ViSQOL: The Virtual Speech Quality Objective Listener
File Type:
PDFItem Type:
Conference PaperDate:
2012Citation:
Andrew Hines, Jan Skoglund, Anil Kokaram, Naomi Harte, ViSQOL: The Virtual Speech Quality Objective Listener, The International Workshop on Acoustic Signal Enhancement (IWAENC), Aachen, Germany, 4-6 Sept. 2012, 2012, 1 - 4Download Item:
ah_IWAENC2012.pdf (Accepted for publication (author's copy) - Peer Reviewed) 169.9Kb
Abstract:
A model of human speech quality perception has been developed
to provide an objective measure for predicting subjective quality
assessments. The Virtual Speech Quality Objective Listener
(ViSQOL) model is a signal based full reference metric that uses a
spectro-temporal measure of similarity between a reference and a
test speech signal. This paper describes the algorithm and compares
the results with PESQ for common problems in VoIP: clock drift,
associated time warping and jitter. The results indicate that ViSQOL
is less prone to underestimation of speech quality in both scenarios
than the ITU standard.
Author's Homepage:
http://people.tcd.ie/ahineshttp://people.tcd.ie/nharte
http://people.tcd.ie/akokaram
Description:
PUBLISHEDAachen, Germany
Other Titles:
The International Workshop on Acoustic Signal Enhancement (IWAENC)Type of material:
Conference PaperAvailability:
Full text availableKeywords:
speech quality, quality metricsLicences: