# Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation

arXiv: https://arxiv.org/abs/2306.08920 · HTML: https://mlsanity.com/paper/2306.08920/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 15 Jun 2023.

## Builds on (most cited first, 30 of 31)

- [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)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [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)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Speech Model Pre-training for End-to-End Spoken Language Understanding](https://mlsanity.com/paper/1904.03670/) (2019)
- [TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech](https://mlsanity.com/paper/2007.06028/) (2020)
- [An Unsupervised Autoregressive Model for Speech Representation Learning](https://mlsanity.com/paper/1904.03240/) (2019)
- [Unsupervised Speech Recognition](https://mlsanity.com/paper/2105.11084/) (2021)
- [Vector-Quantized Autoregressive Predictive Coding](https://mlsanity.com/paper/2005.08392/) (2020)
- [Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition](https://mlsanity.com/paper/1912.01679/) (2019)
- [Towards End-to-end Unsupervised Speech Recognition](https://mlsanity.com/paper/2204.02492/) (2022)
- [Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings](https://mlsanity.com/paper/1804.00316/) (2018)
- [Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning](https://mlsanity.com/paper/2212.05301/) (2022)
- [Speech Pre-training with Acoustic Piece](https://mlsanity.com/paper/2204.03240/) (2022)
- [Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training](https://mlsanity.com/paper/2206.10125/) (2022)
- [MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets](https://mlsanity.com/paper/2211.07321/) (2022)
- [CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning](https://mlsanity.com/paper/2210.04062/) (2022)
- [CTCBERT: Advancing Hidden-unit BERT with CTC Objectives](https://mlsanity.com/paper/2210.08603/) (2022)

## Built on by (most cited first, 7 of 7)

- [emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation](https://mlsanity.com/paper/2312.15185/) (2023)
- [Leveraging Speech PTM, Text LLM, and Emotional TTS for Speech Emotion Recognition](https://mlsanity.com/paper/2309.10294/) (2023)
- [Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2309.13860/) (2023)
- [Iterative refinement, not training objective, makes HuBERT behave differently from wav2vec 2.0](https://mlsanity.com/paper/2508.08110/) (2025)
- [VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining](https://mlsanity.com/paper/2505.21527/) (2025)
- [MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery](https://mlsanity.com/paper/2512.19612/) (2025)
- [Cluster Assignments in Soft Targets Shape Speech Representations: Evidence from S-JEPA](https://mlsanity.com/paper/2608.19084/) (2026)

## Abstract (arXiv)

The excellent generalization ability of self-supervised learning (SSL) for speech foundation models has garnered significant attention. HuBERT is a successful example that utilizes offline clustering to convert speech features into discrete units for a masked language modeling pretext task. However, simply clustering features as targets by k-means does not fully inspire the model's performance. In this work, we present an unsupervised method to improve SSL targets. Two models are proposed, MonoBERT and PolyBERT, which leverage context-independent and context-dependent phoneme-based units for pre-training. Our models outperform other SSL models significantly on the LibriSpeech benchmark without the need for iterative re-clustering and re-training. Furthermore, our models equipped with context-dependent units even outperform target-improvement models that use labeled data during pre-training. How we progressively improve the unit discovery process is demonstrated through experiments.