Robust voiced/unvoiced speech classification with self-organizing maps

Author

Boda, P.P.

Author_Institution

Acoust. Lab., Helsinki Univ. of Technol., Espoo

Volume

2

fYear

1995

fDate

30 Apr-3 May 1995

Firstpage

1516

Abstract

The goal of this paper is to show the applicability of a new feature set in voiced/unvoiced (V/UV) classification of speech. The decision is based on the Kohonen-type Self-Organizing Maps (SOM) using this new feature set. The set of input features are computed according to the human auditory system using Warped Linear Prediction (WLP) and found to be robust to background noise - thus the classification is reliable for corrupted speech segments, too. Self-Organizing Maps classify noisy patterns with an error rate of less than 2% at 9 dB signal-to-noise ratio

Keywords

pattern classification; prediction theory; self-organising feature maps; speech recognition; Kohonen-type self-organizing maps; corrupted segments; error rate; feature set; human auditory system; noisy patterns; robust voiced/unvoiced speech classification; signal-to-noise ratio; warped linear prediction; Acoustic noise; Auditory system; Filters; Frequency; Humans; Neural networks; Robustness; Self organizing feature maps; Speech coding; Speech synthesis;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1995. ISCAS '95., 1995 IEEE International Symposium on

Conference_Location

Seattle, WA

Print_ISBN

0-7803-2570-2

Type

conf

DOI

10.1109/ISCAS.1995.521423

Filename

521423