Home >

news Help

Publication Information


Title
Japanese: 
English:A Novel Voice Activity Detection Algorithm using Long-Term Spectral Flatness Measure 
Author
Japanese: MaYanna, 西原明法.  
English: Yanna Ma, AKINORI NISHIHARA.  
Language English 
Journal/Book name
Japanese: 
English:2013 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing 
Volume, Number, Page        
Published date 2013 
Publisher
Japanese: 
English: 
Conference name
Japanese: 
English:2013 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing 
Conference site
Japanese: 
English:The island of Hawaii 
File
Abstract This paper proposed a novel and robust voice activity detection (VAD) algorithm utilizing long-term spectral flatness measure (LSFM) which is capable of working at very low signal-to-noise ratios (less than 10 dB). The proposed algorithm was evaluated under eleven types of noises from NOISEX-92 and five types of SNR in core TIMIT TEST corpus. Comparisons with three modern standardized algorithms (ETSI AMR option 1&2 and ITU-T G.729 Annex B) demonstrate that our proposed LSFM-based VAD scheme achieved highest speech hit rate among the four algorithms while keeping good hit rate balance between speech hit rate and nonspeech hit rate.

©2007 Tokyo Institute of Technology All rights reserved.