A study of phonetic feature representations for SVM-based speaker verification
Merkley, Erik E., Baker, Brendan J., Vogt, Robert J., & Sridharan, Sridha (2008) A study of phonetic feature representations for SVM-based speaker verification. In Wysocki, Beta & Tadeusz, Wysocki (Eds.) 2nd International Conference on Signal Processing and Communication Systems 2008, 15-17 December 2008, Gold Coast, Australia.
We investigate an alternative formulation of phonetic feature representations for SVM-based speaker verification. The new features are based on conditional likelihood representations rather than the joint-likelihood or bag-of-ngram calculations traditionally used. Conditional likelihoods are shown to be a more natural method of modelling phonetic information, and improve upon conventional joint likelihoods in a number of cases. The problem of feature normalisation is also examined, with a previously proposed non-parametric method based on rank shown to be particularly useful. Combinations of feature representations are examined and the potential for complementary information between joint and conditional likelihoods considered. Additionally, feature compensation is applied to conditional likelihoods with considerable improvement in performance.
Impact and interest:
Citation counts are sourced monthly from and citation databases.
Citations counts from theindexing service can be viewed at the linked Google Scholar™ search.
|Item Type:||Conference Paper|
|Subjects:||Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING (080100)|
|Divisions:||Past > QUT Faculties & Divisions > Faculty of Built Environment and Engineering
Past > Institutes > Information Security Institute
Past > Schools > School of Engineering Systems
|Copyright Owner:||Copyright 2008 (please consult author)|
|Deposited On:||09 Feb 2009 23:16|
|Last Modified:||29 Feb 2012 13:48|
Repository Staff Only: item control page