Please use this identifier to cite or link to this item: doi:10.22028/D291-25313
Title: An integrated model of acoustics and language using semantic classification trees
Author(s): Nöth, Elmar
De Mori, Renato
Fischer, J.
Gebhard, A.
Harbeck, Stefan
Kompe, Ralf
Kuhn, R.
Niemann, Heinrich
Mast, Marion
Language: English
Year of Publication: 1996
SWD key words: Künstliche Intelligenz
Free key words: artificial intelligence
DDC notations: 004 Computer science, internet
Publikation type: Report
Abstract: We propose Multi-level Semantic Classication Trees to combine different information sources for predicting speech events (e.g. word chains, phrases, etc.) Traditionally in speech recognition systems these information sources (acoustic evidence, language model) are calculated independently and combined via Bayes rule. The proposed approach allows one to combine sources of different types - is no longer necessary for each source to yield a probability. Moreover the tree can look at several information sources simultaneously. The approach is demonstrated for the prediction of prosodically marked phrase boundaries, combining information about the spoken word chain, word category information, prosodic parameters, and the result of a neural network predicting the boundary on the basis of acoustic-prosodic features. The recognition rates of up to 90% for the two class problem boundary vs. no boundary are already comparable to results achieved with the above mentioned Bayes rule approach that combines the acoustic classifier with a 5-gram categorical language model. This is remarkable, since so far only a small set of questions combining information from different sources have been implemented.
Link to this record: urn:nbn:de:bsz:291-scidok-53210
Series name: Vm-Report / Verbmobil, Verbundvorhaben, [Deutsches Forschungszentrum für Künstliche Intelligenz]
Series volume: 128
Date of registration: 13-Jun-2013
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_128_96.pdf169,98 kBAdobe PDFView/Open

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