TWI918793B - 用於合成語音生成的設備、方法、電腦可讀儲存媒體以及裝置 - Google Patents

用於合成語音生成的設備、方法、電腦可讀儲存媒體以及裝置

Info

Publication number
TWI918793B
TWI918793B TW110145937A TW110145937A TWI918793B TW I918793 B TWI918793 B TW I918793B TW 110145937 A TW110145937 A TW 110145937A TW 110145937 A TW110145937 A TW 110145937A TW I918793 B TWI918793 B TW I918793B
Authority
TW
Taiwan
Prior art keywords
speech
input
encoder
control parameters
generate
Prior art date
Application number
TW110145937A
Other languages
English (en)
Chinese (zh)
Other versions
TW202230328A (zh
Inventor
邊景源
文山古
張樹華
維希德 蒙塔澤里
金萊軒
艾瑞克 維瑟
Original Assignee
美商高通公司
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 美商高通公司 filed Critical 美商高通公司
Publication of TW202230328A publication Critical patent/TW202230328A/zh
Application granted granted Critical
Publication of TWI918793B publication Critical patent/TWI918793B/zh

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
    • G10L13/00—Speech synthesis; Text to speech systems
    • G10L13/02—Methods for producing synthetic speech; Speech synthesisers
    • G10L13/04—Details of speech synthesis systems, e.g. synthesiser structure or memory management
    • G10L13/047—Architecture of speech synthesisers
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G06N3/0475—Generative networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/09—Supervised learning
    • 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
    • G10L13/00—Speech synthesis; Text to speech systems
    • G10L13/02—Methods for producing synthetic speech; Speech synthesisers
    • G10L13/033—Voice editing, e.g. manipulating the voice of the synthesiser
    • 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
    • G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
    • G10L19/02—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using spectral analysis, e.g. transform vocoders or subband vocoders
    • 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
    • G10L21/003—Changing voice quality, e.g. pitch or formants
    • G10L21/007—Changing voice quality, e.g. pitch or formants characterised by the process used
    • 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
    • G10L25/63—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 estimating an emotional state
    • 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
    • G10L21/003—Changing voice quality, e.g. pitch or formants
    • G10L21/007—Changing voice quality, e.g. pitch or formants characterised by the process used
    • G10L21/013—Adapting to target pitch
    • G10L2021/0135—Voice conversion or morphing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Acoustics & Sound (AREA)
  • Human Computer Interaction (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Quality & Reliability (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Child & Adolescent Psychology (AREA)
  • Hospice & Palliative Care (AREA)
  • Psychiatry (AREA)
  • Telephonic Communication Services (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • User Interface Of Digital Computer (AREA)
TW110145937A 2021-01-21 2021-12-08 用於合成語音生成的設備、方法、電腦可讀儲存媒體以及裝置 TWI918793B (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US17/154,372 US11676571B2 (en) 2021-01-21 2021-01-21 Synthesized speech generation
US17/154,372 2021-01-21

Publications (2)

Publication Number Publication Date
TW202230328A TW202230328A (zh) 2022-08-01
TWI918793B true TWI918793B (zh) 2026-03-21

Family

ID=79092855

Family Applications (1)

Application Number Title Priority Date Filing Date
TW110145937A TWI918793B (zh) 2021-01-21 2021-12-08 用於合成語音生成的設備、方法、電腦可讀儲存媒體以及裝置

Country Status (8)

