DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation

Published: 25 Sept 2024, Last Modified: 06 Nov 2024NeurIPS 2024 posterEveryoneRevisionsBibTeXCC BY 4.0
Keywords: speech-to-speech translation, non-autoregressive modeling, diffusion models
Abstract: Non-autoregressive Transformers (NATs) are recently applied in direct speech-to-speech translation systems, which convert speech across different languages without intermediate text data. Although NATs generate high-quality outputs and offer faster inference than autoregressive models, they tend to produce incoherent and repetitive results due to complex data distribution (e.g., acoustic and linguistic variations in speech). In this work, we introduce DiffNorm, a diffusion-based normalization strategy that simplifies data distributions for training NAT models. After training with a self-supervised noise estimation objective, DiffNorm constructs normalized target data by denoising synthetically corrupted speech features. Additionally, we propose to regularize NATs with classifier-free guidance, improving model robustness and translation quality by randomly dropping out source information during training. Our strategies result in a notable improvement of about $+7$ ASR-BLEU for English-Spanish (En-Es) translation and $+2$ ASR-BLEU for English-French (En-Fr) on the CVSS benchmark, while attaining over $14\times$ speedup for En-Es and $5 \times$ speedup for En-Fr translations compared to autoregressive baselines.
Primary Area: Speech and audio
Submission Number: 14299
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview