Record Details

Singing voice detection in polyphonic music using predominant pitch

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Singing voice detection in polyphonic music using predominant pitch
 
Creator RAO, V
RAMAKRISHNAN, S
RAO, P
 
Subject audio segmentation
voice detection
 
Description This paper demonstrates the superiority of energy-based features derived from the knowledge of predominant-pitch, for singing voice detection in polyphonic music over commonly used spectral features. However, such energy-based features tend to misclassify loud, pitched instruments. To provide robustness to such accompaniment we exploit the relative instability of the pitch contour of the singing voice by attenuating harmonic spectral content belonging to stable-pitch instruments, using sinusoidal modeling. The obtained feature shows high classification accuracy when applied to north Indian classical music data and is also found suitable for automatic detection of vocal-instrumental boundaries required for smoothing the frame-level classifier decisions.
 
Publisher ISCA-INST SPEECH COMMUNICATION ASSOC
 
Date 2011-10-25T20:01:02Z
2011-12-15T09:12:06Z
2011-10-25T20:01:02Z
2011-12-15T09:12:06Z
2009
 
Type Proceedings Paper
 
Identifier INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5,1135-1138
978-1-61567-692-7
http://dspace.library.iitb.ac.in/xmlui/handle/10054/15808
http://hdl.handle.net/100/2474
 
Source 10th INTERSPEECH 2009 Conference,Brighton, ENGLAND,SEP 06-10, 2009
 
Language English