Direct Speech Translation for Automatic Subtitling

Transactions of the Association for Computational Linguistics, vol. 11, pp. 1355–1376

Abstract

Abstract Automatic subtitling is the task of automatically translating the speech of audiovisual content into short pieces of timed text, i.e., subtitles and their corresponding timestamps. The generated subtitles need to conform to space and time requirements, while being synchronized with the speech and segmented in a way that facilitates comprehension. Given its considerable complexity, the task has so far been addressed through a pipeline of components that separately deal with transcribing, translating, and segmenting text into subtitles, as well as predicting timestamps. In this paper, we propose the first direct speech translation model for automatic subtitling that generates subtitles in the target language along with their timestamps with a single model. Our experiments on 7 language pairs show that our approach outperforms a cascade system in the same data condition, also being competitive with production tools on both in-domain and newly released out-domain benchmarks covering new scenarios.

Authors 6

1. Sara Papi corresponding

   University of Trento · Fondazione Bruno Kessler

   Affiliation as printed

   Fondazione Bruno Kessler, Trento, Italy. spapi@fbk.eu

   University of Trento, Trento, Italy

2. Marco Gaido corresponding

   University of Trento · Fondazione Bruno Kessler

   Affiliation as printed

   Fondazione Bruno Kessler, Trento, Italy. mgaido@fbk.eu

   University of Trento, Trento, Italy

3. Alina Karakanta Aachen

   Leiden University

   Affiliation as printed

   Leiden University Centre for Linguistics, Leiden, The Netherlands

4. Mauro Cettolo corresponding

   Fondazione Bruno Kessler

   Affiliation as printed

   Fondazione Bruno Kessler, Trento, Italy. cettolo@fbk.eu

5. Matteo Negri corresponding

   Fondazione Bruno Kessler

   Affiliation as printed

   Fondazione Bruno Kessler, Trento, Italy. negri@fbk.eu

6. Marco Turchi
   Affiliation as printed

   Zoom Video Communications, Karlsruhe, Germany