CN109285556B - Audio processing method, device, equipment and storage medium - Google Patents

Audio processing method, device, equipment and storage medium Download PDF

Info

Publication number
CN109285556B
CN109285556B CN201811152719.1A CN201811152719A CN109285556B CN 109285556 B CN109285556 B CN 109285556B CN 201811152719 A CN201811152719 A CN 201811152719A CN 109285556 B CN109285556 B CN 109285556B
Authority
CN
China
Prior art keywords
audio data
channel audio
waveform diagram
channel
waveform
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
Application number
CN201811152719.1A
Other languages
Chinese (zh)
Other versions
CN109285556A (en
Inventor
贺学焱
欧阳能钧
宋晔
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Apollo Intelligent Connectivity Beijing Technology Co Ltd
Original Assignee
Apollo Intelligent Connectivity Beijing Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Apollo Intelligent Connectivity Beijing Technology Co Ltd filed Critical Apollo Intelligent Connectivity Beijing Technology Co Ltd
Priority to CN201811152719.1A priority Critical patent/CN109285556B/en
Publication of CN109285556A publication Critical patent/CN109285556A/en
Application granted granted Critical
Publication of CN109285556B publication Critical patent/CN109285556B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering
    • 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
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0272—Voice signal separating
    • 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
    • G10L25/60—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 for measuring the quality of voice signals
    • 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
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering
    • G10L2021/02082—Noise filtering the noise being echo, reverberation of the speech

Landscapes

  • Engineering & Computer Science (AREA)
  • Quality & Reliability (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)
  • Stereophonic System (AREA)

Abstract

The application provides an audio processing method, an apparatus, a device and a storage medium, wherein the method comprises the following steps: acquiring stereo audio data sent by a terminal; carrying out separation processing on the stereo audio data to obtain first channel audio data and second channel audio data; removing echo data in the second channel audio data to obtain processed second channel audio data; and respectively carrying out oscillogram drawing processing on the first channel audio data, the second channel audio data and the processed second channel audio data to obtain a first oscillogram, a second oscillogram and a third oscillogram. The quality of the audio sent by the terminal is automatically judged without manually judging the audio quality, the judgment efficiency of judging whether the audio quality, the hardware of the terminal and the front-end signal processing capacity meet the requirements of a speech recognition engine is improved, and the labor cost is reduced; and accurately judging whether the hardware and the front-end signal processing capability of the terminal meet the requirements of a speech recognition engine.

