WO2023027634A3 - 音频信号的分离方法、装置、设备、存储介质及程序 - Google Patents

音频信号的分离方法、装置、设备、存储介质及程序 Download PDF

Info

Publication number
WO2023027634A3
WO2023027634A3 PCT/SG2022/050588 SG2022050588W WO2023027634A3 WO 2023027634 A3 WO2023027634 A3 WO 2023027634A3 SG 2022050588 W SG2022050588 W SG 2022050588W WO 2023027634 A3 WO2023027634 A3 WO 2023027634A3
Authority
WO
WIPO (PCT)
Prior art keywords
audio signal
information
amplitude
storage medium
separation method
Prior art date
Application number
PCT/SG2022/050588
Other languages
English (en)
French (fr)
Other versions
WO2023027634A2 (zh
Inventor
孔秋强
刘濠赫
Original Assignee
脸萌有限公司
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 脸萌有限公司 filed Critical 脸萌有限公司
Publication of WO2023027634A2 publication Critical patent/WO2023027634A2/zh
Publication of WO2023027634A3 publication Critical patent/WO2023027634A3/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G10L21/028—Voice signal separating using properties of sound source

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Signal Processing (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Stereophonic System (AREA)

Abstract

摘要本公开实施例提供一种音频信号的分离方法、装置、设备、电子设备、计算机可读存储介质、计算机程序产品及计算机程序，该方法包括：确定待处理的混合音频信号的第一幅值信息、以及混合音频信号的第一相位信息，对所述第一幅值信息进行处理，得到混合音频信号与第一音频信号之间的幅值差异信息和相位差异信息，第一音频信号为混合音频信号中第一音源对应的纯净音频信号，根据第一幅值信息、第一相位信息、幅值差异信息和相位差异信息，确定第一音频信号。通过上述过程中，能够提升音频分离效果。
PCT/SG2022/050588 2021-08-27 2022-08-18 音频信号的分离方法、装置、设备、存储介质及程序 WO2023027634A2 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110993553.1A CN115731941A (zh) 2021-08-27 2021-08-27 音频信号的分离方法、装置、设备、存储介质及程序
CN202110993553.1 2021-08-27

Publications (2)

Publication Number Publication Date
WO2023027634A2 WO2023027634A2 (zh) 2023-03-02
WO2023027634A3 true WO2023027634A3 (zh) 2023-04-13

Family

ID=85290141

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/SG2022/050588 WO2023027634A2 (zh) 2021-08-27 2022-08-18 音频信号的分离方法、装置、设备、存储介质及程序

Country Status (2)

Country Link
CN (1) CN115731941A (zh)
WO (1) WO2023027634A2 (zh)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140247947A1 (en) * 2011-12-19 2014-09-04 Panasonic Corporation Sound separation device and sound separation method
CN109584903A (zh) * 2018-12-29 2019-04-05 中国科学院声学研究所 一种基于深度学习的多人语音分离方法
CN110503976A (zh) * 2019-08-15 2019-11-26 广州华多网络科技有限公司 音频分离方法、装置、电子设备及存储介质
CN111128214A (zh) * 2019-12-19 2020-05-08 网易（杭州）网络有限公司 音频降噪方法、装置、电子设备及介质
CN111192594A (zh) * 2020-01-10 2020-05-22 腾讯音乐娱乐科技（深圳）有限公司 人声和伴奏分离方法及相关产品
CN111540374A (zh) * 2020-04-17 2020-08-14 杭州网易云音乐科技有限公司 伴奏和人声提取方法及装置、逐字歌词生成方法及装置
CN111724807A (zh) * 2020-08-05 2020-09-29 字节跳动有限公司 音频分离方法、装置、电子设备及计算机可读存储介质
CN113099336A (zh) * 2020-01-08 2021-07-09 北京小米移动软件有限公司 调整耳机音频参数的方法及装置、耳机、存储介质

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140247947A1 (en) * 2011-12-19 2014-09-04 Panasonic Corporation Sound separation device and sound separation method
CN109584903A (zh) * 2018-12-29 2019-04-05 中国科学院声学研究所 一种基于深度学习的多人语音分离方法
CN110503976A (zh) * 2019-08-15 2019-11-26 广州华多网络科技有限公司 音频分离方法、装置、电子设备及存储介质
CN111128214A (zh) * 2019-12-19 2020-05-08 网易（杭州）网络有限公司 音频降噪方法、装置、电子设备及介质
CN113099336A (zh) * 2020-01-08 2021-07-09 北京小米移动软件有限公司 调整耳机音频参数的方法及装置、耳机、存储介质
CN111192594A (zh) * 2020-01-10 2020-05-22 腾讯音乐娱乐科技（深圳）有限公司 人声和伴奏分离方法及相关产品
CN111540374A (zh) * 2020-04-17 2020-08-14 杭州网易云音乐科技有限公司 伴奏和人声提取方法及装置、逐字歌词生成方法及装置
CN111724807A (zh) * 2020-08-05 2020-09-29 字节跳动有限公司 音频分离方法、装置、电子设备及计算机可读存储介质

Also Published As

Publication number Publication date
CN115731941A (zh) 2023-03-03
WO2023027634A2 (zh) 2023-03-02

Similar Documents

Publication Publication Date Title
CN106297815B (zh) 一种语音识别场景中回音消除的方法
WO2017191970A3 (ko) 바이노럴 렌더링을 위한 오디오 신호 처리 방법 및 장치
MX364461B (es) Método y dispositivo para lograr el registro de audio objetivo y aparato electrónico.
RU2012157193A (ru) Система и способ для обработки звука
WO2010013940A3 (en) A method and an apparatus for processing an audio signal
EP4373106A3 (en) Method and device to control audio playback devices
AU2003303362A8 (en) Audio reproduction apparatus, feedback system and method
WO2017206900A1 (zh) 声音文件的音质识别方法及装置
EP4242828A3 (en) Audio apparatus and method of audio processing
CN101192182B (zh) 音频放音测试装置及方法
WO2023027634A3 (zh) 音频信号的分离方法、装置、设备、存储介质及程序
MX2022015652A (es) Metodos, aparatos y sistemas para deteccion y extraccion de fuentes de audio de subbanda espacialmente identificables.
US20150201393A1 (en) Devices, systems and methods of location identification
CN112053669A (zh) 一种人声消除方法、装置、设备及介质
CN109036455B (zh) 直达声与背景声提取方法、扬声器系统及其声重放方法
CN108347688A (zh) 根据单声道音频数据提供立体声效果的影音处理方法及影音处理装置
WO2023140787A3 (zh) 视频的处理方法、装置、电子设备、存储介质和程序产品
EP4030424A3 (en) Method and apparatus of processing voice for vehicle, electronic device and medium
CN103916097A (zh) 用于处理音频信号的设备和方法
CN105101011A (zh) 音频输出控制方法和装置
CN111131961A (zh) 一种音箱以及音箱共振的改善方法
WO2022074202A3 (en) Apparatus, method, or computer program for processing an encoded audio scene using a parameter smoothing
MX2023002587A (es) Dispositivo y metodo de procesamiento acustico y programa.
WO2022074201A3 (en) Apparatus, method, or computer program for processing an encoded audio scene using a bandwidth extension
EP4284030A3 (en) Audio signal processing method, audio signal processing apparatus and audio signal processing program

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 18570923

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE