WO2022037419A1 - 音频内容识别方法、装置、设备和计算机可读介质 - Google Patents

音频内容识别方法、装置、设备和计算机可读介质 Download PDF

Info

Publication number
WO2022037419A1
WO2022037419A1 PCT/CN2021/110849 CN2021110849W WO2022037419A1 WO 2022037419 A1 WO2022037419 A1 WO 2022037419A1 CN 2021110849 W CN2021110849 W CN 2021110849W WO 2022037419 A1 WO2022037419 A1 WO 2022037419A1
Authority
WO
WIPO (PCT)
Prior art keywords
speech
speech segment
segment
recognition
audio
Prior art date
Application number
PCT/CN2021/110849
Other languages
English (en)
French (fr)
Inventor
孔亚鲁
何怡
Original Assignee
北京字节跳动网络技术有限公司
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 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Publication of WO2022037419A1 publication Critical patent/WO2022037419A1/zh
Priority to US17/985,795 priority Critical patent/US11783808B2/en

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
    • G10L15/00—Speech recognition
    • G10L15/04—Segmentation; Word boundary detection
    • 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
    • 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
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/083—Recognition networks
    • 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
    • G10L15/00—Speech recognition
    • G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
    • 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
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • 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
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/233—Processing of audio elementary streams
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
    • H04N21/234336—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements by media transcoding, e.g. video is transformed into a slideshow of still pictures or audio is converted into text
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/439—Processing of audio elementary streams
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/439—Processing of audio elementary streams
    • H04N21/4394—Processing of audio elementary streams involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
    • H04N21/4402—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display
    • H04N21/440236—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display by media transcoding, e.g. video is transformed into a slideshow of still pictures, audio is converted into text
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/488—Data services, e.g. news ticker
    • H04N21/4884—Data services, e.g. news ticker for displaying subtitles
    • 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
    • G10L15/00—Speech recognition
    • G10L15/005—Language recognition
    • 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
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command
    • 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
    • G10L25/78—Detection of presence or absence of voice signals

