Toward optimal mixture model based vector quantization
2005 (English)In: 2005 Fifth International Conference on Information, Communications and Signal Processing, 2005, 1329-1333 p.Conference paper (Refereed)
Gaussian mixture model (GMM) based vector quantization (VQ) using a data-dependent weighted Euclidean distortion measure is presented. It is shown how GMM-VQ can be improved by using GMMs that model the optimal VQ point density rather than the source probability density as is done in previous work. GMM training procedures as well as procedures for encoding and decoding that takes a weighted distortion measure into account are presented. The usefulness of the proposed procedures is demonstrated on a source derived from speech spectrum parameters.
Place, publisher, year, edition, pages
2005. 1329-1333 p.
Decoding, Parameter estimation, Probability, Signal distortion, Signal encoding, Vector quantization, Data-dependent weighted, Euclidean distortion, Probability density, Speech spectrum parameters, Gaussian noise (electronic)
IdentifiersURN: urn:nbn:se:kth:diva-156273ScopusID: 2-s2.0-34147115614ISBN: 0780392833ISBN: 9780780392830OAI: oai:DiVA.org:kth-156273DiVA: diva2:767537
2005 Fifth International Conference on Information, Communications and Signal Processing, 6 December 2005 through 9 December 2005, Bangkok, Thailand
QC 201412012014-12-012014-11-262014-12-01Bibliographically approved