Please use this identifier to cite or link to this item: doi:10.22028/D291-25194
Title: A hybrid RBF-HMM system for continuous speech recognition
Author(s): Reichl, W.
Ruske, G.
Language: English
Year of Publication: 1996
OPUS Source: Saarbrücken, 1996
SWD key words: Künstliche Intelligenz
DDC notations: 004 Computer science, internet
Publikation type: Report
Abstract: A hybrid system for continuous speech recognition, consisting of a neural network with Radial Basis Functions and Hidden Markov Models is described in this paper together with discriminant training techniques. Initially the neural net is trained to approximate a-posteriori probabilities of single HMM states. These probabilities are used by the Viterbi algorithm to calculate the total scores for the individual hybrid phoneme models. The final training of the hybrid system is based on the "Minimum Classification Error'; objective function, which approximates the misclassification rate of the hybrid classifier, and the "Generalized Probabilistic Descent'; algorithm. The hybrid system was used in continuous speech recognition experiments with phoneme units and shows about 63.8% phoneme recognition rate in a speaker-independent task.
Link to this record: urn:nbn:de:bsz:291-scidok-41917
Series name: Vm-Report / Verbmobil, Verbundvorhaben, [Deutsches Forschungszentrum für Künstliche Intelligenz]
Series volume: 109
Date of registration: 6-Sep-2011
Faculty: SE - Sonstige Einrichtungen
Department: SE - DFKI Deutsches Forschungszentrum für Künstliche Intelligenz
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
File Description SizeFormat 
report_109_96.pdf285,27 kBAdobe PDFView/Open

Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.