Please use this identifier to cite or link to this item: doi:10.22028/D291-25195
Title: Discriminative training 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: Discriminative training techniques for Hidden-Markov Models were recently proposed and successfully applied for automatic speech recognition. In this paper a discussion of the Minimum Classification Error and the Maximum Mutual Information objective is presented. An extended reestimation formula is used for the HMM parameter update for both objective functions. The discriminative training methods were utilized in speaker independent phoneme recognition experiments and improved the phoneme recognition rates for both discriminative training techniques.
Link to this record: urn:nbn:de:bsz:291-scidok-41926
Series name: Vm-Report / Verbmobil, Verbundvorhaben, [Deutsches Forschungszentrum für Künstliche Intelligenz]
Series volume: 110
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_110_96.pdf328,51 kBAdobe PDFView/Open

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