Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation

TL;DR

This paper introduces an end-to-end speech-to-text translation model that bypasses source transcription, promising to simplify data collection especially for under-resourced languages, demonstrated on a small French-English dataset.

Contribution

It presents the first end-to-end speech-to-text translation model that does not rely on source language transcription during training or decoding.

Findings

Promising results on a French-English synthetic corpus.

Potential to simplify data collection for unwritten languages.

Demonstrates feasibility of direct speech-to-text translation.

Abstract

This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language transcription during learning or decoding. We propose a model for direct speech-to-text translation, which gives promising results on a small French-English synthetic corpus. Relaxing the need for source language transcription would drastically change the data collection methodology in speech translation, especially in under-resourced scenarios. For instance, in the former project DARPA TRANSTAC (speech translation from spoken Arabic dialects), a large effort was devoted to the collection of speech transcripts (and a prerequisite to obtain transcripts was often a detailed transcription guide for languages with little standardized spelling). Now, if end-to-end approaches for speech-to-text translation are successful, one might consider collecting data by asking bilingual speakers to directly utter speech in the source language from target language text utterances. Such an approach has the advantage to be applicable to any unwritten (source) language.