Description

Audio processing method, device, equipment and storage medium
Technical Field
The embodiment of the application relates to the technical field of terminals, in particular to an audio processing method, an audio processing device, audio processing equipment and a storage medium.
Background
With the development of communication and intelligent terminal technologies, various terminals are widely developed and applied, and the terminals include intelligent terminal devices such as mobile phones, tablet computers and computers, and also include other intelligent devices such as intelligent sound boxes and intelligent televisions. After a hardware device manufacturer completes system integration of a terminal, it is necessary to verify whether the quality of audio played by the terminal has met the requirements of a speech engine, so as to determine whether the hardware and front-end signal processing capabilities of the terminal device meet the requirements of the speech recognition engine.
In the prior art, when detecting whether hardware and front-end signal processing capability of hardware equipment meet requirements of a speech recognition engine, an artificial mode scene is adopted to artificially judge the audio quality derived from the equipment.
However, in the prior art, the manual method for discriminating the audio quality derived from the device is time-consuming, is not favorable for rapid detection, and may cause detection errors.
Disclosure of Invention
The embodiment of the application provides an audio processing method, an audio processing device, an audio processing apparatus and a storage medium, which are used for solving the problems in the above scheme.
A first aspect of the present application provides an audio processing method, including:
acquiring stereo audio data sent by a terminal;
separating the stereo audio data to obtain first channel audio data and second channel audio data;
removing echo data in the second channel audio data according to the first channel audio data to obtain processed second channel audio data, wherein the echo data is audio sent by a loudspeaker of the terminal;
performing waveform drawing processing on the first channel audio data, the second channel audio data, and the processed second channel audio data, respectively, to obtain a first waveform corresponding to the first channel audio data, a second waveform corresponding to the second channel audio data, and a third waveform corresponding to the processed second channel audio data.
Optionally, the first channel audio data is speaker channel audio data, and the second channel audio data is microphone channel audio data.
Optionally, the first channel audio data includes a speaker identifier, and the second channel audio data includes a microphone identifier;
before the stereo audio data is separated to obtain first channel audio data and second channel audio data, the method further includes:
and determining the first channel audio data as speaker channel audio data according to the speaker identification, and determining the second channel audio data as microphone channel audio data according to the microphone identification.
Optionally, respectively performing waveform drawing processing on the first channel audio data, the second channel audio data, and the processed second channel audio data to obtain a first waveform diagram corresponding to the first channel audio data, a second waveform diagram corresponding to the second channel audio data, and a third waveform diagram corresponding to the processed second channel audio data, including:
sampling the first channel audio data, the second channel audio data and the processed second channel audio data to obtain first sampled audio data, second sampled audio data and third sampled audio data respectively;
and respectively drawing oscillograms for the first sampled audio data, the second sampled audio data and the third sampled audio data to obtain the first oscillogram, the second oscillogram and the third oscillogram.
Optionally, the method further includes:
acquiring single-channel audio data sent by a terminal;
sampling the single-channel audio data according to the frequency characteristics of the single-channel audio data to obtain sampled single-channel audio data;
and drawing a waveform diagram for the sampled single-channel audio data to obtain a fourth waveform diagram corresponding to the single-channel audio data.
Optionally, after performing waveform drawing processing on the first channel audio data, the second channel audio data, and the processed second channel audio data respectively to obtain a first waveform diagram corresponding to the first channel audio data, a second waveform diagram corresponding to the second channel audio data, and a third waveform diagram corresponding to the processed second channel audio data, the method further includes:
displaying the first waveform diagram, the second waveform diagram and the third waveform diagram.
Optionally, displaying the first waveform diagram, the second waveform diagram, and the third waveform diagram includes:
respectively displaying the first waveform diagram, the second waveform diagram and the third waveform diagram on different display windows;
or,
and displaying the first waveform diagram, the second waveform diagram and the third waveform diagram on the same window in an overlapping manner, wherein the first waveform diagram, the second waveform diagram and the third waveform diagram are different in marking mode.
A second aspect of the present application provides an audio processing apparatus comprising:
the first acquisition module is used for acquiring stereo audio data sent by the terminal;
the separation module is used for carrying out separation processing on the stereo audio data to obtain first channel audio data and second channel audio data;
the removing module is used for removing echo data in the second channel audio data according to the first channel audio data to obtain processed second channel audio data, wherein the echo data is audio sent by a loudspeaker of the terminal;
the first drawing module is configured to perform waveform drawing processing on the first channel audio data, the second channel audio data, and the processed second channel audio data, respectively, to obtain a first waveform corresponding to the first channel audio data, a second waveform corresponding to the second channel audio data, and a third waveform corresponding to the processed second channel audio data.
Optionally, the first channel audio data is speaker channel audio data, and the second channel audio data is microphone channel audio data.
Optionally, the first channel audio data includes a speaker identifier, and the second channel audio data includes a microphone identifier;
the device, still include:
a determining module, configured to determine, according to the speaker identifier, that the first channel audio data is speaker channel audio data before the separating module performs separation processing on the stereo audio data to obtain first channel audio data and second channel audio data, and determine, according to the microphone identifier, that the second channel audio data is microphone channel audio data.
Optionally, the first drawing module includes:
the sampling submodule is used for sampling the first channel audio data, the second channel audio data and the processed second channel audio data to respectively obtain first sampling audio data, second sampling audio data and third sampling audio data;
and the drawing submodule is used for drawing oscillograms for the first sampling audio data, the second sampling audio data and the third sampling audio data respectively to obtain the first oscillogram, the second oscillogram and the third oscillogram.
Optionally, the apparatus further includes:
the second acquisition module is used for acquiring single-channel audio data sent by the terminal;
the sampling module is used for sampling the single-channel audio data according to the frequency characteristics of the single-channel audio data to obtain the sampled single-channel audio data;
and the second drawing module is used for drawing a waveform diagram for the sampled single-channel audio data to obtain a fourth waveform diagram corresponding to the single-channel audio data.
Optionally, the apparatus further includes:
