An elitist approach for extracting automatically well-realized speech sounds with high confidence

Simple item page
dc.creatorMaj, Jean-Baptiste
dc.creatorBonneau, Anne
dc.creatorFohr, Dominique
dc.creatorLaprie, Yves
dc.date2005-11-22
dc.date.accessioned2026-07-07T06:49:38Z
dc.date.available2026-07-07T06:49:38Z
dc.descriptionThis paper presents an "elitist approach" for extracting automatically well-realized speech sounds with high confidence. The elitist approach uses a speech recognition system based on Hidden Markov Models (HMM). The HMM are trained on speech sounds which are systematically well-detected in an iterative procedure. The results show that, by using the HMM models defined in the training phase, the speech recognizer detects reliably specific speech sounds with a small rate of errors.
dc.identifierhttps://arxiv.org/abs/cs/0511079
dc.identifierhttp://arxiv.org/abs/cs/0511079
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/104419
dc.subjectComputation and Language
dc.titleAn elitist approach for extracting automatically well-realized speech sounds with high confidence
dc.typetext

Files

Collections

arXiv