CoChat

Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups

The DOI matches its Crossref record; 68 of the 71 references it cites were found in a registry or an index.

Abstract

Most current speech recognition systems use hidden Markov models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well each state of each HMM fits a frame or a short window of frames of coefficients that represents the acoustic input. An alternative way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition benchmarks, sometimes by a large margin. This article provides an overview of this progress and represents the shared views of four research groups that have had recent successes in using DNNs for acoustic modeling in speech recognition.

Overview

Integrity signals

Registry

Crossref · 10.1109/msp.2012.2205597

Cites

68 of 68 references verified0 citation errors · 0 not checkable

Statistics

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

Verification

Claims the paper makes

This paper’s full text isn’t openly available, 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

Show all 68 references

Research works printed but not linked: 5

  1. sainath, 2011, Improvements in using deep belief networks for large vocabulary continuous speech recognition, Speech and Language Algorithm Group IBM Yorktown Heights NY Tech Rep UTML TR 2010-003
  2. rifai, 0, Contractive autoencoders: Explicit invariance during feature extraction, Proc 28th Int Conf Machine Learning, 833
  3. yu, 2011, Discriminative pretraining of deep neural networks, U S Patent Filing
  4. mohamed, 0, Deep belief networks for phone recognition, Proc NIPS Workshop Deep Learning for Speech Recognition and Related Applications
  5. pearl, 1988, Probabilistic Inference in Intelligent Systems Networks of Plausible Inference

Cited by

Metadata

Authors
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., & Kingsbury, B.
Affiliations
  • University of Toronto (CA)
  • University of Waterloo (CA)
  • Microsoft (United States) (US)
  • Google (United States) (US)
  • IBM (United States) (US)
  • Michigan State University (US)
Venue
IEEE Signal Processing Magazine
Published
2012-11
Volume
29
Issue
6
Pages
82-97
ISSN
1053-5888 (ISSN-L)
OpenAlex
W2160815625
Cited by
10,260
References
71
Citations by year
2026: 253 · 2025: 526 · 2024: 610 · 2023: 696 · 2022: 837 · 2021: 978 · 2020: 1232 · 2019: 1313 · 2018: 1220 · 2017: 967 · 2016: 712 · 2015: 498 · 2014: 276 · 2013: 128 · 2012: 9
FWCI
284.71
Type
journal article
Language
en
Open access
closed
Locations
IEEE Signal Processing Magazine (publishedVersion)
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 › Speech and dialogue systems
Keywords
deep neural network, acoustic modeling, speech recognition, hidden Markov models, Gaussian mixture model, feedforward neural networks, posterior probability

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.