Back to Search
Start Over
SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training
- Publication Year :
- 2022
-
Abstract
- The rapid development of single-modal pre-training has prompted researchers to pay more attention to cross-modal pre-training methods. In this paper, we propose a unified-modal speech-unit-text pre-training model, SpeechUT, to connect the representations of a speech encoder and a text decoder with a shared unit encoder. Leveraging hidden-unit as an interface to align speech and text, we can decompose the speech-to-text model into a speech-to-unit model and a unit-to-text model, which can be jointly pre-trained with unpaired speech and text data respectively. Our proposed SpeechUT is fine-tuned and evaluated on automatic speech recognition (ASR) and speech translation (ST) tasks. Experimental results show that SpeechUT gets substantial improvements over strong baselines, and achieves state-of-the-art performance on both the LibriSpeech ASR and MuST-C ST tasks. To better understand the proposed SpeechUT, detailed analyses are conducted. The code and pre-trained models are available at https://aka.ms/SpeechUT.<br />Comment: 14 pages, accepted by EMNLP 2022
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2210.03730
- Document Type :
- Working Paper