Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
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 hiddenlayer 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 largevocabulary 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 asignificant 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
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" }