Volltext-Downloads (blau) und Frontdoor-Views (grau)

Articulatory-acoustic Feature Recognition: Comparison of Machine Learning and HMM methods

  • HMMs are the dominating technique used in speech recognition today since they perform well in overall phone recognition. In this paper, we show the comparison of HMM methods and machine learning techniques, such as neural networks, decision trees and ensemble classifiers with boosting and bagging in the task of articulatory-acoustic feature classification. The experimental results show that HMM methods work well for the classification of such features as vocalic. However, decision tree and bagging outperform HMMs for the fricative classification task since the data skewness is much higher than for the feature vocalic classification task. This demonstrates that HMMs do not perform as well as decision trees and bagging in highly skewed data settings.

Export metadata

  • Export Bibtex
  • Export RIS

Additional Services

Share in Twitter Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author:Jan Macek, Supphanat Kanokphara, Anja Geumann
URN:http://nbn-resolving.de/urn:nbn:de:bsz:mh39-57041
ISBN:9785745201103
Parent Title (English):Proceedings of the 10th International Conference on Speech and Computer, 17-19 October, Patras, Greece (SPECOM 2005)
Publisher:University of Patras
Place of publication:Patras
Document Type:Conference Proceeding
Language:English
Year of first Publication:2005
Date of Publication (online):2016/12/13
Publicationstate:Postprint
GND Keyword: Automatische Spracherkennung; Artikulatorische Phonetik
First Page:99
Last Page:102
Dewey Decimal Classification:400 Sprache / 400 Sprache, Linguistik
Leibniz-Classification:Sprache, Linguistik
Open Access?:Ja
Licence (German):License LogoEs gilt das UrhG

$Rev: 12793 $