Sciweavers

55 search results - page 11 / 11
» Large vocabulary continuous speech recognition with context-...
Sort
View
LREC
2010
173views Education» more  LREC 2010»
13 years 9 months ago
Language Modeling Approach for Retrieving Passages in Lecture Audio Data
Spoken Document Retrieval (SDR) is a promising technology for enhancing the utility of spoken materials. After the spoken documents have been transcribed by using a Large Vocabula...
Koichiro Honda, Tomoyosi Akiba
LREC
2008
93views Education» more  LREC 2008»
13 years 9 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...
ICASSP
2010
IEEE
13 years 7 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
INTERSPEECH
2010
13 years 2 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
NAACL
1994
13 years 9 months ago
The Hub and Spoke Paradigm for CSR Evaluation
In this paper, we introduce the new paradigm used in the most recent ARPA-sponsoredContinuousSpeech Recognition(CSR) evaluation and then discuss the important features of the test...
Francis Kubala, Jerome R. Bellegarda, Jordan Cohen...