a display module, configured to display the first waveform diagram, the second waveform diagram, and the third waveform diagram after the first rendering module performs waveform diagram rendering processing on the first channel audio data, the second channel audio data, and the processed second channel audio data, respectively, to obtain a first waveform diagram corresponding to the first channel audio data, a second waveform diagram corresponding to the second channel audio data, and a third waveform diagram corresponding to the processed second channel audio data.
Optionally, the display module is specifically configured to:
respectively displaying the first waveform diagram, the second waveform diagram and the third waveform diagram on different display windows;
or,
and displaying the first waveform diagram, the second waveform diagram and the third waveform diagram in an overlapped mode on the same window, wherein the first waveform diagram, the second waveform diagram and the third waveform diagram are different in marking mode.
A third aspect of the application provides a control device, a transmitter, a receiver, a memory and a processor;
the memory is to store computer instructions; the processor is configured to execute the computer instructions stored in the memory to implement the audio processing method provided in any implementation manner of the first aspect.
A fourth aspect of the present application provides a storage medium, comprising: a readable storage medium and computer instructions stored in the readable storage medium; the computer instructions are used for implementing the audio processing method provided by any implementation manner of the first aspect.
According to the audio processing method, the audio processing device, the audio processing equipment and the storage medium, stereo audio data sent by a terminal are obtained; carrying out separation processing on the stereo audio data to obtain first channel audio data and second channel audio data; removing echo data in the second channel audio data according to the first channel audio data to obtain processed second channel audio data, wherein the echo data is audio sent by a loudspeaker of the terminal; and respectively carrying out oscillogram drawing processing on the first channel audio data, the second channel audio data and the processed second channel audio data to obtain a first oscillogram, a second oscillogram and a third oscillogram. The quality of the audio sent by the terminal can be automatically judged without manually judging the audio quality, so that the judgment efficiency of judging whether the audio quality, the hardware of the terminal and the front-end signal processing capacity meet the requirements of a speech recognition engine is improved, and the labor cost is reduced; whether the hardware and the front-end signal processing capability of the terminal meet the requirements of a speech recognition engine can be accurately judged.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a flowchart of a first embodiment of an audio processing method according to an embodiment of the present application;
fig. 2 is a flowchart of a second embodiment of an audio processing method according to an embodiment of the present application;
fig. 3 is a schematic diagram of 8-bit audio data in a second embodiment of an audio processing method according to the present application;
fig. 4 is a schematic diagram of 16-bit audio data in a second embodiment of an audio processing method according to the present application;
fig. 5 is a first schematic interface diagram in a second embodiment of an audio processing method according to the present application;
fig. 6 is a second schematic interface diagram in a second embodiment of an audio processing method according to the present application;
fig. 7 is a third schematic interface diagram in a second embodiment of an audio processing method according to the present application;
fig. 8 is a flowchart of a third embodiment of an audio processing method according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of a first embodiment of an audio processing apparatus according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of a second embodiment of an audio processing apparatus according to an embodiment of the present application;
fig. 11 is a schematic structural diagram of a first embodiment of a control device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
With the gradual development of the artificial intelligence technology, an audio technology is provided on the terminal, for example, a voice recognition function is provided, the terminal can output and record audio, and the terminal can process the audio. The accuracy of the audio calculation result, especially the accuracy of the speech engine calculation result, is completely affected by the quality of the audio data, and the terminal cannot correctly process a distorted section of speech data. Therefore, before the device accesses the voice recognition function, whether the hardware of the terminal and the front-end signal processing capability of the system meet the basic requirements of the voice recognition engine needs to be checked.
In the prior art, the quality requirements of a speech recognition engine of a terminal on audio data are clear voice, smooth sound, full tone, no amplitude interception, low equipment background noise and higher signal-to-noise ratio than a fixed value. The speech recognition engine requires a certain noise reduction capability of the hardware device of the terminal, etc. At present, no existing tool in the market can help manufacturers to quickly check whether the quality of the audio generated by the terminal reaches the standard, so most manufacturers do not know how to check the front-end signal processing capability of the speech engine after completing system integration, and only can rely on a speech interaction software provider. After the terminal accesses the speech recognition engine, the terminal has a series of problems of low awakening rate and low recognition rate; after the examination and analysis by the speech recognition expert, the fact that the front-end signal processing capability of the terminal hardware equipment does not meet the requirement of a speech engine is found. Therefore, after the hardware device of the terminal completes system integration, it is necessary to verify whether the quality of the audio data sent by the terminal has reached the requirements of the speech engine.
In the prior art, after a manufacturer completes the integration of a system and hardware of a terminal, a voice technology provider sends out a voice recognition expert to check and accept the hardware function of the terminal, the checking and accepting method is that a voice engineer simulates a voice interaction scene through manual work, then a recording device is used for recording audio data sent by the terminal, then the audio data are exported from the recording device, and professional audio analysis software is used for manually judging and checking and accepting the quality of the audio data.
However, in the prior art, whether the audio data sent by the terminal reaches the standard or not is judged, a professional voice engineer needs to use audio analysis software to manually compare and analyze the audio data, so that problems are not easy to quickly troubleshoot, quick detection is not easy, and a detection error condition may occur.
In view of the above existing problems, the present application provides an audio processing method, apparatus, device and storage medium, which can automatically determine the quality of an audio sent by a terminal without manually determining the quality of the audio. This scheme is illustrated in detail below by means of several specific examples.
Fig. 1 is a flowchart of a first embodiment of an audio processing method provided in an embodiment of the present application, and as shown in fig. 1, an execution subject of the scheme may be a control device, or a terminal device, and the audio processing method specifically includes the following steps:
s101, stereo audio data sent by a terminal are obtained.
In this step, specifically, when the terminal sends out stereo audio data, the stereo audio data is recorded. Among them, stereo audio data is also called two-channel audio data.
