Sciweavers

509 search results - page 60 / 102
» icassp 2008
Sort
View
ICASSP
2008
IEEE
15 years 7 months ago
Discriminative learning for optimizing detection performance in spoken language recognition
We propose novel approaches for optimizing the detection performance in spoken language recognition. Two objective functions are designed to directly relate model parameters to tw...
Donglai Zhu, Haizhou Li, Bin Ma, Chin-Hui Lee
ICASSP
2008
IEEE
15 years 7 months ago
Combination of strongly and weakly constrained recognizers for reliable detection of OOVS
This paper addresses the detection of OOV segments in the output of large vocabulary continuous speech recognition (LVCSR) system. First, standard confidence measures based on fr...
Lukas Burget, Petr Schwarz, Pavel Matejka, Mirko H...
82
Voted
ICASSP
2008
IEEE
15 years 7 months ago
An unsupervised web-based topic language model adaptation method
This paper focuses on a solution to better adapt ASR systems, whose language models (LM) are usually trained on topic-independent corpora, to new topics, in particular in the case...
Gwénolé Lecorvé, Guillaume Gr...
ICASSP
2008
IEEE
15 years 7 months ago
Target-oriented phone tokenizers for spoken language recognition
This paper presents a new strategy for designing the parallel phone recognizers for spoken language recognition. Given a collection of parallel phone recognizers, we select a subs...
Rong Tong, Bin Ma, Haizhou Li, Engsiong Chng
78
Voted
ICASSP
2008
IEEE
15 years 7 months ago
Cepstral domain feature compensation based on diagonal approximation
In this paper, we propose a novel approach to feature compensation performed in the cepstral domain. We apply the linear approximation method in the cepstral domain to simplify th...
Woohyung Lim, Chang Woo Han, Jong Won Shin, Nam So...