HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
HuBERT: самообучение представлений речи посредством маскированного предсказания скрытых единиц
2021-01-01
SCID: 54.1/pvtmmb5h
Discuss with AI
HuBERThidden unitsk-means clusteringmasked predictionself-supervised speech representation learning
Figures from the paper
Abstract (AI)
Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the pre-training phase, and (3) sound units have variable lengths with no explicit segmentation. To deal with these three problems, we propose the Hidden-Unit BERT (HuBERT) approach for self-supervised speech representation learning, which utilizes an offline clustering step to provide aligned target labels for a BERT-like prediction loss. A key ingredient of our approach is applying the prediction loss over the masked regions only, which forces the model to learn a combined acoustic and language model over the continuous inputs. HuBERT relies primarily on the consistency of the unsupervised clustering step rather than the intrinsic quality of the assigned cluster labels. Starting with a simple k-means teacher of 100 clusters, and using two iterations of clustering, the HuBERT model either matches or improves upon the state-of-the-art wav2vec 2.0 performance on the Librispeech (960h) and Libri-light (60,000h) benchmarks with 10min, 1h, 10h, 100h, and 960h fine-tuning subsets. Using a 1B parameter model, HuBERT shows up to 19% and 13% relative WER reduction on the more challenging dev-other and test-other evaluation subsets.
Key Findings
1
A 1B-parameter HuBERT model achieves up to 19% relative WER reduction on dev-other and 13% on test-other.
2
Applying the prediction loss only to masked regions encourages learning a joint acoustic and language model over continuous speech inputs.
3
HuBERT addresses multiple sound units, absent pretraining lexicons, and variable unit lengths using offline clustering to generate aligned targets for masked prediction.
4
HuBERT depends primarily on consistency of unsupervised cluster assignments rather than the intrinsic quality of cluster labels.
5
With a 100-cluster k-means teacher and two clustering iterations, HuBERT matches or exceeds wav2vec 2.0 on Librispeech and Libri-light across multiple fine-tuning data sizes.
Research Object
speech representations learned from unlabeled continuous speech inputs
Research Subject
the masked-prediction learning behavior and recognition performance of the representations, including acoustic–language modeling and WER
Publication Details
Publication Date
2021-01-01
Journal
IEEE/ACM Transactions on Audio Speech and Language Processing
Publisher
Institute of Electrical and Electronics Engineers
ISSN
2329-9290
Cited by
5978
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai4
Cited by7
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing2022
MM-LLMs: Recent Advances in MultiModal Large Language Models2024
Self-Supervised Speech Representation Learning: A Review2022
A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges2024
Speaker Normalization for Self-Supervised Speech Emotion Recognition2022
Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?2022
Adapting Self-Supervised Models to Multi-Talker Speech Recognition Using Speaker Embeddings2023