Textless Acoustic Model With Self-supervised Distillation For Noise-robust Expressive Speech-to-speech Translation
2024 · Min-Jae Hwang, Ilia Kulikov, Benjamin Peloquin, et al.
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 compe
Authors
(none)
Tags
Stats
Related papers
- Direct Speech-to-speech Translation With Discrete Units (2021)13.97
- Textless Direct Speech-to-speech Translation With Discrete Speech Representation (2022)9.76
- DINO-VITS: Data-efficient Zero-shot TTS With Self-supervised Speaker Verification Loss For Noise Robustness (2023)3.58
- Textless Speech-to-speech Translation On Real Data (2021)13.65
- Enhanced Direct Speech-to-speech Translation Using Self-supervised Pre-training And Data Augmentation (2022)10.85
- Dinosr: Self-distillation And Online Clustering For Self-supervised Speech Representation Learning (2023)0.00
- Unity: Two-pass Direct Speech-to-speech Translation With Discrete Units (2022)9.59
- Preserving Speaker Information In Direct Speech-to-speech Translation With Non-autoregressive Generation And Pretraining (2024)0.00