Speech recognition in the Waxholm dialog system
1994 (English)Conference paper (Refereed)
The speech recognition component in the KTH "Waxholm" dialog system is described. It will handle continuous speech with a vocabulary of about 1000 words. The output of the recogniser is fed to a probabilistic, knowledge-based parser, that contains a context-free grammar compiled into an augmented transition network.
Place, publisher, year, edition, pages
1994. 22-23 p.
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-91239OAI: oai:DiVA.org:kth-91239DiVA: diva2:508936
Working papers from the 8th Swedish Phonetics Conference
NR 201408052012-03-112012-03-11Bibliographically approved