Hierarchical Neural Network Structures for Phoneme Recognition

Lieferzeit: Lieferbar innerhalb 14 Tagen

106,99 

Signals and Communication Technology

ISBN: 3642432107
ISBN 13: 9783642432101
Autor: Vasquez, Daniel/Gruhn, Rainer/Minker, Wolfgang
Verlag: Springer Verlag GmbH
Umfang: xviii, 134 S.
Erscheinungsdatum: 09.11.2014
Auflage: 1/2014
Produktform: Kartoniert
Einband: Kartoniert

In this book, hierarchical structures based on neural networks are investigated for automatic speech recognition. These structures are evaluated on the phoneme recognition task where a  Hybrid Hidden Markov Model/Artificial Neural Network paradigm is used. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron. Additionally, the output of the first level serves as a second level input. The computational speed of the phoneme recognizer can be substantially increased by removing redundant information still contained at the first level output. Several techniques based on temporal and phonetic criteria have been investigated to remove this redundant information. The computational time could be reduced by 57% whilst keeping the system accuracy comparable to the baseline hierarchical approach.

Artikelnummer: 7477739 Kategorie:

Beschreibung

Herstellerkennzeichnung:


Springer Verlag GmbH
Tiergartenstr. 17
69121 Heidelberg
DE

E-Mail: juergen.hartmann@springer.com

Das könnte Ihnen auch gefallen …