Expressive speech-to-speech translation (S2ST) aims to transfer prosodic attributes of source speech to target speech while maintaining translation accuracy. Existing research in expressive S2ST is limited, typically focusing on a single expressivity aspect at a time. Likewise, this research area lacks standard evaluation protocols and well-curated benchmark datasets. In this work, we propose a holistic cascade system for expressive S2ST, combining multiple prosody transfer techniques previously considered only in isolation. We curate a benchmark expressivity test set in the TV series domain and explored a second dataset in the audiobook domain. Finally, we present a human evaluation protocol to assess multiple expressive dimensions across speech pairs. Experimental results indicate that bi-lingual annotators can assess the quality of expressive preservation in S2ST systems, and the holistic modeling approach outperforms single-aspect systems. Audio samples can be accessed through our demo webpage: https://facebookresearch.github.io/speech_translation/cascade_expressive_s2st.
|Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
|Published - 2023
|48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 - Rhodes Island, Greece
Duration: 4 Jun 2023 → 10 Jun 2023
Bibliographical notePublisher Copyright:
© 2023 IEEE.
- Expressive speech-to-speech translation
- controllable text-to-speech
- prosody transfer