Sciweavers

61 search results - page 12 / 13
» 'Early recognition' of polysyllabic words in continuous spee...
Sort
View
ICASSP
2011
IEEE
12 years 10 months ago
Unsupervised determination of efficient Korean LVCSR units using a Bayesian Dirichlet process model
Korean is an agglutinative language that does not have explicit word boundaries. It is also a highly inflective language that exhibits severe coarticulation effects. These charac...
Sakriani Sakti, Andrew M. Finch, Ryosuke Isotani, ...
INTERSPEECH
2010
13 years 1 months ago
Language model cross adaptation for LVCSR system combination
State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple subsystems developed at different sites. Cross system adaptatio...
Xunying Liu, Mark J. F. Gales, Philip C. Woodland
ACL
2003
13 years 7 months ago
Accurate Unlexicalized Parsing
We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down fa...
Dan Klein, Christopher D. Manning
ICASSP
2010
IEEE
13 years 6 months ago
The effect of lattice pruning on MMIE training
In discriminative training, such as Maximum Mutual Information Estimation (MMIE) training, a word lattice is usually used as a compact representation of many different sentence hy...
Long Qin, Alexander I. Rudnicky
LREC
2008
93views Education» more  LREC 2008»
13 years 7 months ago
First Broadcast News Transcription System for Khmer Language
In this paper we present an overview on the development of a large vocabulary continuous speech recognition (LVCSR) system for Khmer, the official language of Cambodia, spoken by ...
Sopheap Seng, Sethserey Sam, Laurent Besacier, Bri...