A one-pass Search Algorithm for Understanding Natural Spoken Time Utterances b...

Title A one-pass Search Algorithm for Understanding Natural Spoken Time Utterances by Stochastic Models
Authors Josef G. Bauer, Holger Stahl, Johannes Müller
Type Scientific Conference Paper
Abstract A system for understanding time utterances spoken in German language is presented. Stochastic models contain the knowledge in the semantic, syntactic and acousticphonetic levels. An adequate semantic representation allows the integration of these models within a one-pass Viterbi search. The simultaneous use of all knowledge sources for the search procedure results in the smallest possible search space for the determination of the most probable semantic content accurately following the Bayes classification rule. Both the recognition accuracy and the computing speed facilitate a realistic application.
Keywords: speech recognition, language understanding, spoken man-machine-dialogue, stochastic models, onepass search, representation of syntactic and semantic knowledge
Reference Proceedings Eurospeech '95 (Madrid, Spain, 1995), pp. 567-570
Year 1995
Language English
Download Dateisymbol Scientific Conference Paper as pdf file  (45 kByte)

Twitter-Symbol Facebook-Symbol XING-Symbol Delicious-Symbol Senden-Symbol

© WebDesign by Johannes Müller - Briefsymbol Kontakt
erstellt am 21.02.2007, zuletzt geändert am 09.01.2008