Phase Space Parameters for Neural Network Based Vowel Recognition

Autor:	N. S. Sreekanth, P. Prajith, N. K. Narayanan
Rok vydání:	2004
Předmět:	Nonlinear system Signal processing Point distribution model Artificial neural network Computer science Phase space Speech recognition Chaotic Time domain Mixture model Space (mathematics) Algorithm Backpropagation
Zdroj:	Neural Information Processing ISBN: 9783540239314 ICONIP
DOI:	10.1007/978-3-540-30499-9_187
Popis:	This paper presents the implementation of a neural network with error back propagation algorithm for the speech recognition application with Phase Space Point Distribution as the input parameter. By utilizing nonlinear or chaotic signal processing techniques to extract time domain based phase space features, a method is suggested for speech recognition. Two sets of experiments are presented in this paper. In the first, exploiting the theoretical results derived in nonlinear dynamics, a processing space called phase space is generated and a recognition parameter called Phase Space Point Distribution (PSPD) is extracted. In the second experiment Phase Space Map at a phase angle p/2 is reconstructed and PSPD is calculated. The output of a neural network with error back propagation algorithm demonstrate that phase space features contain substantial discriminatory power
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::efdc298e0c68aadbbe9551b2de1c08ad https://doi.org/10.1007/978-3-540-30499-9_187 Zobrazit plný text záznamu