Record Details

Detection of stop landmarks using gaussian mixture modeling of speech spectrum

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Detection of stop landmarks using gaussian mixture modeling of speech spectrum
 
Creator JAYAN, AR
PANDEY, PC
 
Subject intelligibility
hearing
clear
enhancement
speech enhancement
acoustic landmark detection
gaussian mixture modeling
 
Description Perception of speech under adverse listening conditions may be improved by processing it to incorporate properties of clear speech. It needs automated detection of stop landmarks and enhancement of bursts and transition segments. A technique for accurate detection of stop landmarks in continuous speech based on parameters derived from Gaussian mixture modeling of log magnitude spectrum, a voicing onset-offset detector, and a spectral flatness measure is presented. Applying the technique on sentences from the TIMIT database resulted in burst detection rates of 98, 97, 95: 90, and 73% at temporal accuracies of 30, 20, 15, 10, and 5 ms respectively.
 
Publisher IEEE
 
Date 2011-10-24T13:20:32Z
2011-12-15T09:11:38Z
2011-10-24T13:20:32Z
2011-12-15T09:11:38Z
2009
 
Type Proceedings Paper
 
Identifier 2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS,4681-4684
978-1-4244-2353-8
1520-6149
http://dx.doi.org/10.1109/ICASSP.2009.4960675
http://dspace.library.iitb.ac.in/xmlui/handle/10054/15430
http://hdl.handle.net/100/2193
 
Source IEEE International Conference on Acoustics, Speech and Signal Processing,Taipei, TAIWAN,APR 19-24, 2009
 
Language English