# UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units

arXiv: https://arxiv.org/abs/2212.08055 · HTML: https://mlsanity.com/paper/2212.08055/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 71 of its 108 references that are in the map.
- First posted on arXiv 15 Dec 2022.

## Builds on (most cited first, 30 of 71)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [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)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://mlsanity.com/paper/2008.00401/) (2020)
- [Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges](https://mlsanity.com/paper/1907.05019/) (2019)
- [Speech Resynthesis from Discrete Disentangled Self-Supervised Representations](https://mlsanity.com/paper/2104.00355/) (2021)
- [R-Drop: Regularized Dropout for Neural Networks](https://mlsanity.com/paper/2106.14448/) (2021)
- [CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB](https://mlsanity.com/paper/1911.04944/) (2019)
- [fairseq S2T: Fast Speech-to-Text Modeling with fairseq](https://mlsanity.com/paper/2010.05171/) (2020)
- [End-to-End Attention-based Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1508.04395/) (2015)

## Built on by (most cited first, 30 of 60)

- [Recent Advances in Discrete Speech Tokens: A Review](https://mlsanity.com/paper/2502.06490/) (2025)
- [Autoregressive Diffusion Transformer for Text-to-Speech Synthesis](https://mlsanity.com/paper/2406.05551/) (2024)
- [DASB - Discrete Audio and Speech Benchmark](https://mlsanity.com/paper/2406.14294/) (2024)
- [Intelligible Lip-to-Speech Synthesis with Speech Units](https://mlsanity.com/paper/2305.19603/) (2023)
- [StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning](https://mlsanity.com/paper/2406.03049/) (2024)
- [DUB: Discrete Unit Back-translation for Speech Translation](https://mlsanity.com/paper/2305.11411/) (2023)
- [BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric](https://mlsanity.com/paper/2212.08486/) (2022)
- [High-Fidelity Simultaneous Speech-To-Speech Translation](https://mlsanity.com/paper/2502.03382/) (2025)
- [AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation](https://mlsanity.com/paper/2312.02512/) (2023)
- [Scaling Analysis of Interleaved Speech-Text Language Models](https://mlsanity.com/paper/2504.02398/) (2025)
- [Speech is More Than Words: Do Speech-to-Text Translation Systems Leverage Prosody?](https://mlsanity.com/paper/2410.24019/) (2024)
- [Translatotron 3: Speech to Speech Translation with Monolingual Data](https://mlsanity.com/paper/2305.17547/) (2023)
- [Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation](https://mlsanity.com/paper/2308.01831/) (2023)
- [ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit](https://mlsanity.com/paper/2304.04596/) (2023)
- [TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation](https://mlsanity.com/paper/2405.17809/) (2024)
- [A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation](https://mlsanity.com/paper/2406.06937/) (2024)
- [Back Translation for Speech-to-text Translation Without Transcripts](https://mlsanity.com/paper/2305.08709/) (2023)
- [DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation](https://mlsanity.com/paper/2310.07403/) (2023)
- [GSQA: An End-to-End Model for Generative Spoken Question Answering](https://mlsanity.com/paper/2312.09781/) (2023)
- [Efficient Monotonic Multihead Attention](https://mlsanity.com/paper/2312.04515/) (2023)
- [Exploring In-Image Machine Translation with Real-World Background](https://mlsanity.com/paper/2505.15282/) (2025)
- [PRIM: Towards Practical In-Image Multilingual Machine Translation](https://mlsanity.com/paper/2509.05146/) (2025)
- [UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice](https://mlsanity.com/paper/2509.21144/) (2025)
- [Duplex Diffusion Models Improve Speech-to-Speech Translation](https://mlsanity.com/paper/2305.12628/) (2023)
- [Multilingual Speech-to-Speech Translation into Multiple Target Languages](https://mlsanity.com/paper/2307.08655/) (2023)
- [TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages](https://mlsanity.com/paper/2402.16021/) (2024)
- [Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation](https://mlsanity.com/paper/2406.02733/) (2024)
- [Towards Practical and Efficient Image-to-Speech Captioning with Vision-Language Pre-training and Multi-modal Tokens](https://mlsanity.com/paper/2309.08531/) (2023)
- [Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?](https://mlsanity.com/paper/2406.07289/) (2024)
- [Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens](https://mlsanity.com/paper/2602.16687/) (2026)

## Abstract (arXiv)

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, predicting discrete units achieves 2.51x decoding speed-up compared to that case.