Logo des Repositoriums
 

Automatic parameter tuning and extended training material: recent advances in the Fraunhofer speech recognition system

dc.contributor.authorSchwenninger, Jochen
dc.contributor.authorStein, Daniel
dc.contributor.authorStadtschnitzer, Michael
dc.contributor.editorHorbach, Matthias
dc.date.accessioned2019-03-07T09:32:29Z
dc.date.available2019-03-07T09:32:29Z
dc.date.issued2013
dc.description.abstractBuilding the acoustic and language models on a larger amount of training data is a well-known method for robustifying automatic speech recognition approaches. The adaption of the decoder settings afterwards, however, is often only marginally addressed (e.g. being manually set or using default values provided by a toolkit). Without proper adaption, these settings are most often sub-optimal and lead to degraded performance without unlocking the full potential of the speech recognizer. Ideally, the decoder settings should be optimized after each modification of the language model and/or the acoustic model of the speech recognition system, a task that is typically too tedious for manual work. In this paper, we employ an automatic optimization technique on the Fraunhofer IAIS speech recognition setup as a subsequent step to training data increase. We will present the improvements of the expanded training data for the acoustic models and the optimization of the decoder settings on the German Difficult Speech Corpus. Index Terms: simultaneous perturbation stochastic approximation, free decoding parameters, word error rate optimizationen
dc.identifier.isbn978-3-88579-614-5
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/20714
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofINFORMATIK 2013 – Informatik angepasst an Mensch, Organisation und Umwelt
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-220
dc.subjectsimultaneous perturbation stochastic approximation
dc.subjectfree decoding param- eters
dc.subjectword error rate optimization
dc.titleAutomatic parameter tuning and extended training material: recent advances in the Fraunhofer speech recognition systemen
dc.typeText/Conference Paper
gi.citation.endPage3011
gi.citation.publisherPlaceBonn
gi.citation.startPage3002
gi.conference.date16.-20. September 2013
gi.conference.locationKoblenz
gi.conference.sessiontitleRegular Research Papers

Dateien

Originalbündel
1 - 1 von 1
Lade...
Vorschaubild
Name:
3002.pdf
Größe:
174.27 KB
Format:
Adobe Portable Document Format