Cross-Lingual Transfer Learning for Speech Translation

ACL ARR 2024 August Submission154 Authors

Abstract: There has been increasing interest in building multilingual foundation models for NLP and speech research. This paper examines how to expand the speech translation capability of these models with restricted data. Whisper, a speech foundation model with strong performance on speech recognition and English translation, is used as the example model. Using speech-to-speech retrieval to analyse the audio representations generated by the encoder, we show that utterances from different languages are mapped to a shared semantic space. This shared embedding space can then be leveraged for zero-shot cross-lingual transfer in speech translation. By fine-tuning the Whisper decoder with only English-to-Chinese speech translation data, improved performance for translation to Chinese can be obtained for multiple languages, in addition to English. Furthermore, for languages related to those seen in training it is possible to perform speech translation, despite the model never seeing the language in training, or being able to perform transcription.

Paper Type: Short

Research Area: Speech Recognition, Text-to-Speech and Spoken Language Understanding

Research Area Keywords: speech technologies, speech translation, multilingual MT, automatic speech recognition, cross-lingual transfer, multilingual representations

Contribution Types: Model analysis & interpretability, Approaches to low-resource settings

Languages Studied: English, French, German, Chinese, Japanese, Kabuverdianu, Asturian, Cebuano, Kyrgyz, Sorani Kurdish, Irish

Submission Number: 154