Paper Info
Title
An on-line VAD based on Multi-Normalisation Scoring (MNS) of observation likelihoods.
Abstract
•A novel on-line voice activity detection (VAD) technique with no delay is proposed.•The VAD relies on Multi-Normalization Scoring (MNS) and a classifier.•MNS is based on generating multiple score vectors with various normalization ratios.•A validation experiment with two standard VADs proves its good performance.
Year
DOI
Venue
2018
10.1016/j.eswa.2018.05.038
Expert Systems with Applications
Keywords
Field
DocType
VAD,Observation likelihood,MNS,On-line speech processing
Pattern recognition,Computer science,Voice activity detection,Expert system,Communication channel,Artificial intelligence,Classifier (linguistics),Perceptron,Machine learning
Journal
Volume
ISSN
Citations 
110
0957-4174
0
PageRank 
References 
Authors
0.34
26
3
Name
Order
Citations
PageRank
Igor Odriozola1104.55
Inma Hernáez219621.64
Eva Navas330328.48