For example, a control device is provided, where the control device employs an android system, the android system is provided with a standardized recording Interface (API for short), a sampling rate parameter is 16000 hertz (Hz), and 16-bit encoding is employed; the control equipment can record single-channel audio and double-channel audio through a recording interface, and then the audio is stored in Pulse Code Modulation (PCM for short) PCM and WAV formats; and the terminal plays the stereo audio data, and then the control equipment records the audio through the recording interface to acquire the stereo audio data from the terminal.
S102, carrying out separation processing on the stereo audio data to obtain first channel audio data and second channel audio data.
In this step, specifically, the stereo audio data is subjected to data structure separation processing to obtain two channels of audio data, which are the first channel audio data and the second channel audio data respectively.
For example, the first channel audio data is Speaker (Speaker) channel audio data, and the second channel audio data is Microphone (MIC) channel audio data.
S103, according to the first sound channel audio data, removing echo data in the second sound channel audio data to obtain processed second sound channel audio data, wherein the echo data is audio sent by a loudspeaker of the terminal.
In this step, specifically, first channel audio data and second channel audio data are respectively acquired, where the second channel audio data is microphone channel audio data, and then data acquired by the second channel audio data is superposition of the first channel audio data and actual sound data, and it is necessary to reduce the first channel audio data in the second channel audio data by using a software echo cancellation algorithm. For example, if the first channel audio data is speaker channel audio data, the second channel audio data is microphone channel audio data, and the data collected by the microphone channel audio data is a superposition of the speaker channel audio data and actual sound data, it is necessary to reduce the speaker channel audio data in the microphone channel audio data by using a software echo cancellation algorithm.
The echo data in the second channel audio data can be removed according to the software echo cancellation algorithm, and it can be known that the echo data is the audio frequency sent by the loudspeaker of the terminal, and the echo data is the first channel audio data, so that the processed second channel audio data is obtained.
For example, a control device is provided, the control device adopts an android system, and the control device creates three pipelines; the control equipment divides the obtained stereo audio data sent by the terminal into loudspeaker channel audio data and microphone channel audio data in a stereo mode; the control equipment refers to the audio data of the loudspeaker sound channel, removes the echo data in the audio data of the microphone sound channel, the loudspeaker data is the audio frequency sent out by the loudspeaker of the terminal, and the processed audio data of the microphone sound channel is obtained; the control device places the speaker channel audio data and the processed microphone channel audio data in the created two pipes, respectively.
And S104, respectively carrying out waveform drawing processing on the first channel audio data, the second channel audio data and the processed second channel audio data to obtain a first waveform corresponding to the first channel audio data, a second waveform corresponding to the second channel audio data and a third waveform corresponding to the processed second channel audio data.
In this step, specifically, three pipelines are created, namely a first pipeline, a second pipeline and a third pipeline. Performing waveform drawing processing on the first channel audio data on a first pipeline to obtain a first waveform corresponding to the first channel audio data; performing oscillogram drawing processing on the second channel audio data on a second pipeline to obtain a second oscillogram corresponding to the second channel audio data; and performing waveform drawing processing on the processed second channel audio data on a third pipeline to obtain a third waveform corresponding to the processed second channel audio data.
In the embodiment, stereo audio data sent by a terminal is obtained; carrying out separation processing on the stereo audio data to obtain first channel audio data and second channel audio data; removing echo data in the second channel audio data according to the first channel audio data to obtain processed second channel audio data, wherein the echo data is audio sent by a loudspeaker of the terminal; and respectively carrying out oscillogram drawing processing on the first channel audio data, the second channel audio data and the processed second channel audio data to obtain a first oscillogram, a second oscillogram and a third oscillogram. The quality of the audio sent by the terminal can be automatically judged without manually judging the audio quality, so that the judgment efficiency of judging whether the audio quality, the hardware of the terminal and the front-end signal processing capacity meet the requirements of a speech recognition engine is improved, and the labor cost is reduced; whether the hardware and the front-end signal processing capability of the terminal meet the requirements of a speech recognition engine can be accurately judged.
Fig. 2 is a flowchart of a second embodiment of an audio processing method provided in an embodiment of the present application, and as shown in fig. 2, an execution subject of the scheme may be a control device, or a terminal device, and the audio processing method specifically includes the following steps:
s201, stereo audio data sent by the terminal are obtained.
In this step, specifically, this step may refer to step S101 in fig. 1, and is not described again.
S202, the stereo audio data are separated to obtain first channel audio data and second channel audio data.
Optionally, the first channel audio data is speaker channel audio data, and the second channel audio data is microphone channel audio data.
Or, optionally, the first channel audio data includes a speaker identifier, and the second channel audio data includes a microphone identifier; then before step 203, further comprising: and determining the first channel audio data as the loudspeaker channel audio data according to the loudspeaker identification, and determining the second channel audio data as the microphone channel audio data according to the microphone identification.
In this step, specifically, when the stereo audio data is separated, the characteristics of the data structure are collected in the separation process, and it may be directly determined that the first channel audio data is speaker channel audio data and the second channel audio data is microphone channel audio data.
Or, the first channel audio data carries a speaker identifier, and the second channel audio data carries a microphone identifier, so that it can be determined that the first channel audio data is speaker channel audio data, and the second channel audio data is microphone channel audio data.
For example, fig. 3 is a schematic diagram of 8-bit audio data in a second embodiment of the audio processing method provided in the present application, and as shown in fig. 3, all of the 8-bit monaural audio data are 0 channel data; the 8 is the 0 channel data and the 1 channel data in the stereo audio data in sequence, wherein the 0 channel data is the left channel data of the terminal, and the 1 channel data is the right channel data of the terminal; the channel 0 data and the channel 1 data in the stereo audio data need to be separated to obtain the speaker channel audio data and the microphone channel audio data, respectively.
For example, fig. 4 is a schematic diagram of 16-bit audio data in a second embodiment of the audio processing method provided in the present application, and as shown in fig. 4, the 16-bit mono audio data sequentially includes 0-channel low byte data and 0-channel high byte data; 16, in the stereo audio data, 0 channel low byte data, 0 channel high byte data, 1 channel low byte data, and 1 channel high byte data are sequentially included, where the 0 channel low byte data and the 0 channel high byte data are left channel data of the terminal, and the 1 channel low byte data and the 1 channel high byte data are right channel data of the terminal; the channel 0 data and the channel 1 data in the stereo audio data need to be separated to obtain the speaker channel audio data and the microphone channel audio data, respectively.