Country Link
US (1) US11676571B2 (enExample)
EP (1) EP4281964B1 (enExample)
JP (1) JP7846697B2 (enExample)
KR (1) KR20230133295A (enExample)
CN (1) CN116711002A (enExample)
BR (1) BR112023013902A2 (enExample)
TW (1) TWI918793B (enExample)
WO (1) WO2022159256A1 (enExample)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11676571B2 (en) * 2021-01-21 2023-06-13 Qualcomm Incorporated Synthesized speech generation
US12260851B2 (en) * 2021-07-14 2025-03-25 Google Llc Two-level text-to-speech systems using synthetic training data
US12002455B2 (en) * 2021-07-22 2024-06-04 Qualcomm Incorporated Semantically-augmented context representation generation
US20230037541A1 (en) * 2021-07-29 2023-02-09 Xinapse Co., Ltd. Method and system for synthesizing speeches by scoring speeches
CN115359779B (zh) * 2022-07-26 2025-02-11 招联消费金融股份有限公司 语音合成方法、装置、计算机设备和存储介质
CN115394284B (zh) * 2022-08-23 2024-09-24 平安科技（深圳）有限公司 语音合成方法、系统、设备及存储介质
US12682918B2 (en) 2022-09-13 2026-07-14 Qualcomm Incorporated Source speech modification based on an input speech characteristic mapped to multiple reference embeddings within a threshold similarity
US20240304174A1 (en) * 2023-03-08 2024-09-12 Sony Interactive Entertainment Inc. Ambient Noise Capture for Speech Synthesis of In-Game Character Voices
TWI872556B (zh) * 2023-05-25 2025-02-11 國立清華大學 一種跨辨識任務之情緒辨識方法、系統及電腦程式產品

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW200638336A (en) 2005-03-11 2006-11-01 Qualcomm Inc Time warping frames inside the vocoder by modifying the residual
US20120123782A1 (en) 2009-04-16 2012-05-17 Geoffrey Wilfart Speech synthesis and coding methods
TW202008348A (zh) 2018-07-25 2020-02-16 大陸商騰訊科技（深圳）有限公司 語音合成方法、模型訓練方法、裝置和電腦設備
CN111566655A (zh) 2018-01-11 2020-08-21 新智株式会社 多种语言文本语音合成方法

Family Cites Families (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105390141B (zh) * 2015-10-14 2019-10-18 科大讯飞股份有限公司 声音转换方法和装置
US10332520B2 (en) * 2017-02-13 2019-06-25 Qualcomm Incorporated Enhanced speech generation
US11894008B2 (en) * 2017-12-12 2024-02-06 Sony Corporation Signal processing apparatus, training apparatus, and method
JP6773634B2 (ja) * 2017-12-15 2020-10-21 日本電信電話株式会社 音声変換装置、音声変換方法及びプログラム
KR102072162B1 (ko) * 2018-01-05 2020-01-31 서울대학교산학협력단 인공 지능 기반 외국어 음성 합성 방법 및 장치
KR102473447B1 (ko) * 2018-03-22 2022-12-05 삼성전자주식회사 인공지능 모델을 이용하여 사용자 음성을 변조하기 위한 전자 장치 및 이의 제어 방법
JP6864322B2 (ja) * 2018-07-19 2021-04-28 株式会社エーアイ 音声処理装置、音声処理プログラムおよび音声処理方法
US11138392B2 (en) 2018-07-26 2021-10-05 Google Llc Machine translation using neural network models
WO2020027619A1 (ko) * 2018-08-02 2020-02-06 네오사피엔스 주식회사 순차적 운율 특징을 기초로 기계학습을 이용한 텍스트-음성 합성 방법, 장치 및 컴퓨터 판독가능한 저장매체
US10741169B1 (en) * 2018-09-25 2020-08-11 Amazon Technologies, Inc. Text-to-speech (TTS) processing
JP6747489B2 (ja) * 2018-11-06 2020-08-26 ヤマハ株式会社 情報処理方法、情報処理システムおよびプログラム
KR20200092505A (ko) * 2019-01-13 2020-08-04 네오데우스 주식회사 심층 합성곱 신경망 인공지능을 기반으로 한 미세조정을 통해 소량의 샘플로 화자 적합된 음성합성 모델을 생성하는 방법
US12032920B2 (en) * 2019-03-29 2024-07-09 Google Llc Direct speech-to-speech translation via machine learning
KR102663669B1 (ko) * 2019-11-01 2024-05-08 엘지전자 주식회사 소음 환경에서의 음성 합성
CN111862953B (zh) * 2019-12-05 2023-08-22 北京嘀嘀无限科技发展有限公司 语音识别模型的训练方法、语音识别方法及装置
US11335324B2 (en) * 2020-08-31 2022-05-17 Google Llc Synthesized data augmentation using voice conversion and speech recognition models
EP3989217B1 (en) * 2020-10-22 2023-09-27 Thomson Licensing Method for detecting an audio adversarial attack with respect to a voice input processed by an automatic speech recognition system, corresponding device, computer program product and computer-readable carrier medium
CN112133282B (zh) * 2020-10-26 2022-07-08 厦门大学 轻量级多说话人语音合成系统及电子设备
CN112562728B (zh) * 2020-11-13 2024-06-18 百果园技术(新加坡)有限公司 生成对抗网络训练方法、音频风格迁移方法及装置
CN112466316A (zh) * 2020-12-10 2021-03-09 青海民族大学 一种基于生成对抗网络的零样本语音转换系统
US11676571B2 (en) * 2021-01-21 2023-06-13 Qualcomm Incorporated Synthesized speech generation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW200638336A (en) 2005-03-11 2006-11-01 Qualcomm Inc Time warping frames inside the vocoder by modifying the residual
US20120123782A1 (en) 2009-04-16 2012-05-17 Geoffrey Wilfart Speech synthesis and coding methods
CN111566655A (zh) 2018-01-11 2020-08-21 新智株式会社 多种语言文本语音合成方法
TW202008348A (zh) 2018-07-25 2020-02-16 大陸商騰訊科技（深圳）有限公司 語音合成方法、模型訓練方法、裝置和電腦設備

