Detail publikace

Improved MLP Structures for Data-Driven Feature Extraction for ASR

ZHU, Q., CHEN, B., GRÉZL, F., MORGAN, N.

Originální název

Improved MLP Structures for Data-Driven Feature Extraction for ASR

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

feature extraction, MLP structure, time-frequency patterns

Autoři

ZHU, Q., CHEN, B., GRÉZL, F., MORGAN, N.

Rok RIV

2005

Vydáno

29. 9. 2005

Místo

Lisabon

ISSN

1018-4074

Periodikum

European Conference EUROSPEECH

Stát

Švýcarská konfederace

Strany od

2129

Strany do

2132

Strany počet

4

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="4",
  address="Lisabon",
  issn="1018-4074"
}