Paper ID: 2310.03724

Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer

Paul-Ambroise Duquenne, Holger Schwenk, Benoît Sagot

Recent research has shown that independently trained encoders and decoders, combined through a shared fixed-size representation, can achieve competitive performance in speech-to-text translation. In this work, we show that this type of approach can be further improved with multilingual training. We observe significant improvements in zero-shot cross-modal speech translation, even outperforming a supervised approach based on XLSR for several languages.

Submitted: Oct 5, 2023