Reducing exposure bias in training recurrent neural network transducers
- Xiaodong Cui
- Brian Kingsbury
- et al.
- 2021
- INTERSPEECH 2021
Conference paper
Publications
16 results at INTERSPEECH 2021
Synthesis of expressive speaking styles with limited training data in a multi-speaker, prosody-controllable sequence-to-sequence architecture
- Slava Shechtman
- Raul Fernandez
- et al.
- 2021
- INTERSPEECH 2021
Conference paperOn the limit of English conversational speech recognition
- Zoltan Tuske
- George Saon
- et al.
- 2021
- INTERSPEECH 2021
Conference paperCascaded multilingual audio-visual learning from videos
- Andrew Rouditchenko
- Angie Boggust
- et al.
- 2021
- INTERSPEECH 2021
Conference paperLow resource ASR: The surprising effectiveness of high resource transliteration
- Shreya Khare
- Ashish Mittal
- et al.
- 2021
- INTERSPEECH 2021
Conference paperToken-level supervised contrastive learning for punctuation restoration
- Qiushi Huang
- Tom Ko
- et al.
- 2021
- INTERSPEECH 2021
Conference paper4-bit quantization of LSTM-based speech recognition models
- Andrea Fasoli
- Chia-Yu Chen
- et al.
- 2021
- INTERSPEECH 2021
Conference paperImproving customization of neural transducers by mitigating acoustic mismatch of synthesized audio
- Gakuto Kurata
- George Saon
- et al.
- 2021
- INTERSPEECH 2021
Conference paperKnowledge distillation based training of universal ASR source models for cross-lingual transfer
- 2021
- INTERSPEECH 2021
Conference paperIntegrating dialog history into end-to-end spoken language understanding systems
- 2021
- INTERSPEECH 2021
Conference paper