Definitions

  • Embodiments of the present disclosure relate to the field of computer technology, and in particular, to an audio content identification method, apparatus, device, and computer-readable medium.
  • Some embodiments of the present disclosure propose an audio content recognition method, apparatus, device, and computer-readable medium to solve the technical problems mentioned in the above background section.
  • some embodiments of the present disclosure provide an audio content recognition method.
  • the method includes: segmenting audio to obtain a set of speech segments and a set of non-speech segments; and determining each speech segment in the above-mentioned speech segment set type and language information; for each speech segment in the above-mentioned speech segment set, based on the type and language information of the above-mentioned speech segment, perform speech recognition on the above-mentioned speech segment to obtain a first recognition result.
  • some embodiments of the present disclosure provide an apparatus for recognizing audio content.
  • the apparatus includes: a segmentation unit configured to segment audio to obtain a set of speech segments and a set of non-speech segments; a determination unit configured to to determine the type and language information of each speech segment in the above-mentioned speech segment set; the identification unit is configured to, for each speech segment in the above-mentioned speech segment set, based on the type and language information of the above-mentioned speech segment, to the above-mentioned speech segment Perform speech recognition to obtain a first recognition result.
  • some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device on which one or more programs are stored, when one or more programs are stored by one or more The processor executes such that the one or more processors implement a method as described in any implementation of the first aspect.
  • some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any implementation manner of the first aspect.
  • One of the above-mentioned embodiments of the present disclosure has the following beneficial effects: by separately identifying speech and music clips in the audio, both audio contents can be better identified. And, by separately recognizing the audio of different language content, the effect of speech recognition is further improved.
  • FIG. 1 is a schematic diagram of an application scenario of an audio content recognition method according to some embodiments of the present disclosure
  • FIG. 2 is a flowchart of some embodiments of audio content identification methods according to the present disclosure
  • FIG. 3 is a flow chart of other embodiments of audio content identification methods according to the present disclosure.
  • FIG. 4 is a schematic structural diagram of some embodiments of an audio content recognition apparatus according to the present disclosure.
  • FIG. 5 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure.
  • FIG. 1 shows a schematic diagram of an application scenario to which the audio content recognition method according to some embodiments of the present disclosure can be applied.
  • the computing device 101 may segment the audio 102 to obtain a voice segment set 103 and a non-speech segment set 104 .
  • the above audio includes three audio clips, which are labeled 1, 2, and 3 respectively.
  • the audio clips numbered 1 and 3 are speech clips.
  • the audio segment numbered 2 is a non-speech segment.
  • the type and language information of each speech segment in each speech segment set in the above-mentioned speech segment set 103 is determined.
  • the above types include speaking voice clips and singing voice clips.
  • the audio segment with the reference number 1 is a Chinese speaking voice segment, as indicated by the reference number 105 .
  • the above-mentioned audio segment numbered 3 is an English singing voice segment, as indicated by the reference number 106 .
  • the above-mentioned computing device 101 may perform speech recognition on the above-mentioned speech segments for each speech segment in the above-mentioned speech segment set 103 based on the type and language information 105 and 106 of the above-mentioned speech segments, and obtain a first recognition result 107.
  • the above computing device 101 may be hardware or software.
  • the computing device When the computing device is hardware, it can be implemented as a distributed cluster composed of multiple servers or electronic devices, or can be implemented as a single server or a single electronic device.
  • a computing device When a computing device is embodied in software, it can be implemented as multiple software or software modules, for example, to provide distributed services, or as a single software or software module. There is no specific limitation here.
  • computing devices 101 in FIG. 1 is merely illustrative. There may be any number of computing devices 101 depending on implementation needs.
  • the audio content identification method includes the following steps:
  • Step 201 Segment the audio to obtain a voice segment set and a non-voice segment set.
  • the executor of the audio content recognition method may segment the above audio by using speech recognition software or an online speech recognition tool to obtain a set of speech segments and non-speech segments gather.
  • the above-mentioned executive body may also use a VAD (Voice Activation Detection, voice activity detection) technology to segment the above-mentioned audio to obtain a voice segment set and a non-voice segment set.
  • VAD Voice Activation Detection, voice activity detection
  • the above-mentioned executive body may also input the above-mentioned pre-acquired audio into a pre-trained voice activity detection model to obtain the above-mentioned speech segment set and the above-mentioned non-speech segment set.
  • Step 202 Determine the type and language information of each speech segment in the above-mentioned speech segment set.
  • the above-mentioned types of speech segments may include at least one of laughter speech segments, natural-sound speech segments, and speaking speech segments.
  • the above-mentioned types of speech segments may include: at least one of onomatopoeia speech segments, speaking speech segments, and singing speech segments.
  • the executor of the audio content recognition method may determine the type and language information of each speech segment in the above-mentioned speech segment set by using speech recognition software or an online speech recognition tool.
  • the above-mentioned executive body may also use AED (Activity Event Detection, audio event detection) technology to determine the type of each speech segment in the above-mentioned speech segment set.
  • AED Activity Event Detection, audio event detection
  • LID Location Identification, language identification
  • the above-mentioned executive body may input the above-mentioned speech segment into a pre-trained audio event detection model to obtain the type of the above-mentioned speech segment; input the above-mentioned speech segment into a pre-trained audio event detection model; In the language recognition model of , the language information of the above speech segment is obtained.
  • Step 203 For each speech segment in the above-mentioned speech segment set, based on the type and language information of the above-mentioned speech segment, perform speech recognition on the above-mentioned speech segment to obtain a first recognition result.
  • the above-mentioned executive body may input speech fragments of different types and languages into different speech recognition software modules for recognition.
  • the above-mentioned execution body may also first, for each speech segment in the above-mentioned speech segment set, based on the type and language information of the above-mentioned speech segment, in a preset speech recognition model set , determine a speech recognition model for recognizing the above-mentioned speech segment. After that, the above-mentioned speech segment is input into a speech recognition model for recognizing the above-mentioned speech segment to obtain a first recognition result.
  • the methods provided by some embodiments of the present disclosure enable better recognition effects for both audio contents by using different models to recognize speech and music segments in the audio. And, by using different models for audio of different language content, the effect of speech recognition is further improved.
  • the process 300 of the audio content identification method includes the following steps:
  • Step 301 Segment the audio to obtain a voice segment set and a non-voice segment set.
  • Step 302 Determine the type and language information of each speech segment in the above-mentioned speech segment set.
  • Step 303 For each speech segment in the above-mentioned speech segment set, based on the type and language information of the above-mentioned speech segment, perform speech recognition on the above-mentioned speech segment to obtain a first recognition result.
  • steps 301-303 for the specific implementation of steps 301-303 and the technical effects brought about by them, reference may be made to steps 201-203 in the embodiment corresponding to FIG. 2, and details are not repeated here.
  • Step 304 Determine the label of each non-speech segment in the above-mentioned non-speech segment set.
  • the above-mentioned executive body may determine the label of each non-speech segment in the above-mentioned non-speech segment set by using audio recognition software or an online audio recognition tool.
  • the above-mentioned executive body may further determine the label of each non-speech segment in the above-mentioned non-speech segment set by using an audio event detection network.
  • Step 305 Segment the first recognition result and the label to obtain a second recognition result.
  • the above-mentioned first recognition result and the above-mentioned label constitute the text to be segmented according to the appearance time of the corresponding audio segment in the audio.
  • the execution subject may use sentence segmentation software or an online sentence segmentation tool to perform sentence segmentation on the first recognition result and the label.
  • the above-mentioned execution body may further segment the above-mentioned first recognition result and the above-mentioned label by using a sentence-sentence network.
  • the above-mentioned execution body may further segment the above-mentioned first recognition result and the above-mentioned label by receiving manual input.
  • Step 306 Add each clause in the second recognition result to the video frame corresponding to the target video to obtain a video with subtitles.
  • each sentence in the second recognition result corresponds to at least one video frame in the target video according to the start time and end time of the corresponding audio segment in the audio.
  • the process 300 of the audio content recognition method in some embodiments corresponding to FIG. 2 is the steps of segmenting and adding the second recognition result to the video.
  • the solutions described in these embodiments can make the generated subtitles contain tags of non-speech segments.
  • the audio recognition result can be better displayed in the video. In general, the user's video viewing experience is further improved.
  • the present disclosure provides some embodiments of an audio content recognition apparatus, these apparatus embodiments correspond to those method embodiments shown in FIG. 2 , the apparatus Specifically, it can be applied to various electronic devices.
  • the audio content identification apparatus 400 in some embodiments includes: a segmentation unit 401 , a first determination unit 402 , and an identification unit 403 .
  • the segmenting unit 401 is configured to segment the audio to obtain a set of speech segments and a set of non-speech segments;
  • the first determining unit 402 is configured to determine the type and language of each speech segment in the above-mentioned speech segment set information;
  • the identification unit 403 is configured to perform speech recognition on the speech segment based on the type and language information of the speech segment for each speech segment in the speech segment set to obtain a first recognition result.