S203, according to the first sound channel audio data, removing echo data in the second sound channel audio data to obtain processed second sound channel audio data, wherein the echo data is audio sent by a loudspeaker of the terminal.
In this step, specifically, this step may refer to step S103 in fig. 1, and is not described again.
S204, sampling the first channel audio data, the second channel audio data and the processed second channel audio data to respectively obtain first sampling audio data, second sampling audio data and third sampling audio data.
In this step, specifically, the first channel audio data is sampled according to the frequency characteristic of the first channel audio data to obtain first sampled audio data; sampling the second channel audio data according to the frequency characteristics of the second channel audio data to obtain second sampled audio data; and sampling the processed second channel audio data according to the frequency characteristics of the processed second channel audio data to obtain third sampled audio data.
For example, a control device is provided, the control device adopts an android system, and the control device creates three pipelines which are a first pipeline, a second pipeline and a third pipeline respectively; the control equipment puts the audio data of the loudspeaker sound channel into a first pipeline, puts the audio data of the microphone sound channel into a second pipeline, and puts the processed audio data of the microphone sound channel into a third pipeline; the control equipment samples the audio data of the sound channel of the loudspeaker in the first pipeline to generate first sampled audio data; the control equipment samples the microphone channel audio data in the second pipeline to generate second sampled audio data; and the control equipment samples the processed microphone channel audio data in the second pipeline to generate third sampled audio data.
S205, respectively drawing oscillograms for the first sampled audio data, the second sampled audio data and the third sampled audio data to obtain a first oscillogram, a second oscillogram and a three-oscillogram.
In this step, specifically, for example, a control device is provided, the control device adopts an android system, and the control device creates three pipelines which are a first pipeline, a second pipeline and a third pipeline respectively; the control equipment draws a oscillogram for the first sampling audio data in the first pipeline to obtain a first oscillogram; the control equipment draws a oscillogram for the second sampled audio data in the second pipeline to obtain a second oscillogram; and the control equipment draws a waveform diagram for the third sampled audio data in the third pipeline to obtain a third waveform diagram.
The waveform diagram is drawn in the following way: the number of samples per cycle is equal to the sampling frequency divided by the sine wave frequency to obtain the number of samples per cycle; then divide 2 π radians by the number of samples per cycle; then, obtaining samples per cycle by using a sin function according to the number of samples per cycle; then, the sampling is repeatedly carried out on the sample in one period, so that a continuous waveform is established, and a waveform diagram is obtained.
For example, fig. 5 is a first interface schematic diagram of an embodiment two of the audio processing method provided in the present application, and as shown in fig. 5, a display interface of stereo audio data may be provided, the stereo sound sent by the terminal may be recorded by starting with a "record" key, the stereo sound may be recorded again by selecting a "reset" key, the stereo sound may be deleted by selecting a "delete" key, left channel data of a storm stereo sound may be selected by selecting a "left channel" key, and right channel data of the storm stereo sound may be selected by selecting a "right channel" key.
Fig. 6 is a second interface schematic diagram in a second embodiment of the audio processing method according to the present application, as shown in fig. 6, it can be shown that the sampling rate of stereo audio data is 16000, the audio format of the stereo audio data is PCM, and the stereo audio data is stereo; "on" indicates that echo cancellation is being performed on the stereo audio data is shown; the right channel data subjected to echo cancellation can be played; processing of stereo audio data may be cleared by a "clear record" button selection.
Fig. 7 is a third schematic interface diagram in the second embodiment of the audio processing method according to the embodiment of the present application, and as shown in fig. 7, the first waveform diagram, the second waveform diagram, and the third waveform diagram may be stored in the path a, and names of the first waveform diagram, the second waveform diagram, and the third waveform diagram are displayed
S206, displaying the first waveform diagram, the second waveform diagram and the third waveform diagram.
Optionally, S206 includes the following several embodiments:
first embodiment of S206: and respectively displaying the first waveform diagram, the second waveform diagram and the third waveform diagram on different display windows.
Second embodiment of S206: and displaying the first waveform diagram, the second waveform diagram and the third waveform diagram on the same window in an overlapping manner, wherein the first waveform diagram, the second waveform diagram and the third waveform diagram are different in marking mode.
In this step, specifically, a first waveform diagram corresponding to the first channel audio data, a second waveform diagram corresponding to the second channel audio data, and a third waveform diagram corresponding to the processed second channel audio data are displayed.
For example, the first waveform diagram, the second waveform diagram and the third waveform diagram may be respectively displayed on different display windows of a display screen of the control device. Alternatively, the first waveform diagram, the second waveform diagram, and the third waveform diagram are displayed in an overlapping manner on the same window of the display screen of the control device, and different colors or marks may be given to the three waveform diagrams in order to distinguish the three waveform diagrams.
In this embodiment, audio data of two channels, which are audio data of a first channel and audio data of a second channel respectively, are obtained by performing separation processing on stereo audio data in a data structure; identifying speaker channel audio data and microphone channel audio data; according to the audio data of the sound channel of the loudspeaker, eliminating echo data in the audio data of the sound channel of the microphone; and then sampling and drawing a waveform diagram for the speaker channel audio data, the microphone channel audio data and the processed microphone channel audio data respectively to obtain respective waveform diagrams of the three paths of audio data. The quality of the audio sent by the terminal can be automatically judged without manually judging the audio quality, so that the judgment efficiency of judging whether the audio quality, the hardware of the terminal and the front-end signal processing capacity meet the requirements of a speech recognition engine is improved, and the labor cost is reduced; whether the hardware and the front-end signal processing capability of the terminal meet the requirements of a speech recognition engine can be accurately judged.
Fig. 8 is a flowchart of a third embodiment of an audio processing method provided in an embodiment of the present application, and as shown in fig. 8, an execution subject of the scheme may be a control device, or a terminal device, and the audio processing method specifically includes the following steps:
s301, single-channel audio data sent by the terminal are obtained.
In this step, specifically, when the terminal sends single-channel audio data, the single-channel audio data is recorded.
For example, a control device is provided, the control device adopts an android system, the android system is provided with a standardized recording interface, the sampling rate parameter is 16000 Hz, and 16-bit coding is adopted; the control equipment can record single-channel audio and double-channel audio through the recording interface; the terminal plays the single-channel audio data, then the control equipment records the audio through the recording interface, and the single-channel audio data are obtained from the terminal.
