Direct Speech Translation for Automatic Subtitling
This addresses the problem of efficient and accurate subtitle generation for audiovisual content, representing an incremental improvement by integrating multiple subtasks into one model.
The paper tackles the complex task of automatic subtitling by proposing the first direct speech translation model that generates subtitles with timestamps in a single step, outperforming cascade systems on 7 language pairs and being competitive with production tools on in-domain and out-domain benchmarks.
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 synchronised 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 ST 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.