Článek ve sborníku konference

 
Zhu, Q., Chen, B., Grézl, F., Morgan, N.: Improved MLP Structures for Data-Driven Feature Extraction for ASR, In: Interspeech'2005 - Eurospeech - 9th European Conference on Speech Communication and Technology, Lisabon, PT, 2005, s. 4, ISSN 1018-4074
Jazyk publikace:angličtina
Název publikace:Improved MLP Structures for Data-Driven Feature Extraction for ASR
Název (cs):Vylepšená struktura MLP pro datově-řízenou extrakci píznaků pro ASR
Strany:4
Sborník:Interspeech'2005 - Eurospeech - 9th European Conference on Speech Communication and Technology
Konference:Eurospeech 2005 - Lisboa 9th European conference on speech communication and technology
Místo vydání:Lisabon, PT
Rok:2005
Časopis:European Speech Communication, CZ
ISSN:1018-4074
Klíčová slova
feature extraction, MLP structure, time-frequency patterns
Anotace
Datově-řízená extrakce příznaků s použitím vylepšené struktury MLP pro ASR. V této extrakci příznaků jsou použity čtyřvrstvé MLP.  Je ukázno, že první skrytá vrstva ze čtyřvrstvé ho MLP je schopná detekovat základní vzory z časově-frekvenční roviny.
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.
BibTeX:
@INPROCEEDINGS{
   author = {Qifeng Zhu and Barry Chen and František Grézl and Nelson
	Morgan},
   title = {Improved MLP Structures for Data-Driven Feature Extraction
	for ASR},
   pages = {4},
   booktitle = {Interspeech'2005 - Eurospeech - 9th European Conference on
	Speech Communication and Technology},
   journal = {European Speech Communication},
   year = {2005},
   location = {Lisabon, PT},
   ISSN = {1018-4074},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=7909}
}