Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
MOTLÍČEK, P.
Originální název
Feature Extraction in Speech Coding and Recognition
Typ
výzkumná zpráva
Jazyk
angličtina
Originální abstrakt
This document is dealing with the feature extraction techniques generally used in speech recognition tasks. The most popular features used in speech recognition, such as Mel-Filter bank cepstral coefficients (MFCCs) and Perceptual Linear Prediction (PLP) coefficients, were taken as the baseline features. A significant amount of effort has been devoted to establishing speech feature extraction schemes which enable robust and high performance speech recognition in a range of operating environments. Each scheme consists of several processing stages that will be subjected to the theoretical analysis as well as their contribution to the resulting performance of the whole system. In many descriptions, feature extraction is considered as comprising three different stages: - namely static feature extraction -feature normalization -inclusion of temporal information. In our work we have concentrated on first two stages. In all our speech recognition experiments delta and acceleration components were applied as the temporal derivatives.
Klíčová slova
speech coding, speech recognition, feature normalization, feature extraction, PLP, MFCC
Autoři
Vydáno
11. 9. 2002
Nakladatel
Oregon Graduate Institute of Science and Technology
Místo
Portland
Strany od
1
Strany do
50
Strany počet
URL
http://www.fit.vutbr.cz/~motlicek/publi/2002/rp.pdf
BibTex
@techreport{BUT56724, author="Petr {Motlíček}", title="Feature Extraction in Speech Coding and Recognition", year="2002", publisher="Oregon Graduate Institute of Science and Technology", address="Portland", pages="1--50", url="http://www.fit.vutbr.cz/~motlicek/publi/2002/rp.pdf" }