And S302, sampling the single-channel audio data according to the frequency characteristics of the single-channel audio data to obtain the sampled single-channel audio data.
In this step, specifically, after the single-channel audio data is subjected to sampling processing, the sampled single-channel audio data can be obtained.
And S303, drawing a waveform diagram for the sampled single-channel audio data to obtain a fourth waveform diagram corresponding to the single-channel audio data.
In this step, specifically, for example, a control device is provided, where the control device uses an android system, the control device creates a single-channel data pipe, and uses a thread to read single-channel audio data; then, the thread of the control equipment performs sampling processing on the data pipeline at a certain sampling frequency, and then a real-time oscillogram is drawn; the control device displays a waveform diagram of the single-channel audio data.
In this embodiment, a waveform diagram is drawn for the sampled single-channel audio data, so as to obtain a waveform diagram of the single-channel audio data. The quality of the audio sent by the terminal can be automatically judged without manually judging the audio quality, so that the judgment efficiency of judging whether the audio quality, the hardware of the terminal and the front-end signal processing capacity meet the requirements of a speech recognition engine is improved, and the labor cost is reduced; whether the hardware and the front-end signal processing capability of the terminal meet the requirements of a speech recognition engine can be accurately judged.
Fig. 9 is a schematic structural diagram of a first embodiment of an audio processing apparatus according to an embodiment of the present application, and as shown in fig. 9, the apparatus according to the present embodiment includes:
a first obtaining module 41, configured to obtain stereo audio data sent by a terminal;
a separation module 42, configured to perform separation processing on the stereo audio data to obtain first channel audio data and second channel audio data;
the removing module 43 is configured to remove, according to the first channel audio data, echo data in the second channel audio data to obtain processed second channel audio data, where the echo data is an audio frequency sent by a speaker of the terminal;
the first drawing module 44 is configured to perform waveform drawing processing on the first channel audio data, the second channel audio data, and the processed second channel audio data, respectively, to obtain a first waveform diagram corresponding to the first channel audio data, a second waveform diagram corresponding to the second channel audio data, and a third waveform diagram corresponding to the processed second channel audio data.
The audio processing apparatus provided in this embodiment is the same as the technical solution for implementing the control device in the audio processing method provided in any of the foregoing embodiments, and the implementation principle and technical effects are similar and will not be described again.
Fig. 10 is a schematic structural diagram of a second embodiment of an audio processing apparatus according to an embodiment of the present application, and based on the embodiment shown in fig. 9, as shown in fig. 10, the apparatus according to the present embodiment includes first channel audio data that is speaker channel audio data, and second channel audio data that is microphone channel audio data. Or the first channel audio data comprises a loudspeaker identification, and the second channel audio data comprises a microphone identification; the apparatus provided in this embodiment further includes: the determining module 51 is configured to determine, before the separating module 42 performs separation processing on the stereo audio data to obtain first channel audio data and second channel audio data, that the first channel audio data is speaker channel audio data according to a speaker identifier, and that the second channel audio data is microphone channel audio data according to a microphone identifier.
A first rendering module 44 comprising:
the sampling submodule 441 is configured to sample the first channel audio data, the second channel audio data, and the processed second channel audio data to obtain first sampled audio data, second sampled audio data, and third sampled audio data, respectively;
the rendering sub-module 442 is configured to render a waveform diagram for the first sampled audio data, the second sampled audio data, and the third sampled audio data, respectively, to obtain a first waveform diagram, a second waveform diagram, and a three waveform diagram.
The apparatus provided in this embodiment further includes:
a second obtaining module 52, configured to obtain single-channel audio data sent by the terminal;
the sampling module 53 is configured to perform sampling processing on the single-channel audio data according to the frequency characteristic of the single-channel audio data to obtain sampled single-channel audio data;
and a second drawing module 54, configured to draw a waveform diagram for the sampled single-channel audio data, so as to obtain a fourth waveform diagram corresponding to the single-channel audio data.
The apparatus provided in this embodiment further includes:
the display module 55 is configured to perform waveform drawing processing on the first channel audio data, the second channel audio data, and the processed second channel audio data respectively by the first drawing module 44, to obtain a first waveform diagram corresponding to the first channel audio data, a second waveform diagram corresponding to the second channel audio data, and a third waveform diagram corresponding to the processed second channel audio data, and then display the first waveform diagram, the second waveform diagram, and the third waveform diagram.
The display module 55 is specifically configured to: respectively displaying a first waveform diagram, a second waveform diagram and a third waveform diagram on different display windows; or, the first waveform diagram, the second waveform diagram and the third waveform diagram are displayed in an overlapped mode on the same window, wherein the first waveform diagram, the second waveform diagram and the third waveform diagram are different in marking mode.
The audio processing apparatus provided in this embodiment is the same as the technical solution for implementing the control device in the audio processing method provided in any of the foregoing embodiments, and the implementation principle and the technical effect are similar and are not described again.
Fig. 11 is a schematic structural diagram of a first embodiment of a control device provided in an embodiment of the present application, as shown in fig. 11, the control device, a transmitter 61, a receiver 62, a memory 63, and a processor 64;
memory 63 is used to store computer instructions; the processor 64 is used for executing the computer instructions stored in the memory 63 to implement the technical solution of the audio processing method provided by any implementation manner in the foregoing embodiments.
The present application also provides a storage medium, comprising: readable storage media and computer instructions, the computer instructions stored in the readable storage media; the computer instructions are used for implementing the technical scheme of the audio processing method in any implementation manner provided by the foregoing example.
In the above Specific implementation of the control device, it should be understood that the Processor 64 may be a Central Processing Unit (CPU), other general purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. The general purpose processor may be a microprocessor or the processor 64 may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments disclosed herein may be embodied directly in a hardware processor, or in a combination of hardware and software modules within the processor 64.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: read-only memory (ROM), RAM, flash memory, hard disk, solid state disk, magnetic tape (magnetic tape), floppy disk (flexible disk), optical disk (optical disk), and any combination thereof.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims (14)

