Long-Form End-to-End Speech Translation via Latent Alignment Segmentation

TL;DR

This paper introduces a novel end-to-end speech translation method that simultaneously segments and translates speech in real-time without supervision, achieving state-of-the-art results across multiple languages.

Contribution

It presents a new segmentation approach integrated into the translation model using ST CTC, enabling low-latency, unsupervised segmentation within the same architecture.

Findings

Achieves state-of-the-art translation quality

Operates without supervision or extra parameters

Works across diverse language pairs and domains

Abstract

Current simultaneous speech translation models can process audio only up to a few seconds long. Contemporary datasets provide an oracle segmentation into sentences based on human-annotated transcripts and translations. However, the segmentation into sentences is not available in the real world. Current speech segmentation approaches either offer poor segmentation quality or have to trade latency for quality. In this paper, we propose a novel segmentation approach for a low-latency end-to-end speech translation. We leverage the existing speech translation encoder-decoder architecture with ST CTC and show that it can perform the segmentation task without supervision or additional parameters. To the best of our knowledge, our method is the first that allows an actual end-to-end simultaneous speech translation, as the same model is used for translation and segmentation at the same time. On a diverse set of language pairs and in- and out-of-domain data, we show that the proposed approach achieves state-of-the-art quality at no additional computational cost.