Please use this identifier to cite or link to this item: doi:10.22028/D291-25178
Title: Prosodic scoring of word hypotheses graphs
Author(s): Kompe, Ralf
Kießling, Andreas
Niemann, Heinrich
Nöth, Elmar
Schukat-Talamazzini, Ernst Günter
Zottmann, A.
Batliner, Anton
Language: English
Year of Publication: 1995
OPUS Source: Saarbrücken, 1995
SWD key words: Künstliche Intelligenz
DDC notations: 004 Computer science, internet
Publikation type: Report
Abstract: Prosodic boundary detection is important to disambiguate parsing, especially in spontaneous speech, where elliptic sentences occur frequently. Word graphs are an efficient interface between word recognition and parser. Prosodic classification of word chains has been published earlier. The adjustments necessary for applying these classification techniques to word graphs are discussed in this paper. When classifying a word hypothesis a set of context words has to be determined appropriately. A method has been developed to use stochastic language models for prosodic classification. This as well has been adopted for the use on word graphs. We also improved the set of acoustic-prosodic features with which the recognition errors were reduced by about 60% on the read speech we were working on previously, now achieving 10% error rate for 3 boundary classes and 3% for 2 accent classes. Moving to spontaneous speech the recognition error increases significantly (e.g. 16% for a 2-class boundary task). We show that even on word graphs the combination of language models which model a larger context with acoustic-prosodic classifiers reduces the recognition error by up to 50 %.
Link to this record: urn:nbn:de:bsz:291-scidok-41661
Series name: Vm-Report / Verbmobil, Verbundvorhaben, [Deutsches Forschungszentrum für Künstliche Intelligenz]
Series volume: 90
Date of registration: 5-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_90_95.pdf187,57 kBAdobe PDFView/Open

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