Reference : Semantic Analysis of Spoken Input Using Markov Logic Networks
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/10993/40877
Semantic Analysis of Spoken Input Using Markov Logic Networks
English
Despotovic, Vladimir mailto [University of Belgrade > Technical Faculty in Bor]
Walter, Oliver [University of Paderborn > Department of Communications Engineering]
Haeb-Umbach, Reinhold [University of Paderborn > Department of Communications Engineering]
Sep-2015
Proceedings of the 16th Annual Conference of the International Speech Communication Association (INTERSPEECH 2015)
1859-1863
Yes
International
16th Annual Conference of the International Speech Communication Association (INTERSPEECH 2015)
from 06-09-2015 to 10-09-2015
Dresden
Germany
[en] Unsupervised learning ; Acoustic units ; Speech ; Markov Logic Networks ; Semantic frame
[en] We present a semantic analysis technique for spoken input using Markov Logic Networks (MLNs). MLNs combine graphical models with first-order logic. They are particularly suitable for providing inference in the presence of inconsistent and in- complete data, which are typical of an automatic speech recognizer’s (ASR) output in the presence of degraded speech. The target application is a speech interface to a home automation system to be operated by people with speech impairments, where the ASR output is particularly noisy. In order to cater for dysarthric speech with non-canonical phoneme realizations, acoustic representations of the input speech are learned in an unsupervised fashion. While training data transcripts are not required for the acoustic model training, the MLN training requires supervision, however, at a rather loose and abstract level. Results on two databases, one of them for dysarthric speech, show that MLN-based semantic analysis clearly outperforms baseline approaches employing non-negative matrix factorization, multinomial naive Bayes models, or support vector machines.
Deutsche Forschungsgemeinschaft ; European Commission - EC
http://hdl.handle.net/10993/40877
https://www.isca-speech.org/archive/interspeech_2015/i15_1859.html

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
INTERSPEECH 2015.pdfPublisher postprint172.03 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.