Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 312

The DOI matches its Crossref record; 64 of the 64 references it cites were found in a registry or an index.

TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech

Open access
Liu, Andy T., Li, Shang-Wen, Lee, Hung-yi·2021·IEEE/ACM Transactions on Audio, Speech, and Language Processing

Abstract

We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction, autoregressive prediction, or masked reconstruction. Unlike previous methods, we use alteration along three orthogonal axes to pre-train Transformer Encoders on a large amount of unlabeled speech. The model learns through the reconstruction of acoustic frames from their altered counterpart, where we use a stochastic policy to alter along various dimensions: time, frequency, and magnitude. TERA can be used for speech representations extraction or fine-tuning with downstream models. We evaluate TERA on several downstream tasks, including phoneme classification, keyword spotting, speaker recognition, and speech recognition. We present a large-scale comparison of various self-supervised models. TERA achieves strong performance in the comparison by improving upon surface features and outperforming previous models. In our experiments, we study the effect of applying different alteration techniques, pre-training on more data, and pre-training on various features. We analyze different model sizes and find that smaller models are strong representation learners than larger models, while larger models are more effective for downstream fine-tuning than smaller models. Furthermore, we show the proposed method is transferable to downstream datasets not used in pre-training.

Overview

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1109/taslp.2021.3095662

Cites

64 of 64 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.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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 64 references

Research works printed but not linked: 2

  1. lopes, 2011, Phone recognition on the timit database, Speech Technol /Book, 1, 285
  2. mikolov, 2013, Proc 1st Int Conf Learn Representations

Cited by

See all 312

Metadata

Authors
Liu, A. T., Li, S.-W., & Lee, H.-Y.
Venue
IEEE/ACM Transactions on Audio, Speech, and Language Processing
Published
2021
Volume
29
Pages
2351-2366
ISSN
  • 2329-9290 (ISSN-L)
  • 2329-9304
OpenAlex
W3041561163
Cited by
312
References
64
FWCI
22.23
Type
journal article
Language
en
Open access
green
Funders
  • National Science Council (110-2628-E-002-001)
  • National Taiwan University
  • ASUS AICS

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: TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech. https://app.cochat.ai/papers/10.1109/taslp.2021.3095662
The paper
Liu, A. T., Li, S.-W., & Lee, H.-Y. (2021). TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech. IEEE/ACM Transactions on Audio, Speech, and Language Processing. https://doi.org/10.1109/taslp.2021.3095662

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.