Neural network architectures for speaker independent phoneme recognition

Author

Cutajar, M. ; Gatt, E. ; Grech, I. ; Casha, O. ; Micallef, J.

Author_Institution

Dept. of Microelectron. & Nanoelectron., Univ. of Malta, Msida, Malta

fYear

2011

fDate

4-6 Sept. 2011

Firstpage

90

Lastpage

94

Abstract

Two different neural network architectures were designed for speaker independent phoneme recognition systems. The first architecture consists of the Radial Basis Function (RBF), while in the second architecture a Self-Organising Maps (SOM) neural network replaces the RBF. The Discrete Wavelet Transform (DWT) is used for feature extraction in both systems. Both systems were tested on the TIMIT database. The highest recognition rates obtained are 36.3% and 46.7%, for the RBF and SOM architectures respectively for multi-speaker unlimited vocabulary speech.

Keywords

feature extraction; radial basis function networks; TIMIT database; discrete wavelet transform; feature extraction; multi speaker unlimited vocabulary speech; neural network architectures; self organising maps; speaker independent phoneme recognition; Discrete wavelet transforms; Hidden Markov models; Neurons; Signal processing; Speech; Speech recognition; Strontium;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Signal Processing and Analysis (ISPA), 2011 7th International Symposium on

Conference_Location

Dubrovnik

ISSN

1845-5921

Print_ISBN

978-1-4577-0841-1

Electronic_ISBN

1845-5921

Type

conf

Filename

6046586