Paper Info
Title
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
Abstract
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 (960 h) and Libri-light (60,000 h) benchmarks with 10 min, 1 h, 10 h, 100 h, and 960 h 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.(1)(2)
Year
DOI
Venue
2021
10.1109/TASLP.2021.3122291
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
Keywords
DocType
Volume
Predictive models, Data models, Acoustics, Speech processing, Computational modeling, Task analysis, Bit error rate, Self-supervised learning, BERT
Journal
29
Issue
ISSN
Citations 
1
2329-9290
2
PageRank 
References 
Authors
0.42
20
6
Name
Order
Citations
PageRank
Wei-Ning Hsu111513.93
Benjamin Bolte230.78
Yao-Hung Hubert Tsai341.46
Kushal Lakhotia420.42
Ruslan Salakhutdinov512190764.15
Abdel-rahman Mohamed63772266.13