Sciweavers

ICASSP
2011
IEEE
12 years 7 months ago
A simplified Subspace Gaussian Mixture to compact acoustic models for speech recognition
Speech recognition applications are known to require a significant amount of resources (memory, computing power). However, embedded speech recognition systems, such as in mobile p...
Mohamed Bouallegue, Driss Matrouf, Georges Linares
ICASSP
2011
IEEE
12 years 7 months ago
Whole word discriminative point process models
This paper introduces a discriminative extension to whole-word point process modeling techniques. Meant to circumvent the strong independence assumptions of their generative prede...
Aren Jansen
ICASSP
2011
IEEE
12 years 7 months ago
Lattice-based unsupervised acoustic model training
Unsupervised acoustic model training has been successfully used to improve the performance of automatic speech recognition systems when only a small amount of manually transcribed...
Thiago Fraga-Silva, Jean-Luc Gauvain, Lori Lamel
ICASSP
2011
IEEE
12 years 7 months ago
Maximum likelihood adaptation of histogram equalization with constraint for robust speech recognition
In this paper, we propose a novel feature space adaptation technique to improve the robustness of speech recognition in noisy environments. Histogram equalization (HEQ) is an effe...
Xiong Xiao, Jinyu Li, Engsiong Chng, Haizhou Li
INTERSPEECH
2010
12 years 10 months ago
An improved wavelet-based dereverberation for robust automatic speech recognition
This paper presents an improved wavelet-based dereverberation method for automatic speech recognition (ASR). Dereverberation is based on filtering reverberant wavelet coefficients...
Randy Gomez, Tatsuya Kawahara
EMNLP
2007
13 years 5 months ago
Learning Structured Models for Phone Recognition
We present a maximally streamlined approach to learning HMM-based acoustic models for automatic speech recognition. In our approach, an initial monophone HMM is iteratively refin...
Slav Petrov, Adam Pauls, Dan Klein
ICASSP
2008
IEEE
13 years 10 months ago
Modified polyphone decision tree specialization for porting multilingual Grapheme based ASR systems to new languages
Automatic speech recognition (ASR) systems have been developed only for a very limited number of the estimated 7,000 languages in the world. In order to avoid the evolvement of a ...
Sebastian Stüker
ICASSP
2009
IEEE
13 years 10 months ago
Language model transformation applied to lightly supervised training of acoustic model for congress meetings
For effective training of acoustic and language models for spontaneous speech such as meetings, it is significant to exploit the texts available in a large scale, which may not b...
Tatsuya Kawahara, Masato Mimura, Yuka Akita