Feature-dependent compensation of coders in speech recognition

dc.creatorBecerra Yoma, Néstor
dc.creatorMolina, Carlos
dc.date.accessioned2008-12-10T15:34:38Z
dc.date.available2008-12-10T15:34:38Z
dc.date.created2008-12-10T15:34:38Z
dc.date.issued2006-01
dc.identifierSIGNAL PROCESSING Volume: 86 Issue: 1 Pages: 38-49 Published: JAN 2006
dc.identifier0165-1684
dc.identifierhttps://repositorio.uchile.cl/handle/2250/124761
dc.description.abstractA solution to the problem of speech recognition with signals corrupted by coders is presented. The coding-decoding distortion is modelled as feature dependent. This model is employed to propose an unsupervised expectation-maximization (EM) estimation algorithm of the coding-decoding distortion that is able to cancel the effect of coders with as few as one adapting utterance. No knowledge about the coder is required. The feature-dependent adaptation can give a word error rate (WER) 21% lower than the feature-independent model. Finally, when compared to the baseline system, the reduction in WER can be as high as 70%.
dc.languageen
dc.publisherELSEVIER
dc.subjectSpeech recognition
dc.titleFeature-dependent compensation of coders in speech recognition
dc.typeArtículo de revista


Este ítem pertenece a la siguiente institución