# DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT

arXiv: https://arxiv.org/abs/2110.01900 · HTML: https://mlsanity.com/paper/2110.01900/

## Key facts

- Cited by 144 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 36 references that are in the map.
- First posted on arXiv 5 Oct 2021.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders](https://mlsanity.com/paper/1910.12638/) (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)
- [Multi-task self-supervised learning for Robust Speech Recognition](https://mlsanity.com/paper/2001.09239/) (2020)
- [Unsupervised pretraining transfers well across languages](https://mlsanity.com/paper/2002.02848/) (2020)
- [Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks](https://mlsanity.com/paper/1904.03416/) (2019)
- [DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization](https://mlsanity.com/paper/2012.06659/) (2020)
- [Effectiveness of self-supervised pre-training for speech recognition](https://mlsanity.com/paper/1911.03912/) (2019)
- [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)
- [PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition](https://mlsanity.com/paper/2106.05933/) (2021)
- [Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies](https://mlsanity.com/paper/2011.00406/) (2020)
- [LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech](https://mlsanity.com/paper/2104.11462/) (2021)
- [Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation Learning](https://mlsanity.com/paper/2010.13991/) (2020)
- [Wav2vec-C: A Self-supervised Model for Speech Representation Learning](https://mlsanity.com/paper/2103.08393/) (2021)
- [Improved Speech Representations with Multi-Target Autoregressive Predictive Coding](https://mlsanity.com/paper/2004.05274/) (2020)
- [Shrinking Bigfoot: Reducing wav2vec 2.0 footprint](https://mlsanity.com/paper/2103.15760/) (2021)

## Built on by (most cited first, 30 of 144)

- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling](https://mlsanity.com/paper/2311.00430/) (2023)
- [SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models](https://mlsanity.com/paper/2308.16692/) (2023)
- [SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities](https://mlsanity.com/paper/2203.06849/) (2022)
- [OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer](https://mlsanity.com/paper/2401.16658/) (2024)
- [What Do Self-Supervised Speech Models Know About Words?](https://mlsanity.com/paper/2307.00162/) (2023)
- [BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning](https://mlsanity.com/paper/2206.08657/) (2022)
- [LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT](https://mlsanity.com/paper/2203.15610/) (2022)
- [On the Utility of Self-supervised Models for Prosody-related Tasks](https://mlsanity.com/paper/2210.07185/) (2022)
- [Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data](https://mlsanity.com/paper/2309.13876/) (2023)
- [A Large-Scale Evaluation of Speech Foundation Models](https://mlsanity.com/paper/2404.09385/) (2024)
- [DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning](https://mlsanity.com/paper/2305.10005/) (2023)
- [OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification](https://mlsanity.com/paper/2402.12654/) (2024)
- [DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models](https://mlsanity.com/paper/2305.17651/) (2023)
- [Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models](https://mlsanity.com/paper/2207.06867/) (2022)
- [Structured Pruning of Self-Supervised Pre-trained Models for Speech Recognition and Understanding](https://mlsanity.com/paper/2302.14132/) (2023)
- [SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model](https://mlsanity.com/paper/2210.00705/) (2022)
- [Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?](https://mlsanity.com/paper/2306.00452/) (2023)
- [SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2210.08634/) (2022)
- [Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling](https://mlsanity.com/paper/2202.03543/) (2022)
- [FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning](https://mlsanity.com/paper/2207.00555/) (2022)
- [Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering](https://mlsanity.com/paper/2305.11072/) (2023)
- [Reducing Barriers to Self-Supervised Learning: HuBERT Pre-training with Academic Compute](https://mlsanity.com/paper/2306.06672/) (2023)
- [AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models](https://mlsanity.com/paper/2506.05140/) (2025)
- [Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads](https://mlsanity.com/paper/2308.14456/) (2023)
- [On the social bias of speech self-supervised models](https://mlsanity.com/paper/2406.04997/) (2024)
- [Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study](https://mlsanity.com/paper/2303.06740/) (2023)
- [Task-Agnostic Structured Pruning of Speech Representation Models](https://mlsanity.com/paper/2306.01385/) (2023)
- [Accelerating Transducers through Adjacent Token Merging](https://mlsanity.com/paper/2306.16009/) (2023)

## Abstract (arXiv)

Self-supervised speech representation learning methods like wav2vec 2.0 and Hidden-unit BERT (HuBERT) leverage unlabeled speech data for pre-training and offer good representations for numerous speech processing tasks. Despite the success of these methods, they require large memory and high pre-training costs, making them inaccessible for researchers in academia and small companies. Therefore, this paper introduces DistilHuBERT, a novel multi-task learning framework to distill hidden representations from a HuBERT model directly. This method reduces HuBERT's size by 75% and 73% faster while retaining most performance in ten different tasks. Moreover, DistilHuBERT required little training time and data, opening the possibilities of pre-training personal and on-device SSL models for speech.