Title :
Referential semantic language modeling for data-poor domains
Author :
Wu, Stephen ; Schwartz, Lane ; Schuler, William
Author_Institution :
Dept. of Comput. Sci. & Eng., Minnesota Univ., Minneapolis, MN
fDate :
March 31 2008-April 4 2008
Abstract :
This paper describes a referential semantic language model that achieves accurate recognition in user-defined domains with no available domain-specific training corpora. This model is interesting in that, unlike similar recent systems, it exploits context dynamically, using incremental processing and limited stack memory of an HMM-like time series model to constrain search.
Keywords :
natural language interfaces; programming language semantics; speech processing; speech recognition; time series; HMM-like time series model; data-poor domains; hidden Markov model; referential semantic language modeling; user-defined domains; Artificial intelligence; Computer science; Context modeling; Data engineering; Decoding; Hidden Markov models; Information resources; Natural languages; Speech recognition; Viterbi algorithm; Artificial intelligence; Natural language interfaces; Speech recognition;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4244-1483-3
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2008.4518802