  • the apparatus 400 further includes: a second determining unit, configured to determine the label of each non-speech segment in the above-mentioned non-speech segment set; The first recognition result is segmented with the above label to obtain a second recognition result.
  • the apparatus 400 further includes: an adding unit, configured to add each sentence in the second recognition result to a video frame corresponding to the target video to obtain a video with subtitles .
  • the segmentation unit 401 is further configured to: input the above-mentioned pre-acquired audio into a pre-trained voice activity detection model to obtain the above-mentioned speech segment set and the above-mentioned non-speech segment set .
  • the types of the above speech segments include: at least one of onomatopoeia speech segments, speaking speech segments, and singing speech segments.
  • the first determining unit 402 is further configured to: input the above-mentioned speech segment into a pre-trained audio event detection model to obtain the type of the above-mentioned speech segment; input the above-mentioned speech segment into a In the pre-trained language recognition model, language information of the above-mentioned speech segment is obtained.
  • the recognition unit 403 is further configured to: for each speech segment in the above-mentioned speech segment set, based on the type and language information of the above-mentioned speech segment, in a preset speech recognition model set , determining a speech recognition model for recognizing the above-mentioned speech segment; inputting the above-mentioned speech segment into the speech recognition model for recognizing the above-mentioned speech segment to obtain a first recognition result.
  • the second determining unit is further configured to: input each non-speech segment in the above-mentioned non-speech segment set into a pre-trained sound event detection model to obtain the above-mentioned non-speech segment Tag of.
  • the units recorded in the apparatus 400 correspond to the respective steps in the method described with reference to FIG. 2 . Therefore, the operations, features, and beneficial effects described above with respect to the method are also applicable to the apparatus 400 and the units included therein, and details are not described herein again.
  • FIG. 5 it shows a schematic structural diagram of an electronic device (eg, the server or terminal device in FIG. 1 ) 500 suitable for implementing some embodiments of the present disclosure.
  • Electronic devices in some embodiments of the present disclosure may include, but are not limited to, such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals Mobile terminals such as in-vehicle navigation terminals, etc., and stationary terminals such as digital TVs, desktop computers, and the like.
  • the electronic device shown in FIG. 5 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.
  • an electronic device 500 may include a processing device (eg, a central processing unit, a graphics processor, etc.) 501 that may be loaded into random access according to a program stored in a read only memory (ROM) 502 or from a storage device 508 Various appropriate actions and processes are executed by the programs in the memory (RAM) 503 . In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored.
  • the processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504.
  • An input/output (I/O) interface 505 is also connected to bus 504 .
  • the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration An output device 507 such as a computer; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509 .
  • Communication means 509 may allow electronic device 500 to communicate wirelessly or by wire with other devices to exchange data. While FIG. 5 shows electronic device 500 having various means, it should be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in FIG. 5 can represent one device, and can also represent multiple devices as required.
  • the processes described above with reference to the flowcharts may be implemented as computer software programs.
  • some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from a network via communication device 509, or from storage device 508, or from ROM 502.
  • the processing device 501 When the computer program is executed by the processing device 501, the above-mentioned functions defined in the methods of some embodiments of the present disclosure are performed.
  • the computer-readable medium described in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, electrical wire, optical fiber cable, RF (radio frequency), etc., or any suitable combination of the foregoing.
  • the client and server can use any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol) to communicate, and can communicate with digital data in any form or medium Communication (eg, a communication network) interconnects.
  • HTTP HyperText Transfer Protocol
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (eg, the Internet), and peer-to-peer networks (eg, ad hoc peer-to-peer networks), as well as any currently known or future development network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device is made to: segment the audio to obtain a voice segment set and a non-voice segment set; determine the above Type and language information of each speech segment in the speech segment set; for each speech segment in the above-mentioned speech segment set, based on the type and language information of the above-mentioned speech segment, perform speech recognition on the above-mentioned speech segment, and obtain a first recognition result .
  • Computer program code for carrying out operations of some embodiments of the present disclosure may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, or a combination thereof , as well as conventional procedural programming languages - such as "C" or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider to via Internet connection).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.
  • the units described in some embodiments of the present disclosure may be implemented by means of software, and may also be implemented by means of hardware.
  • the described unit can also be set in the processor, for example, it can be described as: a processor includes a segmentation unit, a determination unit, and an identification unit. Wherein, the names of these units do not constitute a limitation of the unit itself under certain circumstances, for example, the segmentation unit may also be described as a "unit of audio segmentation".
  • exemplary types of hardware logic components include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), Systems on Chips (SOCs), Complex Programmable Logical Devices (CPLDs) and more.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs Systems on Chips
  • CPLDs Complex Programmable Logical Devices
  • an audio content recognition method including: segmenting audio to obtain a set of speech segments and a set of non-speech segments; Type and language information; for each speech segment in the above-mentioned speech segment set, based on the type and language information of the above-mentioned speech segment, perform speech recognition on the above-mentioned speech segment to obtain a first recognition result.
  • the method further includes: determining a label of each non-speech segment in the non-speech segment set; segmenting the first recognition result and the label to obtain a second recognition result .
  • the above method further includes: adding each clause in the above second recognition result to a video frame corresponding to the target video to obtain a video with subtitles.
  • the above-mentioned segmentation of the pre-acquired audio to obtain a voice segment set and a non-voice segment set includes: inputting the pre-acquired audio into a pre-trained voice activity detector In the model, the above-mentioned speech segment set and the above-mentioned non-speech segment set are obtained.
  • the types of the above-mentioned speech segments include: at least one of onomatopoeia speech segments, speaking speech segments, and singing speech segments.
  • the above-mentioned determining the type and language information of each speech segment in the above-mentioned speech segment set includes: inputting the above-mentioned speech segment into a pre-trained audio event detection model to obtain the above-mentioned speech The type of the segment; the above-mentioned speech segment is input into the pre-trained language recognition model, and the language information of the above-mentioned speech segment is obtained.
  • the speech recognition is performed on the above-mentioned speech segment, and the first recognition result is obtained, including: For each speech segment in the above-mentioned speech segment set, based on the type and language information of the above-mentioned speech segment, in the preset speech recognition model set, determine a speech recognition model for recognizing the above-mentioned speech segment; input the above-mentioned speech segment into into the speech recognition model for recognizing the above-mentioned speech segment to obtain the first recognition result.
  • determining the label of each non-speech segment in the non-speech segment set includes: inputting each non-speech segment in the non-speech segment set into a pre-trained voice In the event detection model, the labels of the above non-speech segments are obtained.
  • an apparatus for recognizing audio content comprising: a segmentation unit configured to segment audio to obtain a set of speech segments and a set of non-speech segments; a determination unit configured to to determine the type and language information of each speech segment in the above-mentioned speech segment set; the identification unit is configured to, for each speech segment in the above-mentioned speech segment set, based on the type and language information of the above-mentioned speech segment, to the above-mentioned speech segment Perform speech recognition to obtain a first recognition result.
  • the apparatus further includes: a second determining unit configured to determine the label of each non-speech segment in the above-mentioned non-speech segment set; The recognition result is segmented with the above label to obtain a second recognition result.
  • the apparatus further includes: an adding unit configured to add each clause in the second recognition result to a video frame corresponding to the target video to obtain a video with subtitles.
  • the segmentation unit is further configured to: input the pre-acquired audio into a pre-trained voice activity detection model to obtain the above-mentioned speech segment set and the above-mentioned non-speech segment set.
  • the types of the above-mentioned speech segments include: at least one of onomatopoeia speech segments, speaking speech segments, and singing speech segments.
  • the first determining unit is further configured to: input the above-mentioned speech segment into a pre-trained audio event detection model to obtain the type of the above-mentioned speech segment; input the above-mentioned speech segment into a pre-trained audio event detection model; In the trained language recognition model, language information of the above speech segment is obtained.
  • the recognition unit is further configured to: for each speech segment in the above-mentioned speech segment set, based on the type and language information of the above-mentioned speech segment, in a preset speech recognition model set , determining a speech recognition model for recognizing the above-mentioned speech segment; inputting the above-mentioned speech segment into the speech recognition model for recognizing the above-mentioned speech segment to obtain a first recognition result.
  • the second determining unit is further configured to: input each non-speech segment in the above-mentioned non-speech segment set into a pre-trained sound event detection model to obtain the above-mentioned non-speech segment Tag of.
  • an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, when the one or more programs are stored by one or more The processors execute such that one or more processors implement a method as in any of the above.
  • a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements any of the methods described above.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Signal Processing (AREA)
  • Machine Translation (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

