CoChat

Vector-Quantized Autoregressive Predictive Coding

Open access
Chung, Yu-An, Tang, Hao, Glass, James · 2020 · Interspeech 2020

The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.

Abstract

Autoregressive Predictive Coding (APC), as a self-supervised objective, has enjoyed success in learning representations from large amounts of unlabeled data, and the learned representations are rich for many downstream tasks.However, the connection between low self-supervised loss and strong performance in downstream tasks remains unclear.In this work, we propose Vector-Quantized Autoregressive Predictive Coding (VQ-APC), a novel model that produces quantized representations, allowing us to explicitly control the amount of information encoded in the representations.By studying a sequence of increasingly limited models, we reveal the constituents of the learned representations.In particular, we confirm the presence of information with probing tasks, while showing the absence of information with mutual information, uncovering the model's preference in preserving speech information as its capacity becomes constrained.We find that there exists a point where phonetic and speaker information are amplified to maximize a selfsupervised objective.As a byproduct, the learned codes for a particular model capacity correspond well to English phones.

Overview

Integrity signals

Registry

Crossref · 10.21437/interspeech.2020-1228

Cites

27 of 27 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Cited by

See all 97

Metadata

Authors
Chung, Y.-A., Tang, H., & Glass, J.
Affiliations
MIT Computer Science and Artificial Intelligence Laboratory (US)
Venue
Interspeech 2020
Publisher
ISCA
Published
2020-10-25
Pages
3760-3764
ISSN
2308-457X (ISSN-L)
OpenAlex
W3097286738
Cited by
97
References
27
Citations by year
2026: 2 · 2025: 7 · 2024: 21 · 2023: 18 · 2022: 24 · 2021: 22 · 2020: 3
FWCI
6.31
Type
conference paper
Language
en
Open access
Licence
public-domain
Locations
  • Interspeech (USB) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, public-domain)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
  • Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
Keywords
vector quantization, self-supervised learning, representation learning, probing tasks, mutual information, speech representation, phonetic information, speaker information, model capacity, downstream task performance

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

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.