispatches journey by processing element
When the form of sequence code is realized, which can be general processor, such as central processing unit (central
Processing unit, CPU) or it is other can be with the processor of caller code.For another example, these units can integrate one
It rises, is realized in the form of system on chip (system-on-a-chip, SOC).
Fig. 6 is the structural schematic diagram of another data processing equipment provided by the invention, which for example may be used
To be electronic equipment, such as car-mounted terminal, smart home etc..As shown in fig. 6, the data processing equipment 600 includes: memory
601 and at least one processor 602.
Memory 601, for storing program instruction.
Processor 602, for being performed the data processing method realized in the present embodiment, specific implementation in program instruction
Principle can be found in above-described embodiment, and details are not described herein again for the present embodiment.
The data processing equipment 600 can also include and input/output interface 603.
Input/output interface 603 may include independent output interface and input interface, or integrated input and defeated
Integrated interface out.Wherein, output interface is used for output data, and input interface is used to obtain the data of input.
The present invention also provides a kind of readable storage medium storing program for executing, it is stored with and executes instruction in readable storage medium storing program for executing, work as data processing
When at least one processor of device executes this and executes instruction, when computer executed instructions are executed by processor, realize above-mentioned
Data processing method in embodiment.
The present invention also provides a kind of program product, the program product include execute instruction, this execute instruction be stored in it is readable
In storage medium.At least one processor of data processing equipment can read this from readable storage medium storing program for executing and execute instruction, at least
One processor executes this and executes instruction so that data processing equipment implements the data processing that above-mentioned various embodiments provide
Method.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the module, only
Only a kind of logical function partition, there may be another division manner in actual implementation, for example, multiple modules can combine or
It is desirably integrated into another system, or some features can be ignored or not executed.
In addition, each module in each embodiment of the present invention can integrate in one processing unit, it is also possible to each
A module physically exists alone, can also be with two or more modules in a unit.Above-mentioned integrated unit both may be used
To use formal implementation of hardware, can also be realized in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) or processor (English: processor) execute this hair
The part steps of bright each embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory
(English: Read-Only Memory, abbreviation: ROM), random access memory (English: Random Access Memory, letter
Claim: RAM), the various media that can store program code such as magnetic or disk.
In the above-described embodiments, it should be appreciated that processor can be central processing unit (English: Central
Processing Unit, referred to as: CPU), it can also be other general processors, digital signal processor (English: Digital
Signal Processor, referred to as: DSP), specific integrated circuit (English: Application Specific Integrated
Circuit, referred to as: ASIC) etc..General processor can be microprocessor or the processor is also possible to any conventional place
Manage device etc..It can be embodied directly in hardware processor in conjunction with the step of the method disclosed in the present and execute completion or use
Hardware and software module combination in reason device execute completion.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (10)
1. a kind of data processing method, which is characterized in that the method is applied to electronic equipment, and the electronic equipment includes setting
Audio input device in each sound area, which comprises
Obtain the voice data of the audio input device acquisition at least two sound areas；
Judge in the corresponding data buffer storage container in each sound area with the presence or absence of available space；
Calling first thread, successively there are the data buffer storage containers of available space, and corresponding voice data is written to each, and abandons
There is no the corresponding voice data of data buffer storage container of available space.
2. the method according to claim 1, wherein the corresponding data buffer storage in each sound area of judgement
It whether there is available space in container, comprising:
Judge the remaining space of the corresponding data buffer storage container in the sound area, if more than or equal to the audio input in the sound area
The size of the voice data of equipment acquisition；
If so, determining the corresponding data buffer storage container in the sound area, there are available spaces；
If not, it is determined that available space is not present in the corresponding data buffer storage container in the sound area.
3. the method according to claim 1, wherein the audio input device for obtaining at least two sound areas is adopted
The voice data of collection, comprising:
The interface of audio input device is called, obtains VoP, the VoP includes at least two sound area
Audio input device acquisition voice data；
The voice data of the audio input device acquisition in each sound area is isolated from the VoP.
4. the method according to claim 1, wherein the method also includes:
It is unread to caching from the first data buffer storage container if calling corresponding second thread of the first data buffer storage container
Voice data, then by corresponding second thread suspension of the first data buffer storage container, the first data buffer storage container is
The uncached data buffer storage container for having voice data.
