Isometric MT: Neural Machine Translation for Automatic Dubbing

TL;DR

This paper presents a novel neural machine translation method called Isometric MT that directly generates length-matched translations for automatic dubbing, improving quality without complex reranking.

Contribution

It introduces a self-learning transformer model that produces length-controlled translations without needing multiple hypotheses or reranking.

Findings

Outperforms existing length-control methods in automatic and manual evaluations.

Effective across four language pairs with publicly available benchmarks.

Maintains translation quality while closely matching source length.

Abstract

Automatic dubbing (AD) is among the machine translation (MT) use cases where translations should match a given length to allow for synchronicity between source and target speech. For neural MT, generating translations of length close to the source length (e.g. within +-10% in character count), while preserving quality is a challenging task. Controlling MT output length comes at a cost to translation quality, which is usually mitigated with a two step approach of generating N-best hypotheses and then re-ranking based on length and quality. This work introduces a self-learning approach that allows a transformer model to directly learn to generate outputs that closely match the source length, in short Isometric MT. In particular, our approach does not require to generate multiple hypotheses nor any auxiliary ranking function. We report results on four language pairs (English - French, Italian, German, Spanish) with a publicly available benchmark. Automatic and manual evaluations show that our method for Isometric MT outperforms more complex approaches proposed in the literature.