End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation
| Type of publication: | Conference paper |
| Citation: | Juan_EMNLP_2023 |
| Publication status: | Published |
| Booktitle: | The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP) |
| Series: | 1 |
| Volume: | 1 |
| Number: | 1 |
| Year: | 2023 |
| Month: | December |
| Location: | Singapore |
| URL: | https://arxiv.org/abs/2311.006... |
| Abstract: | Conventional speech-to-text translation (ST) systems are trained on single-speaker utterances, and they may not generalize to real-life scenarios where the audio contains conversations by multiple speakers. In this paper, we tackle single-channel multi-speaker conversational ST with an end-to-end and multi-task training model, named Speaker-Turn Aware Conversational Speech Translation, that combines automatic speech recognition, speech translation and speaker turn detection using special tokens in a serialized labeling format. We run experiments on the Fisher-CALLHOME corpus, which we adapted by merging the two single-speaker channels into one multi-speaker channel, thus representing the more realistic and challenging scenario with multi-speaker turns and cross-talk. Experimental results across single- and multi-speaker conditions and against conventional ST systems, show that our model outperforms the reference systems on the multi-speaker condition, while attaining comparable performance on the single-speaker condition. We release scripts for data processing and model training. |
| Keywords: | |
| Projects |
Idiap |
| Authors | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