5. according to the method described in claim 4, it is characterized in that, the method also includes:
When the duration of corresponding second thread suspension of the first data buffer storage container is greater than preset duration, restore described the
Corresponding second thread of one data buffer storage container.
6. a kind of data processing equipment, which is characterized in that described device is applied to electronic equipment, and the electronic equipment includes setting
Audio input device in each sound area, described device include:
Module is obtained, the voice data that the audio input device for obtaining at least two sound areas acquires；
First processing module, for judging in the corresponding data buffer storage container in each sound area with the presence or absence of available space；
Writing module, for calling first thread, successively there are the data buffer storage containers of available space, and corresponding voice is written to each
Data, and abandon the corresponding voice data of data buffer storage container that available space is not present.
7. device according to claim 6, which is characterized in that the first processing module is specifically used for judging the sound
The remaining space of the corresponding data buffer storage container in area, if more than or equal to the voice of the audio input device acquisition in the sound area
The size of data；If so, determining the corresponding data buffer storage container in the sound area, there are available spaces；If not, it is determined that described
Available space is not present in the corresponding data buffer storage container in sound area.
8. device according to claim 6, which is characterized in that described device further include:
Read module, for calling corresponding second thread of the first data buffer storage container, from the first data buffer storage container
The voice data of caching is read, the first data buffer storage container is the uncached data buffer storage container for having voice data；
Second processing module, for calling corresponding second thread of the first data buffer storage container in the read module, from described
In first data buffer storage container it is unread to caching voice data when, by corresponding second line of the first data buffer storage container
Journey is hung up.
9. a kind of data processing equipment characterized by comprising at least one processor and memory；
The memory stores computer executed instructions；
At least one described processor executes the computer executed instructions of the memory storage, so that the data processing equipment
Perform claim requires the described in any item methods of 1-5.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
It executes instruction, when the computer executed instructions are executed by processor, realizes the described in any item methods of claim 1-5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110673871.XA CN113380280B (en) | 2018-12-29 | 2018-12-29 | Data processing method, device and storage medium |
| CN201811632710.0A CN109830249B (en) | 2018-12-29 | 2018-12-29 | Data processing method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811632710.0A CN109830249B (en) | 2018-12-29 | 2018-12-29 | Data processing method, device and storage medium |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110673871.XA Division CN113380280B (en) | 2018-12-29 | 2018-12-29 | Data processing method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109830249A true CN109830249A (en) | 2019-05-31 |
| CN109830249B CN109830249B (en) | 2021-07-06 |
Family
ID=66860010
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811632710.0A Active CN109830249B (en) | 2018-12-29 | 2018-12-29 | Data processing method, device and storage medium |
| CN202110673871.XA Active CN113380280B (en) | 2018-12-29 | 2018-12-29 | Data processing method, device and storage medium |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110673871.XA Active CN113380280B (en) | 2018-12-29 | 2018-12-29 | Data processing method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN109830249B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080817A (en) * | 2019-11-27 | 2020-04-28 | 天地融科技股份有限公司 | Vehicle-mounted unit data writing method, device and system and vehicle-mounted unit |
| CN112698872A (en) * | 2020-12-21 | 2021-04-23 | 北京百度网讯科技有限公司 | Voice data processing method, device, equipment and storage medium |
