Improving End-to-end Mixed-case ASR with Knowledge Distillation and Integration of Voice Activity Cues
- Sashi Novitasari
- Takashi Fukuda
- et al.
- 2025
- INTERSPEECH 2025
Conference paper
Publications
35 results for Takashi Fukuda
Voice Activity-based Text Segmentation for ASR Text Denormalization
- Sashi Novitasari
- Takashi Fukuda
- et al.
- 2025
- INTERSPEECH 2025
Conference paperKnowledge Distillation Based Training of Unified Conformer CTC Models for Multi-form ASR
- 2025
- ICASSP 2025
Conference paperEffective Training of RNN Transducer Models on Diverse Sources of Speech and Text Data
- 2023
- ICASSP 2023
Conference paperGlobal RNN Transducer Models For Multi-dialect Speech Recognition
- 2022
- INTERSPEECH 2022
Conference paperImproving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing
- Xiaodong Cui
- George Saon
- et al.
- 2022
- INTERSPEECH 2022
Conference paperImproving ASR Robustness in Noisy Condition Through VAD Integration
- Sashi Novitasari
- Takashi Fukuda
- et al.
- 2022
- INTERSPEECH 2022
Conference paperKnowledge distillation based training of universal ASR source models for cross-lingual transfer
- 2021
- INTERSPEECH 2021
Conference paperGeneralized Knowledge Distillation from An Ensemble of Specialized Teachers Leveraging Unsupervised Neural Clustering
- 2021
- ICASSP 2021
Conference paperImplicit transfer of privileged acoustic information in a generalized knowledge distillation framework
- 2020
- INTERSPEECH 2020
Conference paper