# Textless Speech-to-Speech Translation With Limited Parallel Data

arXiv: https://arxiv.org/abs/2305.15405 · HTML: https://mlsanity.com/paper/2305.15405/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 59 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 30 of 37)

- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [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)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [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)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [Unsupervised Machine Translation Using Monolingual Corpora Only](https://mlsanity.com/paper/1711.00043/) (2017)
- [Speech Resynthesis from Discrete Disentangled Self-Supervised Representations](https://mlsanity.com/paper/2104.00355/) (2021)
- [Direct speech-to-speech translation with discrete units](https://mlsanity.com/paper/2107.05604/) (2021)
- [Unsupervised Speech Recognition](https://mlsanity.com/paper/2105.11084/) (2021)
- [Textless Speech-to-Speech Translation on Real Data](https://mlsanity.com/paper/2112.08352/) (2021)
- [Direct speech-to-speech translation with a sequence-to-sequence model](https://mlsanity.com/paper/1904.06037/) (2019)
- [Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates](https://mlsanity.com/paper/1911.03167/) (2019)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [Translatotron 2: High-quality direct speech-to-speech translation with voice preservation](https://mlsanity.com/paper/2107.08661/) (2021)
- [Towards Building ASR Systems for the Next Billion Users](https://mlsanity.com/paper/2111.03945/) (2021)
- [Towards End-to-end Unsupervised Speech Recognition](https://mlsanity.com/paper/2204.02492/) (2022)
- [UWSpeech: Speech to Speech Translation for Unwritten Languages](https://mlsanity.com/paper/2006.07926/) (2020)
- [Textless Speech Emotion Conversion using Discrete and Decomposed Representations](https://mlsanity.com/paper/2111.07402/) (2021)
- [Towards Building Text-To-Speech Systems for the Next Billion Users](https://mlsanity.com/paper/2211.09536/) (2022)
- [Textless Direct Speech-to-Speech Translation with Discrete Speech Representation](https://mlsanity.com/paper/2211.00115/) (2022)
- [DUB: Discrete Unit Back-translation for Speech Translation](https://mlsanity.com/paper/2305.11411/) (2023)

## Built on by (most cited first, 3 of 3)

- [Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation](https://mlsanity.com/paper/2308.01831/) (2023)
- [Direct Speech-to-Speech Neural Machine Translation: A Survey](https://mlsanity.com/paper/2411.14453/) (2024)
- [TranSentence: Speech-to-speech Translation via Language-agnostic Sentence-level Speech Encoding without Language-parallel Data](https://mlsanity.com/paper/2401.12992/) (2024)

## Abstract (arXiv)

Existing speech-to-speech translation (S2ST) models fall into two camps: they either leverage text as an intermediate step or require hundreds of hours of parallel speech data. Both approaches are incompatible with textless languages or language pairs with limited parallel data. We present PFB, a framework for training textless S2ST models that require just dozens of hours of parallel speech data. We first pretrain a model on large-scale monolingual speech data, finetune it with a small amount of parallel speech data (20-60 hours), and lastly train with an unsupervised backtranslation objective. We train and evaluate our models for English-to-German, German-to-English and Marathi-to-English translation on three different domains (European Parliament, Common Voice, and All India Radio) with single-speaker synthesized speech. Evaluated using the ASR-BLEU metric, our models achieve reasonable performance on all three domains, with some being within 1-2 points of our higher-resourced topline.