音频内容识别方法、装置（400）、电子设备（500）和计算机可读介质。方法包括：对音频（102）进行切分，得到语音片段集合（103）和非语音片段集合（104）（201,301）；确定语音片段集合（103）中的每个语音片段的类型和语种信息（105,106）（202,302）；对于语音片段集合（103）中的每个语音片段，基于语音片段的类型和语种信息（105,106），对语音片段进行语音识别，得到第一识别结果（203,303）。通过将音频（102）中的说话和音乐片段用不同的模型进行识别，使两种音频（102）内容都能得到更好的识别效果。以及，通过使用不同的模型识别不同语种内容的音频（102），进一步提升了语音识别的效果。

Description

音频内容识别方法、装置、设备和计算机可读介质
相关申请的交叉引用
本申请基于申请号为202010829371.6、申请日为2020年08月18日，名称为“音频内容识别方法、装置、设备和计算机可读介质”的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本公开的实施例涉及计算机技术领域，具体涉及音频内容识别方法、装置、设备和计算机可读介质。
背景技术
为了提升用户观看视频的体验，需要为视频添加字幕。人工添加字幕成本高且效率有限。而现有的自动添加字幕技术，在音频中有多种内容时准确率不能得到保证。其中，音频中的多种内容例如歌声、说话声、咳嗽声、笑声、关门声等。以及，难以应对存在多语种语音片段的音频。
发明内容
本公开的内容部分用于以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。本公开的内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
本公开的一些实施例提出了音频内容识别方法、装置、设备和计算机可读介质，来解决以上背景技术部分提到的技术问题。
第一方面，本公开的一些实施例提供了一种音频内容识别方法，该方法包括：对音频进行切分，得到语音片段集合和非语音片段集合；确定上述语音片段集合中的每个语音片段的类型和语种信息；对于上述语音片段集合中的每个语音片段，基于上述语音片段的类型和语种信息，对上述语音片段进行语音识别，得到第一识别结果。
第二方面，本公开的一些实施例提供了一种音频内容识别装置，装置包括：切分单元，被配置成对音频进行切分，得到语音片段集合和非语音片段集合；确定单元，被配置成确定上述语音片段集合中的每个语音片段的类型和语种信息；识别单元，被配置成对于上述语音片段集合中的每个语音片段，基于上述语音片段的类型和语种信息，对上述语音片段进行语音识别，得到第一识别结果。
第三方面，本公开的一些实施例提供了一种电子设备，包括：一个或多个处理器；存储装置，其上存储有一个或多个程序，当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现如第一方面中任一实现方式描述的方法。
第四方面，本公开的一些实施例提供了一种计算机可读介质，其上存储有计算机程序，其中，程序被处理器执行时实现如第一方面中任一实现方式描述的方法。
本公开的上述各个实施例中的一个实施例具有如下有益效果：通过将音频中的说话和音乐片段分别进行识别，使两种音频内容都能得到更好的识别效果。以及，通过对不同语种内容的音频分别进行识别，进一步提升了语音识别的效果。
附图说明
结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，原件和元素不一定按照比例绘制。
图1是本公开的一些实施例的音频内容识别方法的一个应用场景的示意图；
图2是根据本公开的音频内容识别方法的一些实施例的流程图；
图3是根据本公开的音频内容识别方法的另一些实施例的流程图；
图4是根据本公开的音频内容识别装置的一些实施例的结构示意图；
图5是适于用来实现本公开的一些实施例的电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例。相反，提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。在不冲突的情况下，本公开中的实施例及实施例中的特征可以相互组合。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
下面将参考附图并结合实施例来详细说明本公开。
图1示出了可以应用本公开的一些实施例的音频内容识别方法的一个应用场景的示意图。
在图1所示的应用场景中，首先，计算设备101可以对音频102进行切分，得到语音片段集合103和非语音片段集合104。在本应用场景中，上述音频包含三段音频片段，分别标号为1、2、3。其中，标号为1和3的音频片段为语音片段。标号为2的音频片段为非语音片段。之后，确定上述语音片段集合103中的每个语音片段集合中的每个语音片段的类型和语种信息。在本应用场景中，上述类型包括说话语音片段和唱歌语音片段。其中，上述标号为1的音频片段为中文说话语音片段，如附图标记105所示。上述标号为3的音频片段为英文唱歌语音片段，如附图标记106所示。最后，上述计算设备101可以对于上述语音片段集合103中的每个语音片段，基于上述语音片段的类型和语种信息105、106，对上述语音片段进行 语音识别，得到第一识别结果107。
需要说明的是，上述计算设备101可以是硬件，也可以是软件。当计算设备为硬件时，可以实现成多个服务器或电子设备组成的分布式集群，也可以实现成单个服务器或单个电子设备。当计算设备体现为软件时，可以实现成例如用来提供分布式服务的多个软件或软件模块，也可以实现成单个软件或软件模块。在此不做具体限定。
应该理解，图1中的计算设备101的数目仅仅是示意性的。根据实现需要，可以具有任意数目的计算设备101。
继续参考图2，示出了根据本公开的音频内容识别方法的一些实施例的流程200。该音频内容识别方法，包括以下步骤：
步骤201，对音频进行切分，得到语音片段集合和非语音片段集合。
在一些实施例中，音频内容识别方法的执行主体(例如图1所示的计算设备)可以通过使用语音识别软件或者线上语音识别工具对上述音频进行切分，得到语音片段集合和非语音片段集合。
在一些实施例中，上述执行主体还可以使用VAD(Voice Activation Detection，语音活性检测)技术，对上述音频进行切分，得到语音片段集合和非语音片段集合。
在一些实施例的一些可选的实现方式中，上述执行主体还可以将上述预先获取到的音频输入到预先训练好的语音活性检测模型中，得到上述语音片段集合和上述非语音片段集合。
步骤202，确定上述语音片段集合中的每个语音片段的类型和语种信息。
在一些实施例中，上述语音片段的类型可以包括：笑声语音片段、自然声语音片段、说话语音片段中的至少一项。
在一些实施例的一些可选的实现方式中，上述语音片段的类型可以包括：拟声语音片段、说话语音片段和唱歌语音片段中的至少一项。
在一些实施例中，音频内容识别方法的执行主体可以通过使用语音识别软件或者线上语音识别工具确定上述语音片段集合中的每个语音片段的类型和语种信息。
在一些实施例中，上述执行主体还可以使用AED(Activity Event Detection，音频事件检测)技术确定上述语音片段集合中的每个语音片段的类型。使用LID(Language Identification，语言识别)技术，确定上述语音片段集合中的每个语音片段的语种信息。
在一些实施例的一些可选的实现方式中，上述执行主体可以将将上述语音片段输入到预先训练好的音频事件检测模型中，得到上述语音片段的类型；将上述语音片段输入到预先训练好的语种识别模型中，得到上述语音片段的语种信息。
步骤203，对于上述语音片段集合中的每个语音片段，基于上述语音片段的类型和语种信息，对上述语音片段进行语音识别，得到第一识别结果。
在一些实施例中，上述执行主体可以将不同类型和语种的语音片段输入到不同的语音识别软件模块中进行识别。
在一些实施例的一些可选的实现方式中，上述执行主体还可以首先对于上述语音片段集合中的每个语音片段，基于上述语音片段的类型和语种信息，在预先设定的语音识别模型集合中，确定用于识别上述语音片段的语音识别模型。之后，将上述语音片段输入到用于识别上述语音片段的语音识别模型中，得到第一识别结果。
本公开的一些实施例提供的方法通过将音频中的说话和音乐片段用不同的模型进行识别，使两种音频内容都能得到更好的识别效果。以及，通过使用不同的模型是被不同语种内容的音频，进一步提升了语音识别的效果。
进一步参考图3，其示出了音频内容识别方法的另一些实施例的流程300。该音频内容识别方法的流程300，包括以下步骤：
步骤301，对音频进行切分，得到语音片段集合和非语音片段集合。
步骤302，确定上述语音片段集合中的每个语音片段的类型和语种信息。
步骤303，对于上述语音片段集合中的每个语音片段，基于上述语音片段的类型和语种信息，对上述语音片段进行语音识别，得到第一识别结 果。
在一些实施例中，步骤301-303的具体实现及其所带来的技术效果，可以参考图2对应的实施例中的步骤201-203，在此不再赘述。
步骤304，确定上述非语音片段集合中的每个非语音片段的标签。
在一些实施例中，上述执行主体可以通过使用音频识别软件或者线上音频识别工具，确定上述非语音片段集合中的每个非语音片段的标签。
在一些实施例中，上述执行主体还可以通过使用音频事件检测网络，确定上述非语音片段集合中的每个非语音片段的标签。
步骤305，对上述第一识别结果和上述标签进行分句，得到第二识别结果。
在一些实施例中，上述第一识别结果和上述标签按照对应的音频片段在音频中的出现时间构成待分句文本。
在一些实施例中，上述执行主体可以通过使用分句软件或者线上分句工具，对上述第一识别结果和上述标签进行分句。
在一些实施例中，上述执行主体还可以通过使用分句网络，对上述第一识别结果和上述标签进行分句。
在一些实施例中，上述执行主体还可以通过接收人工输入，对上述第一识别结果和上述标签进行分句。
步骤306，将上述第二识别结果中的每个分句添加到目标视频对应的视频帧中，得到带有字幕的视频。
在一些实施例中，上述第二识别结果中的每个分句按照对应的音频片段在音频中的起始时间和结束时间与上述目标视频中的至少一个视频帧对应。
从图3中可以看出，与图2对应的一些实施例的描述相比，图3对应的一些实施例中的音频内容识别方法的流程300体现了确定非语音片段的标签、对第一识别结果和标签进行分句和将第二识别结果添加到视频中的步骤。由此，这些实施例描述的方案可以使生成的字幕中含有非语音片段的标签。以及，通过对第一识别结果和标签进行分句，使音频识别的结果可以更好的展示在视频中。总体上进一步提高了用户观看视频的体验。
