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) +4

Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Data

no code implementations • 14 Jun 2023 • Yuka Ko, Ryo Fukuda, Yuta Nishikawa, Yasumasa Kano, Katsuhito Sudoh, Satoshi Nakamura

In this paper, we propose an effective way to train a SimulST model using mixed data of SI and offline.

Inter-connection: Effective Connection between Pre-trained Encoder and Decoder for Speech Translation

no code implementations • 26 May 2023 • Yuta Nishikawa, Satoshi Nakamura

In this study, we propose an inter-connection mechanism that aggregates the information from each layer of the speech pre-trained model by weighted sums and inputs into the decoder.

2k Decoder +1