Sciweavers

2047 search results - page 106 / 410
» The limits of speech recognition
Sort
View
ICPR
2006
IEEE
14 years 10 months ago
Switching Auxiliary Chains for Speech Recognition based on Dynamic Bayesian Networks
This paper investigates the problem of incorporating auxiliary information (e.g. pitch) for speech recognition using dynamic Bayesian networks (DBNs). Previous works usually model...
Hui Lin 0001, Zhijian Ou
ICASSP
2009
IEEE
14 years 3 months ago
Generalized Baum-Welch algorithm for discriminative training on large vocabulary continuous speech recognition system
We propose a new optimization algorithm called Generalized Baum Welch (GBW) algorithm for discriminative training on hidden Markov model (HMM). GBW is based on Lagrange relaxation...
Roger Hsiao, Yik-Cheung Tam, Tanja Schultz
ICASSP
2008
IEEE
14 years 3 months ago
Name-aware speech recognition for interactive question answering
In this work we show how interactivity in a voice-enabled question answering application may improve speech recognition. We allow the user to provide a target named entity before ...
Svetlana Stoyanchev, Gökhan Tür, Dilek Z...
ICMCS
2006
IEEE
112views Multimedia» more  ICMCS 2006»
14 years 2 months ago
Minimum Phoneme Error based Filter Bank Analysis for Speech Recognition
In this paper the optimal filter-bank design method based on the Minimum Phone Error (MPE) criteria is investigated. We use Gaussian type filter bank for optimization and variou...
Hao Huang, Jie Zhu
IJCNN
2006
IEEE
14 years 2 months ago
Reservoir-based techniques for speech recognition
— A solution for the slow convergence of most learning rules for Recurrent Neural Networks (RNN) has been proposed under the terms Liquid State Machines (LSM) and Echo State Netw...
David Verstraeten, Benjamin Schrauwen, Dirk Stroob...