Result Details

Improved MLP Structures for Data-Driven Feature Extraction for ASR

ZHU, Q.; CHEN, B.; GRÉZL, F.; MORGAN, N. Improved MLP Structures for Data-Driven Feature Extraction for ASR. Interspeech'2005 - Eurospeech - 9th European Conference on Speech Communication and Technology. European Conference EUROSPEECH. Lisabon: 2005. p. 2129-2132. ISSN: 1018-4074.
Type
conference paper
Language
English
Authors
Zhu Qifeng
Chen Barry, Msc.
Grézl František, Ing., Ph.D., FIT (FIT), DCGM (FIT)
Morgan Nelson, prof.
Abstract

Data-driven feature extraction using improved MLP structure for ASR. Four-layer MLPs are used in this feature extraction. It is shown that the the first hidden layer of a four-layer MLP is able to detect some basic patterns from the time-frequency plane.

Keywords

feature extraction, MLP structure, time-frequency patterns

Annotation

In this paper, we present our recent progress on multi-layer perceptron (MLP) based data-driven feature extraction using improved MLP structures. Four-layer MLPs are used in this study. Different signal processing methods are applied before the input layer of the MLP. We show that the first hidden
layer of a four-layer MLP is able to detect some basic patterns from the time-frequency plane. KLT-based dimension reduction along time is applied as a modulation frequency filter. The new feature extraction was tested on a large
vocabulary continuous speech recognition (LVCSR) task using the NIST 2001 evaluation set. We achieved 11.6% relative word error rate (WER) reduction compared to the traditional PLP-based baseline feature. This is also a
significant improvement compared to our previously published results on the same task using MLP-based features with three-layer MLPs.

Published
2005
Pages
2129–2132
Journal
European Conference EUROSPEECH, ISSN 1018-4074
Proceedings
Interspeech'2005 - Eurospeech - 9th European Conference on Speech Communication and Technology
Conference
Eurospeech 2005 - Lisboa 9th European conference on speech communication and technology
Place
Lisabon
BibTeX 
@inproceedings{BUT18257,
  author="Qifeng {Zhu} and Barry {Chen} and František {Grézl} and Nelson {Morgan}",
  title="Improved MLP Structures for Data-Driven Feature Extraction for ASR",
  booktitle="Interspeech'2005 - Eurospeech - 9th European Conference on Speech Communication and Technology",
  year="2005",
  journal="European Conference EUROSPEECH",
  pages="2129--2132",
  address="Lisabon",
  issn="1018-4074"
}
Projects
Augmented Multi-party Interaction, EU, Sixth Framework programme, 506811-AMI, start: 2004-01-01, end: 2006-12-31, completed
New trends in research and application of voice technology, GACR, Standardní projekty, GA102/05/0278, start: 2005-01-01, end: 2007-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top