Applications of neural networks in speech processing for Romanian language

Author

Gavat, Inge ; Dumitru, Corneliu Octavian ; Costache, Gabriel Nicolae

Author_Institution

Univ. "Politehnica" of Bucharest, Romania

fYear

2002

fDate

2002

Firstpage

65

Lastpage

70

Abstract

In the paper is presented our work concerning speech processing by neural networks. A combination of Kohonen maps and multilayer perceptrons is applied in a word spotting task. A hierarchical segmentation procedure for continuous speech is realized with multilayer perceptrons, Kohonen maps and radial basis function networks. A neuro-statistical structure for isolated word recognition and a neuro-fuzzy hybrid for vowel recognition are analyzed.

Keywords

fuzzy neural nets; multilayer perceptrons; radial basis function networks; self-organising feature maps; speech processing; statistical analysis; Kohonen maps; Romanian language speech processing; continuous speech; hierarchical segmentation procedure; isolated word recognition; multilayer perceptrons; neural networks; neural statistical structure; neuro-fuzzy hybrid; radial basis function networks; vowel recognition; word spotting task; Intelligent networks; Natural languages; Neural networks; Recurrent neural networks; Speech processing; Speech recognition; Strontium; Support vector machine classification; Support vector machines; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Network Applications in Electrical Engineering, 2002. NEUREL '02. 2002 6th Seminar on

Print_ISBN

0-7803-7593-9

Type

conf

DOI

10.1109/NEUREL.2002.1057969

Filename

1057969