Semantic analysis of spoken input using Markov logic networks

Vladimir Despotovic, Oliver Walter, Reinhold Haeb-Umbach

Research output: Contribution to journalConference articlepeer-review

1 Citation (Scopus)

Abstract

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 incomplete 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.

Original languageEnglish
Pages (from-to)1859-1863
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2015-January
Publication statusPublished - 2015
Externally publishedYes
Event16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015 - Dresden, Germany
Duration: 6 Sep 201510 Sep 2015

Keywords

  • Acoustic units
  • Markov Logic Networks
  • Semantic frame
  • Speech
  • Unsupervised learning

Fingerprint

Dive into the research topics of 'Semantic analysis of spoken input using Markov logic networks'. Together they form a unique fingerprint.

Cite this