Also Published As

Publication number Publication date
EP4281964B1 (en) 2026-07-22
US11676571B2 (en) 2023-06-13
US20220230623A1 (en) 2022-07-21
KR20230133295A (ko) 2023-09-19
EP4281964A1 (en) 2023-11-29
CN116711002A (zh) 2023-09-05
BR112023013902A2 (pt) 2024-01-23
TW202230328A (zh) 2022-08-01
JP2024504316A (ja) 2024-01-31
WO2022159256A1 (en) 2022-07-28
JP7846697B2 (ja) 2026-04-15

Similar Documents

Publication Publication Date Title
JP7846697B2 (ja) 合成音声生成
US12380909B2 (en) Context-data based speech enhancement
US11170774B2 (en) Virtual assistant device
WO2024054714A1 (en) Avatar representation and audio generation
WO2019242414A1 (zh) 语音处理方法、装置、存储介质及电子设备
US20240087597A1 (en) Source speech modification based on an input speech characteristic
US11626104B2 (en) User speech profile management
CN105580071A (zh) 用于训练声音识别模型数据库的方法和装置
WO2024054713A1 (en) Avatar facial expressions based on semantical context
CN114708849A (zh) 语音处理方法、装置、计算机设备及计算机可读存储介质
JP2018191145A (ja) 収音装置、収音方法、収音プログラム及びディクテーション方法
CN113056908A (zh) 视频字幕合成方法、装置、存储介质及电子设备
CN118155602A (zh) 语音合成方法、装置、设备以及计算机可读存储介质
CN114267322A (zh) 语音处理方法、装置、计算机可读存储介质及计算机设备
US11646046B2 (en) Psychoacoustic enhancement based on audio source directivity
CN121054023A (zh) 音频处理方法、装置、终端设备、存储介质及程序产品
CN119998869A (zh) 用于媒体生成的媒体片段预测
CN111696565B (zh) 语音处理方法、装置和介质
CN111696566B (zh) 语音处理方法、装置和介质
US20240419731A1 (en) Knowledge-based audio scene graph
CN116092466B (zh) 语音模型的处理方法、装置、计算机设备及存储介质
CN111696564B (zh) 语音处理方法、装置和介质
CN120416713A (zh) 基于本地化处理的实时音频变音控制方法、系统及终端
CN120600047A (zh) 基于本地化处理的实时音频变音控制方法、系统及终端
WO2025240214A1 (en) Source-controlled variable-length audio encoder