Publications

This is our catalog of publications authored by IBM researchers, in collaboration with the global research community. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.

Date

Start

End

Featured collections

Popular topics

104 results for Speech

Knowledge distillation from offline to streaming RNN transducer for end-to-end speech recognition
- - Gakuto Kurata
  - George Saon
- 2020
- INTERSPEECH 2020
Principal style components: Expressive style control and cross-speaker transfer in neural TTS
- - Alexander Sorin
  - Slava Shechtman
  - et al.
- 2020
- INTERSPEECH 2020
Implicit transfer of privileged acoustic information in a generalized knowledge distillation framework
- - Takashi Fukuda
  - Samuel Thomas
- 2020
- INTERSPEECH 2020
Representation based meta-learning for few-shot spoken intent recognition
- - Ashish Mittal
  - Samarth Bharadwaj
  - et al.
- 2020
- INTERSPEECH 2020
Transliteration based data augmentation for training multilingual ASR acoustic models in low resource settings
- - Samuel Thomas
  - Kartik Audhkhasi
  - et al.
- 2020
- INTERSPEECH 2020
New advances in speaker diarization
- - Hagai Aronowitz
  - Weizhong Zhu
  - et al.
- 2020
- INTERSPEECH 2020
Resource-adaptive deep learning for visual speech recognition
- - Alexandros Koumparoulis
  - Gerasimos Potamianos
  - et al.
- 2020
- INTERSPEECH 2020
Predicting Future Accident Risks of Older Drivers by Speech Data from a Voice-Based Dialogue System: A Preliminary Result
- - Yasunori Yamada
  - Kaoru Shinkawa
  - et al.
- 2020
- AHFE 2020
Effective joint training of denoising feature space transforms and Neural Network based acoustic models
- - Takashi Fukuda
  - Osamu Ichikawa
  - et al.
- 2017
- ICASSP 2017
Harmonic feature fusion for robust neural network-based acoustic modeling
- - Osamu Ichikawa
  - Takashi Fukuda
  - et al.
- 2017
- ICASSP 2017