Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation

Min-Jae Hwang, Ilia Kulikov, Benjamin Peloquin, Hongyu Gong, Peng-Jen Chen, Ann Lee


Abstract
In this paper, we propose a textless acoustic model with a self-supervised distillation strategy for noise-robust expressive speech-to-speech translation (S2ST).Recently proposed expressive S2ST systems have achieved impressive expressivity preservation performances by cascading unit-to-speech (U2S) generator to the speech-to-unit translation model. However, these systems are vulnerable to the presence of noise in input speech, which is an assumption in real-world translation scenarios. To address this limitation, we propose a U2S generator that incorporates a distillation with no label (DINO) self-supervised training strategy into it’s pretraining process.Because the proposed method captures noise-agnostic expressivity representation, it can generate qualified speech even in noisy environment.Objective and subjective evaluation results verified that the proposed method significantly improved the performance of the expressive S2ST system in noisy environments while maintaining competitive performance in clean environments.
Anthology ID:
2024.findings-acl.917
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15524–15541
Language:
URL:
https://aclanthology.org/2024.findings-acl.917
DOI:
Bibkey:
Cite (ACL):
Min-Jae Hwang, Ilia Kulikov, Benjamin Peloquin, Hongyu Gong, Peng-Jen Chen, and Ann Lee. 2024. Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation. In Findings of the Association for Computational Linguistics ACL 2024, pages 15524–15541, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation (Hwang et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.917.pdf