TY - GEN
T1 - Referential semantic language modeling for data-poor domains
AU - Wu, Stephen
AU - Schwartz, Lane
AU - Schuler, William
PY - 2008
Y1 - 2008
N2 - 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.
AB - 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.
KW - Artificial intelligence
KW - Natural language interfaces
KW - Speech recognition
UR - http://www.scopus.com/inward/record.url?scp=51449101284&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=51449101284&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2008.4518802
DO - 10.1109/ICASSP.2008.4518802
M3 - Conference contribution
AN - SCOPUS:51449101284
SN - 1424414849
SN - 9781424414840
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 5085
EP - 5088
BT - International Conference on Acoustics, Speech, and Signal Processing
T2 - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Y2 - 31 March 2008 through 4 April 2008
ER -