1. An audio processing method, comprising:
acquiring stereo audio data sent by a terminal;
separating the stereo audio data to obtain first channel audio data and second channel audio data, wherein the first channel audio data is speaker channel audio data, the second channel audio data is microphone channel audio data, and the second channel audio data is superposition of the first channel audio data and actual sound data;
removing echo data in the second channel audio data according to the first channel audio data to obtain processed second channel audio data, wherein the echo data is audio sent by a loudspeaker of the terminal;
and respectively carrying out waveform drawing processing on the first channel audio data, the second channel audio data and the processed second channel audio data to obtain a first waveform corresponding to the first channel audio data, a second waveform corresponding to the second channel audio data and a third waveform corresponding to the processed second channel audio data.
2. The method of claim 1, wherein the first channel audio data includes a speaker identification and the second channel audio data includes a microphone identification;
before the stereo audio data is separated to obtain a first channel audio data and a second channel audio data, the method further includes:
and determining the first channel audio data as speaker channel audio data according to the speaker identification, and determining the second channel audio data as microphone channel audio data according to the microphone identification.
3. The method according to claim 1, wherein performing waveform mapping processing on the first channel audio data, the second channel audio data, and the processed second channel audio data to obtain a first waveform map corresponding to the first channel audio data, a second waveform map corresponding to the second channel audio data, and a third waveform map corresponding to the processed second channel audio data, respectively comprises:
sampling the first channel audio data, the second channel audio data and the processed second channel audio data to obtain first sampled audio data, second sampled audio data and third sampled audio data respectively;
and respectively drawing oscillograms for the first sampled audio data, the second sampled audio data and the third sampled audio data to obtain the first oscillogram, the second oscillogram and the third oscillogram.
4. The method of claim 1, further comprising:
acquiring single-channel audio data sent by a terminal;
sampling the single-channel audio data according to the frequency characteristics of the single-channel audio data to obtain sampled single-channel audio data;
and drawing a waveform diagram for the sampled single-channel audio data to obtain a fourth waveform diagram corresponding to the single-channel audio data.
5. The method of claim 1, further comprising, after performing waveform mapping processing on the first channel audio data, the second channel audio data, and the processed second channel audio data to obtain a first waveform map corresponding to the first channel audio data, a second waveform map corresponding to the second channel audio data, and a third waveform map corresponding to the processed second channel audio data, respectively:
displaying the first waveform diagram, the second waveform diagram and the third waveform diagram.
6. The method of any of claims 1-5, wherein displaying the first waveform map, the second waveform map, and the third waveform map comprises:
respectively displaying the first waveform diagram, the second waveform diagram and the third waveform diagram on different display windows;
or,
and displaying the first waveform diagram, the second waveform diagram and the third waveform diagram in an overlapped mode on the same window, wherein the first waveform diagram, the second waveform diagram and the third waveform diagram are different in marking mode.
7. An audio processing apparatus, comprising:
the first acquisition module is used for acquiring stereo audio data sent by a terminal;
the separation module is configured to separate the stereo audio data to obtain first channel audio data and second channel audio data, where the first channel audio data is speaker channel audio data, the second channel audio data is microphone channel audio data, and the second channel audio data is a superposition of the first channel audio data and actual sound data;
the removing module is used for removing echo data in the second channel audio data according to the first channel audio data to obtain processed second channel audio data, wherein the echo data is audio sent by a loudspeaker of the terminal;
and the first drawing module is used for respectively drawing the first channel audio data, the second channel audio data and the processed second channel audio data into a waveform diagram, so as to obtain a first waveform diagram corresponding to the first channel audio data, a second waveform diagram corresponding to the second channel audio data and a third waveform diagram corresponding to the processed second channel audio data.
8. The apparatus of claim 7, wherein the first channel audio data comprises a speaker identification and the second channel audio data comprises a microphone identification;
the device, still include:
a determining module, configured to determine, according to the speaker identifier, that the first channel audio data is speaker channel audio data before the separating module performs separation processing on the stereo audio data to obtain first channel audio data and second channel audio data, and determine, according to the microphone identifier, that the second channel audio data is microphone channel audio data.
9. The apparatus of claim 7, wherein the first rendering module comprises:
the sampling submodule is used for sampling the first channel audio data, the second channel audio data and the processed second channel audio data to respectively obtain first sampling audio data, second sampling audio data and third sampling audio data;
and the drawing submodule is used for drawing oscillograms for the first sampled audio data, the second sampled audio data and the third sampled audio data respectively to obtain the first oscillogram, the second oscillogram and the third oscillogram.
10. The apparatus of claim 7, further comprising:
the second acquisition module is used for acquiring single-channel audio data sent by the terminal;
the sampling module is used for sampling the single-channel audio data according to the frequency characteristics of the single-channel audio data to obtain the sampled single-channel audio data;
and the second drawing module is used for drawing a waveform diagram for the sampled single-channel audio data to obtain a fourth waveform diagram corresponding to the single-channel audio data.
11. The apparatus of claim 7, further comprising:
a display module, configured to display the first waveform diagram, the second waveform diagram, and the third waveform diagram after the first rendering module performs waveform diagram rendering processing on the first channel audio data, the second channel audio data, and the processed second channel audio data, respectively, to obtain a first waveform diagram corresponding to the first channel audio data, a second waveform diagram corresponding to the second channel audio data, and a third waveform diagram corresponding to the processed second channel audio data.
12. The apparatus according to any one of claims 7-11, wherein the display module is specifically configured to:
respectively displaying the first waveform diagram, the second waveform diagram and the third waveform diagram on different display windows;
or,
and displaying the first waveform diagram, the second waveform diagram and the third waveform diagram in an overlapped mode on the same window, wherein the first waveform diagram, the second waveform diagram and the third waveform diagram are different in marking mode.
13. A control device, characterized by a transmitter, a receiver, a memory and a processor;
the memory is to store computer instructions; the processor is configured to execute the computer instructions stored by the memory to implement the audio processing method of any of claims 1 to 6.
14. A storage medium, comprising: a readable storage medium and computer instructions stored in the readable storage medium; the computer instructions are for implementing the audio processing method of any of claims 1 to 6.
CN201811152719.1A 2018-09-29 2018-09-29 Audio processing method, device, equipment and storage medium Active CN109285556B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811152719.1A CN109285556B (en) 2018-09-29 2018-09-29 Audio processing method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811152719.1A CN109285556B (en) 2018-09-29 2018-09-29 Audio processing method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN109285556A CN109285556A (en) 2019-01-29
CN109285556B true CN109285556B (en) 2022-05-20

