3 papers
cs.CL2024
Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers
Michael Hentschel, Yuta Nishikawa, Tatsuya Komatsu +1
This study presents a novel approach for knowledge distillation (KD) from a BERT teacher model to an automatic speech recognition (ASR) model using intermediate layers. To distil t…
eess.AS2022
Joint Speech Recognition and Audio Captioning
Chaitanya Narisetty, Emiru Tsunoo, Xuankai Chang +3
Speech samples recorded in both indoor and outdoor environments are often contaminated with secondary audio sources. Most end-to-end monaural speech recognition systems either remo…
eess.AS2022
Run-and-back stitch search: novel block synchronous decoding for streaming encoder-decoder ASR
Emiru Tsunoo, Chaitanya Narisetty, Michael Hentschel +2
A streaming style inference of encoder-decoder automatic speech recognition (ASR) system is important for reducing latency, which is essential for interactive use cases. To this en…