进一步参考图4，作为对上述各图所示方法的实现，本公开提供了一种音频内容识别装置的一些实施例，这些装置实施例与图2所示的那些方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图4所示，一些实施例的音频内容识别装置400包括：切分单元401、第一确定单元402、识别单元403。其中，切分单元401，被配置成对音频进行切分，得到语音片段集合和非语音片段集合；第一确定单元402，被配置成确定上述语音片段集合中的每个语音片段的类型和语种信息；识别单元403，被配置成对于上述语音片段集合中的每个语音片段，基于上述语音片段的类型和语种信息，对上述语音片段进行语音识别，得到第一识别结果。
在一些实施例的可选实现方式中，装置400还包括：第二确定单元，被配置成确定上述非语音片段集合中的每个非语音片段的标签；分句单元，被配置成对上述第一识别结果和上述标签进行分句，得到第二识别结果。
在一些实施例的可选实现方式中，装置400还包括：添加单元，被配置成将上述第二识别结果中的每个分句添加到目标视频对应的视频帧中，得到带有字幕的视频。
在一些实施例的可选实现方式中，切分单元401进一步被配置成：将上述预先获取到的音频输入到预先训练好的语音活性检测模型中，得到上述语音片段集合和上述非语音片段集合。
在一些实施例的可选实现方式中，上述语音片段的类型包括：拟声语音片段、说话语音片段和唱歌语音片段中的至少一项。
在一些实施例的可选实现方式中，第一确定单元402进一步被配置成：将上述语音片段输入到预先训练好的音频事件检测模型中，得到上述语音片段的类型；将上述语音片段输入到预先训练好的语种识别模型中，得到上述语音片段的语种信息。
在一些实施例的可选实现方式中，识别单元403进一步被配置成：对于上述语音片段集合中的每个语音片段，基于上述语音片段的类型和语种信息，在预先设定的语音识别模型集合中，确定用于识别上述语音片段的语音识别模型；将上述语音片段输入到用于识别上述语音片段的语音识别 模型中，得到第一识别结果。
在一些实施例的可选实现方式中，第二确定单元进一步被配置成：将上述非语音片段集合中的每个非语音片段输入到预先训练好的声音事件检测模型中，得到上述非语音片段的标签。
可以理解的是，该装置400中记载的诸单元与参考图2描述的方法中的各个步骤相对应。由此，上文针对方法描述的操作、特征以及产生的有益效果同样适用于装置400及其中包含的单元，在此不再赘述。
下面参考图5，其示出了适于用来实现本公开的一些实施例的电子设备(例如图1中的服务器或终端设备)500的结构示意图。本公开的一些实施例中的电子设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图5示出的电子设备仅仅是一个示例，不应对本公开的实施例的功能和使用范围带来任何限制。
如图5所示，电子设备500可以包括处理装置(例如中央处理器、图形处理器等)501，其可以根据存储在只读存储器(ROM)502中的程序或者从存储装置508加载到随机访问存储器(RAM)503中的程序而执行各种适当的动作和处理。在RAM 503中，还存储有电子设备500操作所需的各种程序和数据。处理装置501、ROM 502以及RAM 503通过总线504彼此相连。输入/输出(I/O)接口505也连接至总线504。
通常，以下装置可以连接至I/O接口505：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置506；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置507；包括例如磁带、硬盘等的存储装置508；以及通信装置509。通信装置509可以允许电子设备500与其他设备进行无线或有线通信以交换数据。虽然图5示出了具有各种装置的电子设备500，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。图5中示出的每个方框可以代表一个装置，也可以根据需要代表多个装置。
特别地，根据本公开的一些实施例，上文参考流程图描述的过程可以 被实现为计算机软件程序。例如，本公开的一些实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的一些实施例中，该计算机程序可以通过通信装置509从网络上被下载和安装，或者从存储装置508被安装，或者从ROM 502被安装。在该计算机程序被处理装置501执行时，执行本公开的一些实施例的方法中限定的上述功能。
需要说明的是，本公开的一些实施例所述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开的一些实施例中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开的一些实施例中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(HyperText Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)， 以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：对音频进行切分，得到语音片段集合和非语音片段集合；确定上述语音片段集合中的每个语音片段的类型和语种信息；对于上述语音片段集合中的每个语音片段，基于上述语音片段的类型和语种信息，对上述语音片段进行语音识别，得到第一识别结果。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的一些实施例的操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)——连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开的一些实施例中的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器包括切分单元、确定单元、识别单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，切分单元还可以被描述为“切分音频的单元”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
根据本公开的一个或多个实施例，提供了一种音频内容识别方法，包括：对音频进行切分，得到语音片段集合和非语音片段集合；确定上述语音片段集合中的每个语音片段的类型和语种信息；对于上述语音片段集合中的每个语音片段，基于上述语音片段的类型和语种信息，对上述语音片段进行语音识别，得到第一识别结果。
根据本公开的一个或多个实施例，上述方法还包括：确定上述非语音片段集合中的每个非语音片段的标签；对上述第一识别结果和上述标签进行分句，得到第二识别结果。
根据本公开的一个或多个实施例，上述方法还包括：将上述第二识别结果中的每个分句添加到目标视频对应的视频帧中，得到带有字幕的视频。
根据本公开的一个或多个实施例，上述对预先获取到的音频进行切分，得到语音片段集合和非语音片段集合，包括：将上述预先获取到的音频输入到预先训练好的语音活性检测模型中，得到上述语音片段集合和上述非语音片段集合。
根据本公开的一个或多个实施例，上述语音片段的类型包括：拟声语音片段、说话语音片段和唱歌语音片段中的至少一项。
根据本公开的一个或多个实施例，上述确定上述语音片段集合中的每个语音片段的类型和语种信息，包括：将上述语音片段输入到预先训练好的音频事件检测模型中，得到上述语音片段的类型；将上述语音片段输入到预先训练好的语种识别模型中，得到上述语音片段的语种信息。
根据本公开的一个或多个实施例，上述对于上述语音片段集合中的每 个语音片段，基于上述语音片段的类型和语种信息，对上述语音片段进行语音识别，得到第一识别结果，包括：对于上述语音片段集合中的每个语音片段，基于上述语音片段的类型和语种信息，在预先设定的语音识别模型集合中，确定用于识别上述语音片段的语音识别模型；将上述语音片段输入到用于识别上述语音片段的语音识别模型中，得到第一识别结果。
根据本公开的一个或多个实施例，上述确定上述非语音片段集合中的每个非语音片段的标签，包括：将上述非语音片段集合中的每个非语音片段输入到预先训练好的声音事件检测模型中，得到上述非语音片段的标签。
根据本公开的一个或多个实施例，提供了一种音频内容识别装置，包括：切分单元，被配置成对音频进行切分，得到语音片段集合和非语音片段集合；确定单元，被配置成确定上述语音片段集合中的每个语音片段的类型和语种信息；识别单元，被配置成对于上述语音片段集合中的每个语音片段，基于上述语音片段的类型和语种信息，对上述语音片段进行语音识别，得到第一识别结果。
根据本公开的一个或多个实施例，装置还包括：第二确定单元，被配置成确定上述非语音片段集合中的每个非语音片段的标签；分句单元，被配置成对上述第一识别结果和上述标签进行分句，得到第二识别结果。
根据本公开的一个或多个实施例，装置还包括：添加单元，被配置成将上述第二识别结果中的每个分句添加到目标视频对应的视频帧中，得到带有字幕的视频。
根据本公开的一个或多个实施例，切分单元进一步被配置成：将上述预先获取到的音频输入到预先训练好的语音活性检测模型中，得到上述语音片段集合和上述非语音片段集合。
根据本公开的一个或多个实施例，上述语音片段的类型包括：拟声语音片段、说话语音片段和唱歌语音片段中的至少一项。
根据本公开的一个或多个实施例，第一确定单元进一步被配置成：将上述语音片段输入到预先训练好的音频事件检测模型中，得到上述语音片段的类型；将上述语音片段输入到预先训练好的语种识别模型中，得到上述语音片段的语种信息。
根据本公开的一个或多个实施例，识别单元进一步被配置成：对于上述语音片段集合中的每个语音片段，基于上述语音片段的类型和语种信息，在预先设定的语音识别模型集合中，确定用于识别上述语音片段的语音识别模型；将上述语音片段输入到用于识别上述语音片段的语音识别模型中，得到第一识别结果。
根据本公开的一个或多个实施例，第二确定单元进一步被配置成：将上述非语音片段集合中的每个非语音片段输入到预先训练好的声音事件检测模型中，得到上述非语音片段的标签。
根据本公开的一个或多个实施例，提供了一种电子设备，包括：一个或多个处理器；存储装置，其上存储有一个或多个程序，当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现如上述任一的方法。
根据本公开的一个或多个实施例，提供了一种计算机可读介质，其上存储有计算机程序，其中，程序被处理器执行时实现如上述任一的方法。
以上描述仅为本公开的一些较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开的实施例中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开的实施例中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (11)

