# token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text

arXiv: https://arxiv.org/abs/2210.16755 · HTML: https://mlsanity.com/paper/2210.16755/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 30 Oct 2022.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [Direct speech-to-speech translation with discrete units](https://mlsanity.com/paper/2107.05604/) (2021)
- [mSLAM: Massively multilingual joint pre-training for speech and text](https://mlsanity.com/paper/2202.01374/) (2022)
- [MAESTRO: Matched Speech Text Representations through Modality Matching](https://mlsanity.com/paper/2204.03409/) (2022)
- [SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training](https://mlsanity.com/paper/2110.10329/) (2021)
- [SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data](https://mlsanity.com/paper/2209.15329/) (2022)
- [SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation](https://mlsanity.com/paper/2205.08180/) (2022)
- [Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training](https://mlsanity.com/paper/2206.10125/) (2022)
- [Genre-conditioned Acoustic Models for Automatic Lyrics Transcription of Polyphonic Music](https://mlsanity.com/paper/2204.03307/) (2022)
- [Multi-stage Speaker Extraction with Utterance and Frame-Level Reference Signals](https://mlsanity.com/paper/2011.09624/) (2020)

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

- [EM-Network: Oracle Guided Self-distillation for Sequence Learning](https://mlsanity.com/paper/2306.10058/) (2023)
- [Few-Shot Spoken Language Understanding via Joint Speech-Text Models](https://mlsanity.com/paper/2310.05919/) (2023)
- [Localizing and Editing Knowledge in Large Audio-Language Models](https://mlsanity.com/paper/2603.14343/) (2026)

## Abstract (arXiv)

Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired speech and text. In this paper, we take the idea of self-supervised pre-training one step further and propose token2vec, a novel joint pre-training framework for unpaired speech and text based on discrete representations of speech. Firstly, due to the distinct characteristics between speech and text modalities, where speech is continuous while text is discrete, we first discretize speech into a sequence of discrete speech tokens to solve the modality mismatch problem. Secondly, to solve the length mismatch problem, where the speech sequence is usually much longer than text sequence, we convert the words of text into phoneme sequences and randomly repeat each phoneme in the sequences. Finally, we feed the discrete speech and text tokens into a modality-agnostic Transformer encoder and pre-train with token-level masking language modeling (tMLM). Experiments show that token2vec is significantly superior to various speech-only pre-training baselines, with up to 17.7% relative WER reduction. Token2vec model is also validated on a non-ASR task, i.e., spoken intent classification, and shows good transferability.