Return to search

A comparative analysis of gaussian mixture models and i-vector for speaker verification under mismatched conditions

Orientador: Prof. Dr. Francisco J. Fraga / Dissertação (mestrado) - Universidade Federal do ABC, Programa de Pós-Graduação em Engenharia da Informação, 2014. / Most speaker verifcation systems are based on Gaussian mixture models and more
recently on the so-called i-vector. These two methods are affected in mismatched testtrain
conditions, which might be caused by vocal-efort variability, different speakingstyles
or channel efects. In this work, we compared the impact of speech rate variation
and room reverberation on both methods. We found that performance degradation
due to variation on speech rate can be mitigated by adding fast speech samples into
the training set, which decreased equal error rates for Gaussian mixture models and
i-vector, respectively. Regarding reverberation, we investigated the achievements of
both methods when three diferent reverberation compensation techniques are applied
in order to overcome performance degradation. The results showed that having
reverberant background models separated by diferent levels of reverberation can bene
t both methods, with the i-vector providing the best performance in that scenario.
Finally, the performance of two auditory-inspired features, mel-frequency cepstral coe
ficients and the so-called modulation spectrum features, are compared in presence
of room reverberation. For the speaker verifcation system considered in this work,
modulation spectrum features are equally afected by reverberation time and have
their performance degraded as the level of reverberation increases.

Identiferoai:union.ndltd.org:IBICT/oai:BDTD:76600
Date January 2014
CreatorsAvila, Anderson Raymundo
ContributorsSilva, Francisco José Fraga da, Suyama, Ricardo, Ramírez, Miguel Arjona
Source SetsIBICT Brazilian ETDs
LanguageInglês
Detected LanguageEnglish
Typeinfo:eu-repo/semantics/publishedVersion, info:eu-repo/semantics/masterThesis
Formatapplication/pdf, 96 f. : il.
Sourcereponame:Repositório Institucional da UFABC, instname:Universidade Federal do ABC, instacron:UFABC
Rightsinfo:eu-repo/semantics/openAccess
Relationhttp://biblioteca.ufabc.edu.br/index.php?codigo_sophia=76600&midiaext=69761, http://biblioteca.ufabc.edu.br/index.php?codigo_sophia=76600&midiaext=69762, Cover: http://biblioteca.ufabc.edu.brphp/capa.php?obra=76600

Page generated in 0.0017 seconds