Change search
ReferencesLink to record
Permanent link

Direct link
Discrete Choice Models for Non-Intrusive Quality Assessment
KTH, School of Electrical Engineering (EES), Sound and Image Processing (Closed 130101).
School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand .
2011 (English)In: 12th Annual Conference Of The International Speech Communication Association 2011 (INTERSPEECH 2011), Vols 1-5, ISCA , 2011, 200-203 p.Conference paper (Refereed)
Abstract [en]

Non-intrusive signal quality assessment in general, and its application to speech signal processing, in particular, builds extensively upon statistical regression models. Commonly, the raw preference scores used for fitting these models belong to a categorical scale. Averaging the scores over a number of test subjects results in smooth, close-to-continuous ratings, thus justifying the use of regression as opposed to classification models. A form of marginalization, averaging subjective ratings takes away useful information about the reliability of individual test points. Using a model tailored to the raw data achieves highly competitive performance in terms of conventional performance measures while providing the additional advantage of identifying the usability of individual test points. In this paper, we consider the application of discrete choice models to non-intrusive quality assessment of speech.

Place, publisher, year, edition, pages
ISCA , 2011. 200-203 p.
, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, ISSN 1990-9772
Keyword [en]
Discrete choice model, Distribution fitting, Non-intrusive quality assessment
National Category
Signal Processing
URN: urn:nbn:se:kth:diva-113212ISI: 000316502200052ScopusID: 2-s2.0-84865733461ISBN: 978-1-61839-270-1OAI: diva2:587584
12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011; Florence; Italy; 27 August 2011 through 31 August 2011
Listening Talker (LISTA)
EU, FP7, Seventh Framework Programme

QC 20130524

Available from: 2013-01-14 Created: 2013-01-14 Last updated: 2013-12-13Bibliographically approved

Open Access in DiVA

No full text


Search in DiVA

By author/editor
Petkov, Petko N.Kleijn, W. Bastiaan
By organisation
Sound and Image Processing (Closed 130101)
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 32 hits
ReferencesLink to record
Permanent link

Direct link