  1. 一种音频内容识别方法，包括：
    对音频进行切分，得到语音片段集合和非语音片段集合；
    确定所述语音片段集合中的每个语音片段的类型和语种信息；
    对于所述语音片段集合中的每个语音片段，基于所述语音片段的类型和语种信息，对所述语音片段进行语音识别，得到第一识别结果。
  2. 根据权利要求1所述的方法，其中，所述方法还包括：
    确定所述非语音片段集合中的每个非语音片段的标签；
    对所述第一识别结果和所述标签进行分句，得到第二识别结果。
  3. 根据权利要求2所述的方法，其中，所述方法还包括：
    将所述第二识别结果中的每个分句添加到目标视频对应的视频帧中，得到带有字幕的视频。
  4. 根据权利要求1所述的方法，其中，所述对预先获取到的音频进行切分，得到语音片段集合和非语音片段集合，包括：
    将所述预先获取到的音频输入到预先训练好的语音活性检测模型中，得到所述语音片段集合和所述非语音片段集合。
  5. 根据权利要求1所述的方法，其中，所述语音片段的类型包括：
    拟声语音片段、说话语音片段和唱歌语音片段中的至少一项。
  6. 根据权利要求1所述的方法，其中，所述确定所述语音片段集合中的每个语音片段的类型和语种信息，包括：
    将所述语音片段输入到预先训练好的音频事件检测模型中，得到所述语音片段的类型；
    将所述语音片段输入到预先训练好的语种识别模型中，得到所述语音片段的语种信息。
  7. 根据权利要求1所述的方法，其中，所述对于所述语音片段集合中的每个语音片段，基于所述语音片段的类型和语种信息，对所述语音片段进行语音识别，得到第一识别结果，包括：
    对于所述语音片段集合中的每个语音片段，基于所述语音片段的类型和语种信息，在预先设定的语音识别模型集合中，确定用于识别所述语音片段的语音识别模型；
    将所述语音片段输入到用于识别所述语音片段的语音识别模型中，得到第一识别结果。
  8. 根据权利要求2所述的方法，其中，所述确定所述非语音片段集合中的每个非语音片段的标签，包括：
    将所述非语音片段集合中的每个非语音片段输入到预先训练好的声音事件检测模型中，得到所述非语音片段的标签。
  9. 一种音频内容识别装置，包括：
    切分单元，被配置成对音频进行切分，得到语音片段集合和非语音片段集合；
    第一确定单元，被配置成确定所述语音片段集合中的每个语音片段的类型和语种信息；
    识别单元，被配置成对于所述语音片段集合中的每个语音片段，基于所述语音片段的类型和语种信息，对所述语音片段进行语音识别，得到第一识别结果。
  10. 一种电子设备，包括：
    一个或多个处理器；
    存储装置，其上存储有一个或多个程序，
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-8中任一所述的方法。
  11. 一种计算机可读介质，其上存储有计算机程序，其中，所述程序被处理器执行时实现如权利要求1-8中任一所述的方法。
PCT/CN2021/110849 2020-08-18 2021-08-05 音频内容识别方法、装置、设备和计算机可读介质 WO2022037419A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/985,795 US11783808B2 (en) 2020-08-18 2022-11-11 Audio content recognition method and apparatus, and device and computer-readable medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010829371.6A CN111986655B (zh) 2020-08-18 2020-08-18 音频内容识别方法、装置、设备和计算机可读介质
CN202010829371.6 2020-08-18

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/985,795 Continuation US11783808B2 (en) 2020-08-18 2022-11-11 Audio content recognition method and apparatus, and device and computer-readable medium

Publications (1)

Publication Number Publication Date
WO2022037419A1 true WO2022037419A1 (zh) 2022-02-24

Family

ID=73434644

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/110849 WO2022037419A1 (zh) 2020-08-18 2021-08-05 音频内容识别方法、装置、设备和计算机可读介质

Country Status (3)

Country Link
US (1) US11783808B2 (zh)
CN (1) CN111986655B (zh)
WO (1) WO2022037419A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111986655B (zh) 2020-08-18 2022-04-01 北京字节跳动网络技术有限公司 音频内容识别方法、装置、设备和计算机可读介质
CN112614514B (zh) * 2020-12-15 2024-02-13 中国科学技术大学 有效语音片段检测方法、相关设备及可读存储介质
CN113808615B (zh) * 2021-08-31 2023-08-11 北京字跳网络技术有限公司 音频类别定位方法、装置、电子设备和存储介质
CN115376490B (zh) * 2022-08-19 2024-07-30 北京字跳网络技术有限公司 一种语音识别方法、装置及电子设备
CN115602154B (zh) * 2022-12-15 2023-08-11 杭州网易云音乐科技有限公司 音频识别方法、装置、存储介质和计算设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010091675A (ja) * 2008-10-06 2010-04-22 Mitsubishi Electric Corp 音声認識装置
CN102881309A (zh) * 2012-09-24 2013-01-16 广东欧珀移动通信有限公司 歌词文件生成、校对方法及装置
CN105845129A (zh) * 2016-03-25 2016-08-10 乐视控股（北京）有限公司 一种在音频中切分句子的方法和系统及视频文件的字幕自动生成方法和系统
CN106878805A (zh) * 2017-02-06 2017-06-20 广东小天才科技有限公司 一种混合语种字幕文件生成方法及装置
CN110728976A (zh) * 2018-06-30 2020-01-24 华为技术有限公司 语音识别的方法、装置及系统
CN111986655A (zh) * 2020-08-18 2020-11-24 北京字节跳动网络技术有限公司 音频内容识别方法、装置、设备和计算机可读介质

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6505153B1 (en) * 2000-05-22 2003-01-07 Compaq Information Technologies Group, L.P. Efficient method for producing off-line closed captions
US20030236663A1 (en) * 2002-06-19 2003-12-25 Koninklijke Philips Electronics N.V. Mega speaker identification (ID) system and corresponding methods therefor
EP1542206A1 (en) * 2003-12-11 2005-06-15 Sony International (Europe) GmbH Apparatus and method for automatic classification of audio signals
KR100636317B1 (ko) * 2004-09-06 2006-10-18 삼성전자주식회사 분산 음성 인식 시스템 및 그 방법
US8046221B2 (en) * 2007-10-31 2011-10-25 At&T Intellectual Property Ii, L.P. Multi-state barge-in models for spoken dialog systems
US8606581B1 (en) * 2010-12-14 2013-12-10 Nuance Communications, Inc. Multi-pass speech recognition
CN103714812A (zh) * 2013-12-23 2014-04-09 百度在线网络技术（北京）有限公司 一种语音识别方法及装置
CN105895078A (zh) * 2015-11-26 2016-08-24 乐视致新电子科技（天津）有限公司 动态选择语音模型的语音识别方法及装置
CN105788592A (zh) * 2016-04-28 2016-07-20 乐视控股（北京）有限公司 一种音频分类方法及装置
US10490209B2 (en) * 2016-05-02 2019-11-26 Google Llc Automatic determination of timing windows for speech captions in an audio stream
US10860685B2 (en) * 2016-11-28 2020-12-08 Google Llc Generating structured text content using speech recognition models
CN112802459B (zh) * 2017-05-23 2024-06-18 创新先进技术有限公司 一种基于语音识别的咨询业务处理方法及装置
CN109147771B (zh) * 2017-06-28 2021-07-06 广州视源电子科技股份有限公司 音频分割方法和系统
CN107797984B (zh) * 2017-09-11 2021-05-14 远光软件股份有限公司 智能交互方法、设备及存储介质
US11024291B2 (en) * 2018-11-21 2021-06-01 Sri International Real-time class recognition for an audio stream
CN110349564B (zh) * 2019-07-22 2021-09-24 思必驰科技股份有限公司 一种跨语言语音识别方法和装置
CN111243595B (zh) * 2019-12-31 2022-12-27 京东科技控股股份有限公司 信息处理方法和装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010091675A (ja) * 2008-10-06 2010-04-22 Mitsubishi Electric Corp 音声認識装置
CN102881309A (zh) * 2012-09-24 2013-01-16 广东欧珀移动通信有限公司 歌词文件生成、校对方法及装置
CN105845129A (zh) * 2016-03-25 2016-08-10 乐视控股（北京）有限公司 一种在音频中切分句子的方法和系统及视频文件的字幕自动生成方法和系统
CN106878805A (zh) * 2017-02-06 2017-06-20 广东小天才科技有限公司 一种混合语种字幕文件生成方法及装置
CN110728976A (zh) * 2018-06-30 2020-01-24 华为技术有限公司 语音识别的方法、装置及系统
CN111986655A (zh) * 2020-08-18 2020-11-24 北京字节跳动网络技术有限公司 音频内容识别方法、装置、设备和计算机可读介质

Also Published As

Publication number Publication date
CN111986655A (zh) 2020-11-24
CN111986655B (zh) 2022-04-01
US11783808B2 (en) 2023-10-10
US20230091272A1 (en) 2023-03-23

Similar Documents

Publication Publication Date Title
WO2022037419A1 (zh) 音频内容识别方法、装置、设备和计算机可读介质
WO2020238320A1 (zh) 用于生成表情包的方法和装置
WO2023083142A1 (zh) 分句方法、装置、存储介质及电子设备
US20240029709A1 (en) Voice generation method and apparatus, device, and computer readable medium
CN112509562B (zh) 用于文本后处理的方法、装置、电子设备和介质
US20240079002A1 (en) Minutes of meeting processing method and apparatus, device, and medium
WO2023082931A1 (zh) 用于语音识别标点恢复的方法、设备和存储介质
CN112182255A (zh) 用于存储媒体文件和用于检索媒体文件的方法和装置
WO2022228067A1 (zh) 语音处理方法、装置和电子设备
CN117633228A (zh) 模型训练方法和装置
CN115640815A (zh) 翻译方法、装置、可读介质及电子设备
WO2022037383A1 (zh) 语音处理方法、装置、电子设备和计算机可读介质
CN112954453B (zh) 视频配音方法和装置、存储介质和电子设备
WO2024146338A1 (zh) 视频生成方法、装置、电子设备及存储介质
CN112017685B (zh) 语音生成方法、装置、设备和计算机可读介质
CN111859970B (zh) 用于处理信息的方法、装置、设备和介质
US20240096347A1 (en) Method and apparatus for determining speech similarity, and program product
WO2021170094A1 (zh) 用于信息交互的方法和装置
CN112652329B (zh) 文本重对齐方法、装置、电子设备和存储介质
CN113221554A (zh) 文本处理方法、装置、电子设备和存储介质
CN113221514A (zh) 文本处理方法、装置、电子设备和存储介质
CN112699687A (zh) 内容编目方法、装置和电子设备
CN111859971A (zh) 用于处理信息的方法、装置、设备和介质
CN113808615B (zh) 音频类别定位方法、装置、电子设备和存储介质
CN111681660B (zh) 语音识别方法、装置、电子设备和计算机可读介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21857514

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21857514

Country of ref document: EP

Kind code of ref document: A1