Applying Elliptical Basis Function Neural Networks to VAD for Wireless Communication Systems

Hosun LEE
Sukyung KIM
Sungkwon PARK

Publication
IEICE TRANSACTIONS on Communications   Vol.E89-B    No.4    pp.1423-1424
Publication Date: 2006/04/01
Online ISSN: 1745-1345
DOI: 10.1093/ietcom/e89-b.4.1423
Print ISSN: 0916-8516
Type of Manuscript: LETTER
Category: Fundamental Theories for Communications
Keyword: 
voice activity detection,  neural network,  elliptical basis function,  linear prediction coefficients,  

Full Text: PDF(108.5KB)>>
Buy this Article


Summary: 
Voice activity detection (VAD) determines whether a slice of waveform is voice or silence. The proposed VAD algorithm applying Elliptical Basis Function (EBF) neural networks uses k-means clustering and least mean square for the update algorithm. The error rates achieved by the EBF network have superior performance to those of G.729 Annex B and RBF.