JPWO2021050197A5 - - Google Patents
Download PDFInfo
- Publication number
- JPWO2021050197A5 JPWO2021050197A5 JP2022515928A JP2022515928A JPWO2021050197A5 JP WO2021050197 A5 JPWO2021050197 A5 JP WO2021050197A5 JP 2022515928 A JP2022515928 A JP 2022515928A JP 2022515928 A JP2022515928 A JP 2022515928A JP WO2021050197 A5 JPWO2021050197 A5 JP WO2021050197A5
- Authority
- JP
- Japan
- Prior art keywords
- semantic parser
- seed
- tuple
- discriminator
- training
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201962898682P | 2019-09-11 | 2019-09-11 | |
US62/898,682 | 2019-09-11 | ||
PCT/US2020/046072 WO2021050197A1 (en) | 2019-09-11 | 2020-08-13 | Using a generative adversarial network to train a semantic parser of a dialog system |
Publications (2)
Publication Number | Publication Date |
---|---|
JP2022547998A JP2022547998A (ja) | 2022-11-16 |
JPWO2021050197A5 true JPWO2021050197A5 (de) | 2023-03-29 |
Family
ID=72235013
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2022515928A Pending JP2022547998A (ja) | 2019-09-11 | 2020-08-13 | 対話システムのセマンティックパーサを訓練するための敵対的生成ネットワークの使用 |
Country Status (5)
Country | Link |
---|---|
US (2) | US11908460B2 (de) |
EP (1) | EP4028930A1 (de) |
JP (1) | JP2022547998A (de) |
CN (1) | CN114365141A (de) |
WO (1) | WO2021050197A1 (de) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023192766A1 (en) * | 2022-03-31 | 2023-10-05 | D5Ai Llc | Generation and discrimination training as a variable resolution game |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8447611B2 (en) * | 2006-09-05 | 2013-05-21 | Fortemedia, Inc. | Pen-type voice computer and method thereof |
-
2020
- 2020-08-13 EP EP20761471.0A patent/EP4028930A1/de active Pending
- 2020-08-13 CN CN202080063344.0A patent/CN114365141A/zh active Pending
- 2020-08-13 US US16/992,306 patent/US11908460B2/en active Active
- 2020-08-13 JP JP2022515928A patent/JP2022547998A/ja active Pending
- 2020-08-13 WO PCT/US2020/046072 patent/WO2021050197A1/en unknown
-
2024
- 2024-01-11 US US18/410,229 patent/US20240144923A1/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20240177705A1 (en) | Optimal human-machine conversations using emotion-enhanced natural speech using artificial neural networks and reinforcement learning | |
US11664020B2 (en) | Speech recognition method and apparatus | |
US10559299B1 (en) | Reconciliation between simulator and speech recognition output using sequence-to-sequence mapping | |
EP3857543B1 (de) | Auf synthetischen daten trainierte konversationsagent-pipeline | |
KR102439740B1 (ko) | 제작자 제공 콘텐츠 기반 인터랙티브 대화 애플리케이션 테일링 | |
US10235991B2 (en) | Hybrid phoneme, diphone, morpheme, and word-level deep neural networks | |
KR20230003056A (ko) | 비음성 텍스트 및 스피치 합성을 사용한 스피치 인식 | |
US20020123891A1 (en) | Hierarchical language models | |
US10255910B2 (en) | Centered, left- and right-shifted deep neural networks and their combinations | |
KR20230056741A (ko) | 목소리 변환 및 스피치 인식 모델을 사용한 합성 데이터 증강 | |
US7069513B2 (en) | System, method and computer program product for a transcription graphical user interface | |
WO2022187168A1 (en) | Instantaneous learning in text-to-speech during dialog | |
JP7393585B2 (ja) | テキスト読み上げのためのWaveNetの自己トレーニング | |
Gondala et al. | Error-driven pruning of language models for virtual assistants | |
US7383187B2 (en) | System, method and computer program product for a distributed speech recognition tuning platform | |
US8438029B1 (en) | Confidence tying for unsupervised synthetic speech adaptation | |
JP6594251B2 (ja) | 音響モデル学習装置、音声合成装置、これらの方法及びプログラム | |
JP6712754B2 (ja) | 談話機能推定装置及びそのためのコンピュータプログラム | |
Wester et al. | A comparison of data-derived and knowledge-based modeling of pronunciation variation | |
US9355636B1 (en) | Selective speech recognition scoring using articulatory features | |
US9892726B1 (en) | Class-based discriminative training of speech models | |
US20230237987A1 (en) | Data sorting for generating rnn-t models | |
JPWO2021050197A5 (de) | ||
CN113066473A (zh) | 一种语音合成方法、装置、存储介质及电子设备 | |
US20230098315A1 (en) | Training dataset generation for speech-to-text service |