JP2022515048A5 - - Google Patents

Info

Publication number
JP2022515048A5
JP2022515048A5 JP2021533448A JP2021533448A JP2022515048A5 JP 2022515048 A5 JP2022515048 A5 JP 2022515048A5 JP 2021533448 A JP2021533448 A JP 2021533448A JP 2021533448 A JP2021533448 A JP 2021533448A JP 2022515048 A5 JP2022515048 A5 JP 2022515048A5
Authority
JP
Japan
Prior art keywords
script
words
speech recognition
recognition model
transcribing
Prior art date
Application number
JP2021533448A
Other languages
English (en)
Japanese (ja)
Other versions
JP2022515048A (ja
JP7208399B2 (ja
JPWO2020122974A5 (https=
Filing date
Publication date
Application filed filed Critical
Priority claimed from PCT/US2019/017258 external-priority patent/WO2020122974A1/en
Publication of JP2022515048A publication Critical patent/JP2022515048A/ja
Publication of JP2022515048A5 publication Critical patent/JP2022515048A5/ja
Publication of JPWO2020122974A5 publication Critical patent/JPWO2020122974A5/ja
Application granted granted Critical
Publication of JP7208399B2 publication Critical patent/JP7208399B2/ja
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

JP2021533448A 2018-12-12 2019-02-08 音声認識の訓練および採点のための音訳 Active JP7208399B2 (ja)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US201862778431P 2018-12-12 2018-12-12
US62/778,431 2018-12-12
PCT/US2019/017258 WO2020122974A1 (en) 2018-12-12 2019-02-08 Transliteration for speech recognition training and scoring

Publications (4)

Publication Number Publication Date
JP2022515048A JP2022515048A (ja) 2022-02-17
JP2022515048A5 true JP2022515048A5 (https=) 2022-08-25
JPWO2020122974A5 JPWO2020122974A5 (https=) 2022-08-25
JP7208399B2 JP7208399B2 (ja) 2023-01-18

Family

ID=65520451

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2021533448A Active JP7208399B2 (ja) 2018-12-12 2019-02-08 音声認識の訓練および採点のための音訳

Country Status (5)

Country Link
EP (1) EP3877973B1 (https=)
JP (1) JP7208399B2 (https=)
KR (1) KR102731583B1 (https=)
CN (1) CN113396455B (https=)
WO (1) WO2020122974A1 (https=)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114420159B (zh) * 2020-10-12 2025-04-18 苏州声通信息科技有限公司 音频评测方法及装置、非瞬时性存储介质
US11568858B2 (en) * 2020-10-17 2023-01-31 International Business Machines Corporation Transliteration based data augmentation for training multilingual ASR acoustic models in low resource settings
CN113626563A (zh) * 2021-08-30 2021-11-09 京东方科技集团股份有限公司 训练自然语言处理模型和自然语言处理的方法、电子设备
CN113889105B (zh) * 2021-09-29 2025-07-04 北京搜狗科技发展有限公司 一种语音翻译方法、装置和用于语音翻译的装置
CN114118108A (zh) * 2021-11-11 2022-03-01 支付宝(杭州)信息技术有限公司 建立转译模型的方法、转译方法和对应装置
CN114299930B (zh) * 2021-12-21 2025-03-14 广州虎牙科技有限公司 端到端语音识别模型处理方法、语音识别方法及相关装置
CN114520001B (zh) * 2022-03-22 2025-08-01 科大讯飞股份有限公司 一种语音识别方法、装置、设备及存储介质
KR102616598B1 (ko) * 2023-05-30 2023-12-22 주식회사 엘솔루 번역 자막을 이용한 원문 자막 병렬 데이터 생성 방법

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8335688B2 (en) * 2004-08-20 2012-12-18 Multimodal Technologies, Llc Document transcription system training
US20080221866A1 (en) * 2007-03-06 2008-09-11 Lalitesh Katragadda Machine Learning For Transliteration
JP2009157888A (ja) 2007-12-28 2009-07-16 National Institute Of Information & Communication Technology 音訳モデル作成装置、音訳装置、及びそれらのためのコンピュータプログラム
US7472061B1 (en) * 2008-03-31 2008-12-30 International Business Machines Corporation Systems and methods for building a native language phoneme lexicon having native pronunciations of non-native words derived from non-native pronunciations
WO2009129315A1 (en) 2008-04-15 2009-10-22 Mobile Technologies, Llc System and methods for maintaining speech-to-speech translation in the field
US9176936B2 (en) * 2012-09-28 2015-11-03 International Business Machines Corporation Transliteration pair matching
US10540957B2 (en) * 2014-12-15 2020-01-21 Baidu Usa Llc Systems and methods for speech transcription
JP2018028848A (ja) 2016-08-19 2018-02-22 日本放送協会 変換処理装置、音訳処理装置、およびプログラム
US10255909B2 (en) * 2017-06-29 2019-04-09 Intel IP Corporation Statistical-analysis-based reset of recurrent neural networks for automatic speech recognition

Similar Documents

Publication Publication Date Title
JP2022515048A5 (https=)
US11664020B2 (en) Speech recognition method and apparatus
US10573296B1 (en) Reconciliation between simulator and speech recognition output using sequence-to-sequence mapping
US20230230576A1 (en) Text-to-speech synthesis method and system, and a method of training a text-to-speech synthesis system
US9721561B2 (en) Method and apparatus for speech recognition using neural networks with speaker adaptation
WO2020068790A1 (en) Conversational agent pipeline trained on synthetic data
US10235991B2 (en) Hybrid phoneme, diphone, morpheme, and word-level deep neural networks
US20160071512A1 (en) Multilingual prosody generation
CN106297800B (zh) 一种自适应的语音识别的方法和设备
JP7055630B2 (ja) 音声認識のための学習方法、学習装置、コンピュータプログラム及び記憶媒体
WO2017136016A1 (en) Re-recognizing speech with external data sources
US8447603B2 (en) Rating speech naturalness of speech utterances based on a plurality of human testers
JP2007279744A5 (https=)
CN112634866A (zh) 语音合成模型训练和语音合成方法、装置、设备及介质
KR20240122776A (ko) 뉴럴 음성 합성의 적응 및 학습
CN111933121B (zh) 一种声学模型训练方法及装置
CN108039168B (zh) 声学模型优化方法及装置
US20130030808A1 (en) Computer-Implemented Systems and Methods for Scoring Concatenated Speech Responses
KR20190012419A (ko) 발화 유창성 자동 평가 시스템 및 방법
WO2015025788A1 (ja) 定量的ｆ０パターン生成装置及び方法、並びにｆ０パターン生成のためのモデル学習装置及び方法
JPWO2020122974A5 (https=)
CN112259084A (zh) 语音识别方法、装置和存储介质
CN119993196A (zh) 一种语音训练数据的获取方法、装置、设备及介质
JP2013214016A (ja) 音響モデル性能評価装置とその方法とプログラム
CN114267339A (zh) 语音识别处理方法及系统、设备以及存储介质