Comparison of current frame-based phoneme classifiers

DSpace/Manakin Repository

aaK citaci nebo jako odkaz na tento záznam použijte identifikátor:

Show simple item record Pfeifer, Václav Balík, Miroslav 2012-01-06T14:30:08Z 2012-01-06T14:30:08Z 2011
dc.identifier.citation Advances in electrical and electronic engineering. 2011, vol. 9, no. 5, p. 243-250. cs
dc.identifier.issn 1804-3119
dc.description.abstract This paper compares today’s most common frame-based classifiers. These classifiers can be divided into the two main groups – generic classifiers which creates the most probable model based on the training data (for example GMM) and discriminative classifiers which focues on creating decision hyperplane. A lot of research has been done with the GMM classifiers and therefore this paper will be mainly focused on the frame-based classifiers. Two discriminative classifiers will be presented. These classifiers implements a hieararchical tree root structure over the input phoneme group which shown to be an effective. Based on these classifiers, two efficient training algorithms will be presented. We demonstrate advantages of our training algorithms by evaluating all classifiers over the TIMIT speech corpus. cs
dc.format.extent 143718 bytes cs
dc.format.mimetype application/pdf cs
dc.language.iso en cs
dc.publisher Vysoká škola báňská - Technická univerzita Ostrava cs
dc.relation.ispartofseries Advances in electrical and electronic engineering cs
dc.relation.uri cs
dc.rights © Vysoká škola báňská - Technická univerzita Ostrava
dc.rights Creative Commons Attribution 3.0 Unported (CC BY 3.0)
dc.subject classifier cs
dc.subject comparison cs
dc.subject frame-based cs
dc.subject phoneme cs
dc.subject speech cs
dc.subject hierarchical cs
dc.title Comparison of current frame-based phoneme classifiers cs
dc.type article cs
dc.rights.access openAccess cs
dc.type.version publishedVersion cs
dc.type.status Peer-reviewed cs

Files in this item

Files Size Format View Description
AEEE-2011-9-4-243-pfeifer.pdf 140.3Kb PDF View/Open publishedVersion

This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search



My Account