Family

ID=65182332

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811152719.1A Active CN109285556B (en) 2018-09-29 2018-09-29 Audio processing method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN109285556B (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110033784B (en) * 2019-04-10 2020-12-25 北京达佳互联信息技术有限公司 Audio quality detection method and device, electronic equipment and storage medium
CN110138991B (en) * 2019-06-21 2021-05-25 思必驰科技股份有限公司 Echo cancellation method and device
CN110503982B (en) * 2019-09-17 2024-03-22 腾讯科技（深圳）有限公司 Voice quality detection method and related device
CN111615035B (en) * 2020-05-22 2021-05-14 歌尔科技有限公司 Beam forming method, device, equipment and storage medium
CN111916083B (en) * 2020-08-20 2023-08-22 北京基智科技有限公司 Intelligent equipment voice instruction recognition algorithm through big data acquisition
CN112233697B (en) * 2020-12-09 2021-04-13 北京云测信息技术有限公司 Audio data detection method and device and audio data detection equipment
CN118592041A (en) * 2022-12-16 2024-09-03 北京小米移动软件有限公司 Audio acquisition analysis method and device

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105390142A (en) * 2015-12-17 2016-03-09 广州大学 Digital hearing aid voice noise elimination method
CN105448294A (en) * 2015-12-09 2016-03-30 江苏天安智联科技股份有限公司 Intelligent voice recognition system for vehicle equipment
CN105575397A (en) * 2014-10-08 2016-05-11 展讯通信（上海）有限公司 Voice noise reduction method and voice collection device
CN106910510A (en) * 2017-02-16 2017-06-30 智车优行科技（北京）有限公司 Vehicle-mounted power amplifying device, vehicle and its audio play handling method
CN107068164A (en) * 2017-05-25 2017-08-18 北京地平线信息技术有限公司 Acoustic signal processing method, device and electronic equipment
CN107785028A (en) * 2016-08-25 2018-03-09 上海英波声学工程技术股份有限公司 Voice de-noising method and device based on signal autocorrelation
CN108322859A (en) * 2018-02-05 2018-07-24 北京百度网讯科技有限公司 Equipment, method and computer readable storage medium for echo cancellor

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105575397A (en) * 2014-10-08 2016-05-11 展讯通信（上海）有限公司 Voice noise reduction method and voice collection device
CN105448294A (en) * 2015-12-09 2016-03-30 江苏天安智联科技股份有限公司 Intelligent voice recognition system for vehicle equipment
CN105390142A (en) * 2015-12-17 2016-03-09 广州大学 Digital hearing aid voice noise elimination method
CN107785028A (en) * 2016-08-25 2018-03-09 上海英波声学工程技术股份有限公司 Voice de-noising method and device based on signal autocorrelation
CN106910510A (en) * 2017-02-16 2017-06-30 智车优行科技（北京）有限公司 Vehicle-mounted power amplifying device, vehicle and its audio play handling method
CN107068164A (en) * 2017-05-25 2017-08-18 北京地平线信息技术有限公司 Acoustic signal processing method, device and electronic equipment
CN108322859A (en) * 2018-02-05 2018-07-24 北京百度网讯科技有限公司 Equipment, method and computer readable storage medium for echo cancellor

Also Published As

Publication number Publication date
CN109285556A (en) 2019-01-29

Similar Documents

Publication Publication Date Title
CN109285556B (en) Audio processing method, device, equipment and storage medium
US7567676B2 (en) Sound event detection and localization system using power analysis
CN113986187B (en) Audio region amplitude acquisition method and device, electronic equipment and storage medium
CN112017693B (en) Audio quality assessment method and device
AU2014413559A1 (en) A signal processing apparatus for enhancing a voice component within a multi-channel audio signal
CN106952654A (en) Robot noise-reduction method, device and robot
CN113259832B (en) Microphone array detection method and device, electronic equipment and storage medium
CN111355995A (en) Method and device for determining sound delay time of Bluetooth device and terminal device
CN111107284A (en) Real-time generation system and generation method for video subtitles
CN112382266B (en) Speech synthesis method, device, electronic equipment and storage medium
CN103299657B (en) Audio signal processing
US20200314580A1 (en) Method and apparatus for voice or sound activity detection for spatial audio
CN117095698A (en) Alarm sound identification method and device, electronic equipment and storage medium
CN114420100B (en) Voice detection method and device, electronic equipment and storage medium
KR101382356B1 (en) Apparatus for forgery detection of audio file
CN104835500A (en) Method and device for acquiring audio information
CN113542785B (en) Switching method for input and output of audio applied to live broadcast and live broadcast equipment
CN115243183A (en) Audio detection method, device and storage medium
CN112735481B (en) POP sound detection method and device, terminal equipment and storage medium
CN105577909A (en) Denoising method and device
CN112242150B (en) Method and system for detecting stereo
CN111933174B (en) Voice processing method, device, equipment and system
CN112542157B (en) Speech processing method, device, electronic equipment and computer readable storage medium
CN114093376A (en) Method and device for identifying audio data packaging format, storage medium and equipment
WO2019061192A1 (en) Audio processing method and related product

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
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20211018

Address after: 100176 101, floor 1, building 1, yard 7, Ruihe West 2nd Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing

Applicant after: Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd.

Address before: 100085 Baidu Building, 10 Shangdi Tenth Street, Haidian District, Beijing

Applicant before: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd.

GR01 Patent grant
GR01 Patent grant