CoChat

Hubert: How Much Can a Bad Teacher Benefit ASR Pre-Training?

Hsu, Wei-Ning, Tsai, Yao-Hung Hubert, Bolte, Benjamin, Salakhutdinov, Ruslan, Mohamed, Abdelrahman · 2021 · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Cited by 119

The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.

Abstract

Compared to vision and language applications, self-supervised pre-training approaches for ASR are challenged by three unique problems: (1) There are multiple sound units in each input utterance, (2) With audio-only pre-training, there is no lexicon of sound units, and (3) Sound units have variable lengths with no explicit segmentation. In this paper, we propose the Hidden-Unit BERT (HUBERT) model which utilizes a cheap k-means clustering step to provide aligned target labels for pre-training of a BERT model. A key ingredient of our approach is applying the predictive loss over the masked regions only. This allows the pre-training stage to benefit from the consistency of the unsupervised teacher rather that its intrinsic quality. Starting with a simple k-means teacher of 100 cluster, and using two iterations of clustering, the HUBERT model matches the state-of-the-art wav2vec 2.0 performance on the ultra low-resource Libri-light 10h, 1h, 10min supervised subsets.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icassp39728.2021.9414460

Cites

17 of 17 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 17 references

Cited by

See all 119

Metadata

Authors
Hsu, W.-N., Tsai, Y.-H. H., Bolte, B., Salakhutdinov, R., & Mohamed, A.
Venue
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher
IEEE
Published
2021-06-06
Pages
6533-6537
ISSN
1520-6149 (ISSN-L)
OpenAlex
W3160799772
Cited by
119
References
17
FWCI
12.59
Type
conference paper
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Hubert: How Much Can a Bad Teacher Benefit ASR Pre-Training? https://app.cochat.ai/papers/10.1109/icassp39728.2021.9414460
The paper
Hsu, W.-N., Tsai, Y.-H. H., Bolte, B., Salakhutdinov, R., & Mohamed, A. (2021). Hubert: How Much Can a Bad Teacher Benefit ASR Pre-Training? ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp39728.2021.9414460

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.