Sciweavers

316 search results - page 16 / 64
» Evaluation of random-projection-based feature combination on...
Sort
View
EMNLP
2008
13 years 10 months ago
Integrating Multi-level Linguistic Knowledge with a Unified Framework for Mandarin Speech Recognition
To improve the Mandarin large vocabulary continuous speech recognition (LVCSR), a unified framework based approach is introduced to exploit multi-level linguistic knowledge. In th...
Xinhao Wang, Jiazhong Nie, Dingsheng Luo, Xihong W...
ICASSP
2010
IEEE
13 years 9 months ago
A kernel mean matching approach for environment mismatch compensation in speech recognition
The mismatch between training and test environmental conditions presents a challenge to speech recognition systems. In this paper, we investigate an approach for matching the dist...
Abhishek Kumar, John H. L. Hansen
ICASSP
2011
IEEE
13 years 15 days ago
Non-linear noise compensation for robust speech recognition using Gauss-Newton method
In this paper, we present the Gauss-Newton method as a unified approach to optimizing non-linear noise compensation models, such as vector Taylor series (VTS), data-driven parall...
Yong Zhao, Biing-Hwang Juang
ICASSP
2008
IEEE
14 years 3 months ago
Frame-based acoustic feature integration for speech understanding
With the purpose of improving Spoken Language Understanding (SLU) performance, a combination of different acoustic speech recognition (ASR) systems is proposed. State a-posteriori...
Loic Barrault, Christophe Servan, Driss Matrouf, G...
ICASSP
2011
IEEE
13 years 14 days ago
On the use of ideal binary masks for improving phonetic classification
Ideal binary masks are binary patterns that encode the masking characteristics of speech in noise. Recent evidence in speech perception suggests that such binary patterns provide ...
Arun Narayanan, DeLiang Wang