Unity: Two-pass Direct Speech-to-speech Translation With Discrete Units

Abstract

Direct speech-to-speech translation (S2ST), in which all components can be optimized jointly, is advantageous over cascaded approaches to achieve fast inference with a simplified pipeline. We present a novel two-pass direct S2ST architecture, UnitY, which first generates textual representations and predicts discrete acoustic units subsequently. We enhance the model performance by subword prediction in the first-pass decoder, advanced two-pass decoder architecture design and search strategy, and better training regularization. To leverage large amounts of unlabeled text data, we pre-train the first-pass text decoder based on the self-supervised denoising auto-encoding task. Experimental evaluations on benchmark datasets at various data scales demonstrate that UnitY outperforms a single-pass speech-to-unit translation model by 2.5-4.2 ASR-BLEU with 2.83x decoding speed-up. We show that the proposed methods boost the performance even when predicting spectrogram in the second pass. However

Stats

• citations18
• S2 citations—
• github stars0
• HF likes0
• heat score9.59
• arxiv keyinaguma2022unity

Related papers

• Direct Speech-to-speech Translation With Discrete Units (2021)13.97
• Enhanced Direct Speech-to-speech Translation Using Self-supervised Pre-training And Data Augmentation (2022)10.85
• Preserving Speaker Information In Direct Speech-to-speech Translation With Non-autoregressive Generation And Pretraining (2024)0.00
• Joint Pre-training With Speech And Bilingual Text For Direct Speech To Speech Translation (2022)7.81
• A Unit-based System And Dataset For Expressive Direct Speech-to-speech Translation (2025)2.26
• Daspeech: Directed Acyclic Transformer For Fast And High-quality Speech-to-speech Translation (2023)5.24
• Transpeech: Speech-to-speech Translation With Bilateral Perturbation (2022)0.00
• Speech-to-speech Translation With Discrete-unit-based Style Transfer (2023)0.00