BR112021020361A2 - Método e aparelho para determinar um filtro profundo, e uso do dito método - Google Patents

Método e aparelho para determinar um filtro profundo, e uso do dito método

Info

Publication number
BR112021020361A2
BR112021020361A2 BR112021020361A BR112021020361A BR112021020361A2 BR 112021020361 A2 BR112021020361 A2 BR 112021020361A2 BR 112021020361 A BR112021020361 A BR 112021020361A BR 112021020361 A BR112021020361 A BR 112021020361A BR 112021020361 A2 BR112021020361 A2 BR 112021020361A2
Authority
BR
Brazil
Prior art keywords
deep filter
determining
deep
filter
elements
Prior art date
Application number
BR112021020361A
Other languages
English (en)
Inventor
Emanuel Habets
Wolfgang Mack
Original Assignee
Fraunhofer Ges Forschung
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 Fraunhofer Ges Forschung filed Critical Fraunhofer Ges Forschung
Publication of BR112021020361A2 publication Critical patent/BR112021020361A2/pt

Links

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
    • G10L21/0216—Noise filtering characterised by the method used for estimating noise
    • G10L21/0224—Processing in the time domain
    • 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
    • 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
    • G06N3/048—Activation functions
    • 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
    • G10L21/0208—Noise filtering
    • G10L21/0216—Noise filtering characterised by the method used for estimating noise
    • G10L21/0232—Processing in the frequency domain
    • 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
    • G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
    • G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Acoustics & Sound (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Quality & Reliability (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Filters That Use Time-Delay Elements (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
  • Image Analysis (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Noise Elimination (AREA)
  • Paper (AREA)
  • Measurement Of Radiation (AREA)

Abstract

método e aparelho para determinar um filtro profundo, e uso do dito método. trata-se de um método para determinar um filtro profundo que compreende as seguintes etapas: - receber uma mistura; - estimar com o uso de uma rede neural profunda o filtro profundo, em que a estimativa é realizada, de modo que o filtro profundo, ao se aplicar aos elementos da mistura, obtenha estimativas dos respectivos elementos da representação desejada; em que o filtro profundo de pelo menos uma dimensão compreende um tensor com elementos.
BR112021020361A 2019-04-16 2020-04-15 Método e aparelho para determinar um filtro profundo, e uso do dito método BR112021020361A2 (pt)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP19169585.7A EP3726529A1 (en) 2019-04-16 2019-04-16 Method and apparatus for determining a deep filter
PCT/EP2020/060586 WO2020212419A1 (en) 2019-04-16 2020-04-15 Method and apparatus for determining a deep filter

Publications (1)

Publication Number Publication Date
BR112021020361A2 true BR112021020361A2 (pt) 2021-12-07

Family

ID=66217806

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112021020361A BR112021020361A2 (pt) 2019-04-16 2020-04-15 Método e aparelho para determinar um filtro profundo, e uso do dito método

Country Status (9)

Country Link
US (1) US20220059114A1 (pt)
EP (2) EP3726529A1 (pt)
JP (2) JP7486266B2 (pt)
KR (1) KR20210153677A (pt)
CN (1) CN114041185A (pt)
BR (1) BR112021020361A2 (pt)
CA (1) CA3136870A1 (pt)
MX (1) MX2021012603A (pt)
WO (1) WO2020212419A1 (pt)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20210137146A (ko) * 2019-03-10 2021-11-17 카르돔 테크놀로지 엘티디. 큐의 클러스터링을 사용한 음성 증강
WO2021226503A1 (en) 2020-05-08 2021-11-11 Nuance Communications, Inc. System and method for data augmentation for multi-microphone signal processing
GB2620747B (en) * 2022-07-19 2024-10-02 Samsung Electronics Co Ltd Method and apparatus for speech enhancement
US20240112690A1 (en) * 2022-09-26 2024-04-04 Cerence Operating Company Switchable Noise Reduction Profiles

