PromptST: Abstract Prompt Learning for End-to-End Speech Translation

Published: 07 Oct 2023, Last Modified: 01 Dec 2023EMNLP 2023 MainEveryoneRevisionsBibTeX
Submission Type: Regular Long Paper
Submission Track: Speech and Multimodality
Keywords: Speech-to-Text Translation, Linguistic Probing Benchmark, Prompt Learning
TL;DR: We explore the fusion in S2T and propose PromptST to improve.
Abstract: An end-to-end speech-to-text (S2T) translation model is usually initialized from a pre-trained speech recognition encoder and a pre-trained text-to-text (T2T) translation decoder. Although this straightforward setting has been shown empirically successful, there do not exist clear answers to the research questions: 1) how are speech and text modalities fused in S2T model and 2) how to better fuse the two modalities? In this paper, we take the first step toward understanding the fusion of speech and text features in S2T model. We first design and release a 10GB linguistic probing benchmark, namely Speech-Senteval, to investigate the acoustic and linguistic behaviors of S2T models. Preliminary analysis reveals that the uppermost encoder layers of the S2T model can not learn linguistic knowledge efficiently, which is crucial for accurate translation. Based on the finding, we further propose a simple plug-in prompt-learning strategy on the uppermost encoder layers to broaden the abstract representation power of the encoder of S2T models. We call such a prompt-enhanced S2T model PromptST. Experimental results on four widely-used S2T datasets show that PromptST can deliver significant improvements over a strong baseline by capturing richer linguistic knowledge. Benchmarks, code, and scripts are freely available at
Submission Number: 5704