# MTP-S2UT: Enhancing Speech-to-Speech Translation Quality with Multi-token Prediction

arXiv: https://arxiv.org/abs/2510.10003 · HTML: https://mlsanity.com/paper/2510.10003/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 22 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 17 of 17)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Better & Faster Large Language Models via Multi-token Prediction](https://mlsanity.com/paper/2404.19737/) (2024)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot](https://mlsanity.com/paper/2412.02612/) (2024)
- [Direct speech-to-speech translation with discrete units](https://mlsanity.com/paper/2107.05604/) (2021)
- [SeamlessM4T: Massively Multilingual & Multimodal Machine Translation](https://mlsanity.com/paper/2308.11596/) (2023)
- [Direct speech-to-speech translation with a sequence-to-sequence model](https://mlsanity.com/paper/1904.06037/) (2019)
- [WavChat: A Survey of Spoken Dialogue Models](https://mlsanity.com/paper/2411.13577/) (2024)
- [CVSS Corpus and Massively Multilingual Speech-to-Speech Translation](https://mlsanity.com/paper/2201.03713/) (2022)
- [UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units](https://mlsanity.com/paper/2212.08055/) (2022)
- [StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning](https://mlsanity.com/paper/2406.03049/) (2024)
- [VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation](https://mlsanity.com/paper/2504.04060/) (2025)

## Built on by (most cited first, 1 of 1)

- [MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration](https://mlsanity.com/paper/2604.14889/) (2026)

## Abstract (arXiv)

Current direct speech-to-speech translation methods predominantly employ speech tokens as intermediate representations. However, a single speech token is not dense in semantics, so we generally need multiple tokens to express a complete semantic unit. To address this limitation, we introduce multi-token prediction (MTP) loss into speech-to-unit translation (S2UT) models, enabling models to predict multiple subsequent tokens at each position, thereby capturing more complete semantics and enhancing information density per position. Initial MTP implementations apply the loss at the final layer, which improves output representation but initiates information enrichment too late. We hypothesize that advancing the information enrichment process to intermediate layers can achieve earlier and more effective enhancement of hidden representation. Consequently, we propose MTP-S2UT loss, applying MTP loss to hidden representation where CTC loss is computed. Experiments demonstrate that all MTP loss variants consistently improve the quality of S2UT translation, with MTP-S2UT achieving the best performance.