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19948308C2 (de) * 1999-10-06 2002-05-08 Cortologic Ag Verfahren und Vorrichtung zur Geräuschunterdrückung bei der Sprachübertragung
EP2151822B8 (en) * 2008-08-05 2018-10-24 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Apparatus and method for processing an audio signal for speech enhancement using a feature extraction
US9881631B2 (en) * 2014-10-21 2018-01-30 Mitsubishi Electric Research Laboratories, Inc. Method for enhancing audio signal using phase information
US9666183B2 (en) * 2015-03-27 2017-05-30 Qualcomm Incorporated Deep neural net based filter prediction for audio event classification and extraction
US10339921B2 (en) * 2015-09-24 2019-07-02 Google Llc Multichannel raw-waveform neural networks
KR102151682B1 (ko) * 2016-03-23 2020-09-04 구글 엘엘씨 다중채널 음성 인식을 위한 적응성 오디오 강화
US11373672B2 (en) * 2016-06-14 2022-06-28 The Trustees Of Columbia University In The City Of New York Systems and methods for speech separation and neural decoding of attentional selection in multi-speaker environments
US10224058B2 (en) * 2016-09-07 2019-03-05 Google Llc Enhanced multi-channel acoustic models
WO2019008580A1 (en) * 2017-07-03 2019-01-10 Yissum Research Development Company Of The Hebrew University Of Jerusalem Ltd. METHOD AND SYSTEM FOR IMPROVING A VOICE SIGNAL OF A HUMAN SPEAKER IN A VIDEO USING VISUAL INFORMATION
CN108417207B (zh) * 2018-01-19 2020-06-30 苏州思必驰信息科技有限公司 一种深度混合生成网络自适应方法及系统
CN109194595B (zh) * 2018-09-26 2020-12-01 东南大学 一种基于神经网络的信道环境自适应ofdm接收方法

Also Published As

Publication number Publication date
EP3726529A1 (en) 2020-10-21
MX2021012603A (es) 2021-11-12
WO2020212419A1 (en) 2020-10-22
US20220059114A1 (en) 2022-02-24
CA3136870A1 (en) 2020-10-22
KR20210153677A (ko) 2021-12-17
CN114041185A (zh) 2022-02-11
JP7486266B2 (ja) 2024-05-17
EP3956888A1 (en) 2022-02-23
JP2022529912A (ja) 2022-06-27
JP2024038369A (ja) 2024-03-19

Similar Documents

Publication Publication Date Title
BR112021020361A2 (pt) Método e aparelho para determinar um filtro profundo, e uso do dito método
BR112018008709A2 (pt) artigo para uso com aparelho para aquecer o material de fumo para volatilizar pelo menos um componente do material de fumo e aparelhos para aquecer o material de fumo para volatilizar pelo menos um componente do material de fumo
BR112017022323A2 (pt) método para tratar doença do enxerto contra hospedeiro, uso de um composto, e, kit.
AR105655A1 (es) Apuntalantes recubiertos con polímeros reticulados
BR112016023619A2 (pt) técnicas para otimização de potência com base em parâmetros de rede
BR112017001725A2 (pt) tratamento de esclerose lateral amiotrófica
BR112018000241A2 (pt) modelo de recursos de rede para suportar gerenciamento de ciclo de vida de virtualização de função de rede
BR112016024508A2 (pt) emulsão, processo para preparação de uma emulsão, e, uso de uma emulsão
BR112016021678A2 (pt) método e sistema para determinar uma janela de peso de lama em um poço, e, meio legível por computador.
BR112017011956A2 (pt) composição de fraturamento hidráulico, método para fazer e uso da mesma
BR112018071600A2 (pt) métodos, composições e usos relacionados aos mesmos
BR112017001339A2 (pt) método, pasta de cimento e sistema
BR112015032730A2 (pt) método para operar um dispositivo de comunicação, dispositivo de comunicação, luminária e rede de comunicação
BR112016029627B8 (pt) Método para acabamento de engrenagens de metal temperado
BR112015019537A2 (pt) método para produção de couro, couro, uso de um ácido metanossulfônico
BR112017001753A2 (pt) método para determinar comprimento de lacuna de medição e dispositivo de rede
BR112015031824A2 (pt) aparelho e método para uma ocultação melhorada do livro do código adaptativo na ocultação tipo acelp utilizando uma estimativa melhorada de atraso de pitch
BR112018001486A2 (pt) ?composição de limpeza em barra, processo para preparar a composição, método para reduzir atividade antimicrobiana em uma superfície e uso da composição?
BR112017023431A2 (pt) método para estimar saturação de água em medições eletromagnéticas
BR112017027277A2 (pt) ?método para o tratamento ou prevenção de uma doença e métodos para matar uma célula?
BR112017001731A2 (pt) método para produzir uma peça de aço de alta resistência
BR112018071568A2 (pt) métodos, composições e usos relacionados aos mesmos
BR112018004619A2 (pt) vidro de segurança e método para a obtenção
BR112018009618A2 (pt) processo para fabricação de uma dispersão aquosa compreendendo farelo de mostarda, emulsão de óleo em água e processo de fabricação de uma emulsão de óleo em água
BR112016012058A2 (pt) Composição de corante disperso, corante disperso e método de preparação e uso dos mesmos