Harmonic Structure Transform for Speaker Recognition
2011 (English)In: 12th Annual Conference Of The International Speech Communication Association 2011 (INTERSPEECH 2011), Vols 1-5, ISCA , 2011, 372-375 p.Conference paper (Refereed)
We evaluate a new filterbank structure, yielding the harmonic structure cepstral coefficients (HSCCs), on a mismatched-session closed-set speaker classification task. The novelty of the filterbank lies in its averaging of energy at frequencies related by harmonicity rather than by adjacency. Improvements are presented which achieve a 37%rel reduction in error rate under these conditions. The improved features are combined with a similar Mel-frequency cepstral coefficient (MFCC) system to yield error rate reductions of 32%rel, suggesting that HSCCs offer information which is complimentary to that available to today's MFCC-based systems.
Place, publisher, year, edition, pages
ISCA , 2011. 372-375 p.
, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, ISSN 1990-9772 ; 2011
speaker recognition, signal processing, harmonic strucure, spectral analysis
Language Technology (Computational Linguistics)
IdentifiersURN: urn:nbn:se:kth:diva-137167ISI: 000316502200095ScopusID: 2-s2.0-84865772856ISBN: 978-1-61839-270-1OAI: oai:DiVA.org:kth-137167DiVA: diva2:679128
12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011; Florence; Italy; 27 August 2011 through 31 August 2011
QC 201312132013-12-132013-12-112013-12-13Bibliographically approved