Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers

no code implementations • 22 Jan 2024 • Michael Hentschel, Yuta Nishikawa, Tatsuya Komatsu, Yusuke Fujita

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.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Joint Speech Recognition and Audio Captioning

no code implementations • 3 Feb 2022 • Chaitanya Narisetty, Emiru Tsunoo, Xuankai Chang, Yosuke Kashiwagi, Michael Hentschel, Shinji Watanabe

A major hurdle in evaluating our proposed approach is the lack of labeled audio datasets with both speech transcriptions and audio captions.

AudioCaps Audio captioning +4

Run-and-back stitch search: novel block synchronous decoding for streaming encoder-decoder ASR

no code implementations • 25 Jan 2022 • Emiru Tsunoo, Chaitanya Narisetty, Michael Hentschel, Yosuke Kashiwagi, Shinji Watanabe

To this end, we propose a novel blockwise synchronous decoding algorithm with a hybrid approach that combines endpoint prediction and endpoint post-determination.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1