Textless Streaming Speech-to-speech Translation Using Semantic Speech Tokens

Abstract

Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech translation model that outputs discrete speech tokens in a low-latency streaming fashion. This approach eliminates the need for generating text output first, followed by machine translation (MT) and text-to-speech (TTS) systems. The produced speech tokens can be directly used to generate a speech signal with low latency by utilizing an acoustic language model (LM) to obtain acoustic tokens and an audio codec model to retrieve the waveform. Experimental results show that the proposed method outperforms other existing approaches and achieves state-of-the-art results for streaming translation in terms of BLEU, average latency, and BLASER 2.0 scores for multiple language pairs using the CVSS-C dataset as a benchmark.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyzhao2024textless

Related papers

• Transduce And Speak: Neural Transducer For Text-to-speech With Semantic Token Prediction (2023)0.00
• High Fidelity Text-to-speech Via Discrete Tokens Using Token Transducer And Group Masked Language Model (2024)4.52
• Utilizing Neural Transducers For Two-stage Text-to-speech Via Semantic Token Prediction (2024)0.00
• Tight Integrated End-to-end Training For Cascaded Speech Translation (2020)8.35
• When End-to-end Is Overkill: Rethinking Cascaded Speech-to-text Translation (2025)0.00
• Livespeech: Low-latency Zero-shot Text-to-speech Via Autoregressive Modeling Of Audio Discrete Codes (2024)5.84
• Learning When To Translate For Streaming Speech (2021)9.23
• Token-level Serialized Output Training For Joint Streaming ASR And ST Leveraging Textual Alignments (2023)0.00