| EP4044178A3 (en) * | 2021-06-08 | 2023-01-18 | Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd. | Method and apparatus of performing voice wake-up in multiple speech zones, method and apparatus of performing speech recognition in multiple speech zones, device, and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1329300A (en) * | 2000-06-21 | 2002-01-02 | 国际商业机器公司 | Management speech buffer storage method |
| US6640147B1 (en) * | 1997-09-24 | 2003-10-28 | Sony Corporation | Method and apparatus for late buffer processing |
| US20040202073A1 (en) * | 2003-04-09 | 2004-10-14 | Yung-Hsiao Lai | Systems and methods for caching multimedia data |
| CN1585924A (en) * | 2001-11-13 | 2005-02-23 | 皇家飞利浦电子股份有限公司 | Efficient FIFO communication using semaphores |
| EP1591884A2 (en) * | 2004-04-28 | 2005-11-02 | Sony Corporation | Information processing apparatus, information processing method, and program |
| CN101008919A (en) * | 2007-01-31 | 2007-08-01 | 浙江大学 | Audio/video data access method and device based on raw device |
| CN101957800A (en) * | 2010-06-12 | 2011-01-26 | 福建星网锐捷网络有限公司 | Multichannel cache distribution method and device |
| CN103391415A (en) * | 2012-05-11 | 2013-11-13 | 安凯(广州)微电子技术有限公司 | Video data frame loss processing method and system |
| CN203721182U (en) * | 2013-12-25 | 2014-07-16 | 安徽科大讯飞信息科技股份有限公司 | A vehicle-mounted speech processing system |
| CN104090858A (en) * | 2014-06-10 | 2014-10-08 | 中兴通讯股份有限公司 | Data transmission method and device |
| CN104113777A (en) * | 2014-08-01 | 2014-10-22 | 广州金山网络科技有限公司 | Audio stream decoding method and device |
| CN105117351A (en) * | 2015-09-08 | 2015-12-02 | 华为技术有限公司 | Method and apparatus for writing data into cache |
| CN205176826U (en) * | 2015-10-30 | 2016-04-20 | 广西师范大学 | Audio acquisition device based on USB high speed interface |
| CN108897701A (en) * | 2018-06-20 | 2018-11-27 | 珠海市杰理科技股份有限公司 | Cache storage architecture |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1407349A4 (en) * | 2001-07-06 | 2004-10-13 | Genie Australia Pty Ltd E | Method and system for computer software application execution |
| JP2004102647A (en) * | 2002-09-10 | 2004-04-02 | Sony Corp | Recording device and method, reproducing device and method, recording medium and program |
| CN1540954A (en) * | 2003-10-30 | 2004-10-27 | 清华大学深圳研究生院 | Method for controlling flux of audio and video flow transferred in IP video meeting system |
| CN103002384B (en) * | 2011-09-08 | 2015-03-25 | 比亚迪股份有限公司 | Device and method for processing signals of virtual surrounds of four loudspeakers |
| EP2806663B1 (en) * | 2013-05-24 | 2020-04-15 | Harman Becker Automotive Systems GmbH | Generation of individual sound zones within a listening room |
| CN103400496A (en) * | 2013-07-27 | 2013-11-20 | 杭州九树网络科技有限公司 | Information reminding system and method between taxi and passenger |
| JP2015114854A (en) * | 2013-12-12 | 2015-06-22 | 三菱電機株式会社 | Voice transfer device and voice transfer method |
| CN104184817A (en) * | 2014-08-28 | 2014-12-03 | 广州金山网络科技有限公司 | Download optimizing method and device and terminal |
| CN104240739B (en) * | 2014-09-04 | 2017-05-24 | 广东欧珀移动通信有限公司 | Music playing method and device for mobile terminal |
| CN114020482A (en) * | 2017-06-02 | 2022-02-08 | 伊姆西Ip控股有限责任公司 | Method and apparatus for data writing |
| CN109087660A (en) * | 2018-09-29 | 2018-12-25 | 百度在线网络技术（北京）有限公司 | Method, apparatus, equipment and computer readable storage medium for echo cancellor |
-
2018
- 2018-12-29 CN CN201811632710.0A patent/CN109830249B/en active Active
- 2018-12-29 CN CN202110673871.XA patent/CN113380280B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6640147B1 (en) * | 1997-09-24 | 2003-10-28 | Sony Corporation | Method and apparatus for late buffer processing |
| CN1329300A (en) * | 2000-06-21 | 2002-01-02 | 国际商业机器公司 | Management speech buffer storage method |
| CN1585924A (en) * | 2001-11-13 | 2005-02-23 | 皇家飞利浦电子股份有限公司 | Efficient FIFO communication using semaphores |
| US20040202073A1 (en) * | 2003-04-09 | 2004-10-14 | Yung-Hsiao Lai | Systems and methods for caching multimedia data |
| EP1591884A2 (en) * | 2004-04-28 | 2005-11-02 | Sony Corporation | Information processing apparatus, information processing method, and program |
| CN101008919A (en) * | 2007-01-31 | 2007-08-01 | 浙江大学 | Audio/video data access method and device based on raw device |
| CN101957800A (en) * | 2010-06-12 | 2011-01-26 | 福建星网锐捷网络有限公司 | Multichannel cache distribution method and device |
| CN103391415A (en) * | 2012-05-11 | 2013-11-13 | 安凯(广州)微电子技术有限公司 | Video data frame loss processing method and system |
| CN203721182U (en) * | 2013-12-25 | 2014-07-16 | 安徽科大讯飞信息科技股份有限公司 | A vehicle-mounted speech processing system |
| CN104090858A (en) * | 2014-06-10 | 2014-10-08 | 中兴通讯股份有限公司 | Data transmission method and device |
| CN104113777A (en) * | 2014-08-01 | 2014-10-22 | 广州金山网络科技有限公司 | Audio stream decoding method and device |
| CN105117351A (en) * | 2015-09-08 | 2015-12-02 | 华为技术有限公司 | Method and apparatus for writing data into cache |
| CN205176826U (en) * | 2015-10-30 | 2016-04-20 | 广西师范大学 | Audio acquisition device based on USB high speed interface |
| CN108897701A (en) * | 2018-06-20 | 2018-11-27 | 珠海市杰理科技股份有限公司 | Cache storage architecture |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080817A (en) * | 2019-11-27 | 2020-04-28 | 天地融科技股份有限公司 | Vehicle-mounted unit data writing method, device and system and vehicle-mounted unit |
| CN112698872A (en) * | 2020-12-21 | 2021-04-23 | 北京百度网讯科技有限公司 | Voice data processing method, device, equipment and storage medium |
| EP4044178A3 (en) * | 2021-06-08 | 2023-01-18 | Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd. | Method and apparatus of performing voice wake-up in multiple speech zones, method and apparatus of performing speech recognition in multiple speech zones, device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109830249B (en) | 2021-07-06 |
| CN113380280A (en) | 2021-09-10 |
| CN113380280B (en) | 2022-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106887225B (en) | Acoustic feature extraction method and device based on convolutional neural network and terminal equipment | |
| CN109830249A (en) | Data processing method, device and storage medium | |
| JP7324313B2 (en) | Voice interaction method and device, terminal, and storage medium | |
| JP6811755B2 (en) | Voice wake-up method by reading, equipment, equipment and computer-readable media, programs | |
| CN108492827B (en) | Wake-up processing method, device and the storage medium of application program | |
| WO2020028594A1 (en) | Storage edge controller with a metadata computational engine | |
| US20200202857A1 (en) | Voice wake-up processing method, apparatus and storage medium | |
| US20190237070A1 (en) | Voice interaction method, device, apparatus and server | |
| CN110211589A (en) | Awakening method, device and vehicle, the machine readable media of onboard system | |
| KR20220083990A (en) | Method of performing voice wake-up in multiple speech zones, method of performing speech recognition inmultiple speech zones, apparatus, electronic device, storage medium, and computer program | |
| CN110070866A (en) | Audio recognition method and device | |
| CN104978966B (en) | Frame losing compensation implementation method and device in audio stream | |
| CN109712608A (en) | Multitone area wake-up test method, apparatus and storage medium | |
| CN114036390A (en) | Scene service recommendation method and device, electronic equipment and storage medium | |
| CN110992953A (en) | Voice data processing method, device, system and storage medium | |
| CN111312230A (en) | Voice interaction monitoring method and device for voice conversation platform | |
| WO2021164560A1 (en) | Multi-core chip and scheduling method therefor | |
| CN110262838A (en) | A kind of processing method of program crashing, device, terminal and storage medium | |
| CN113870912A (en) | Recording method, device, equipment and storage medium | |
| CN110035167A (en) | The way of recording and relevant apparatus | |
| CN110085237B (en) | Recovery method, device and equipment of interactive process | |
| CN107766264B (en) | Data transfer control method, mobile terminal and computer readable storage medium | |
| CN111899738A (en) | Dialogue generating method, device and storage medium | |
| CN116709112A (en) | Audio data processing method, system, data processing device and storage medium | |
| CN116994579A (en) | Speech recognition method, device, computer equipment and storage medium |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211019 Address after: 100176 101, floor 1, building 1, yard 7, Ruihe West 2nd Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing Patentee after: Apollo Zhilian (Beijing) Technology Co.,Ltd. Address before: 100085 Baidu Building, 10 Shangdi Tenth Street, Haidian District, Beijing Patentee before: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd. |