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 hdl:20.500.11880/25251 http://dx.doi.org/10.22028/D291-25195 |
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 | Size | Format | |
---|---|---|---|---|
report_110_96.pdf | 328,51 kB | Adobe PDF | View/Open |
Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.