Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ IEEE/ACM Transaction...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
ZENODO; IEEE/ACM Transactions on Audio Speech and Language Processing
Article . 2014 . Peer-reviewed
License: IEEE Copyright
Data sources: ZENODO; Crossref
versions View all 2 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Convolutional Neural Networks for Speech Recognition

Authors: Abdel-Hamid, Ossama; Mohamed, Abdel-Rahman; Jiang, Hui; Deng, Li; Penn, Gerald; Yu, Dong;

Convolutional Neural Networks for Speech Recognition

Abstract

Recently, the hybrid deep neural network (DNN)- hidden Markov model (HMM) has been shown to significantly improve speech recognition performance over the conventional Gaussian mixture model (GMM)-HMM. The performance improvement is partially attributed to the ability of the DNN to model complex correlations in speech features. In this paper, we show that further error rate reduction can be obtained by using convolutional neural networks (CNNs). We first present a concise description of the basic CNN and explain how it can be used for speech recognition. We further propose a limited-weight-sharing scheme that can better model speech features. The special structure such as local connectivity, weight sharing, and pooling in CNNs exhibits some degree of invariance to small shifts of speech features along the frequency axis, which is important to deal with speaker and environment variations. Experimental results show that CNNs reduce the error rate by 6%-10% compared with DNNs on the TIMIT phone recognition and the voice search large vocabulary speech recognition tasks.

Related Organizations
Subjects by Vocabulary

Microsoft Academic Graph classification: Artificial neural network Computer science business.industry Time delay neural network Deep learning Speech recognition Word error rate TIMIT Pattern recognition Mixture model Convolutional neural network Artificial intelligence Hidden Markov model business

Keywords

Acoustics and Ultrasonics, Computational Mathematics, Computer Science (miscellaneous), Electrical and Electronic Engineering

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    1K
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 0.01%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Top 0.1%
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Top 0.1%
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 2K
    download downloads 2K
  • citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    1K
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 0.01%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Top 0.1%
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Top 0.1%
    Powered byBIP!BIP!
  • 2K
    views
    2K
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
1K
Top 0.01%
Top 0.1%
Top 0.1%
2K
2K
hybrid