366 search results - page 16 / 74 » Canonical state models for automatic speech recognition |
ICASSP
2009
IEEE
15 years 4 months ago
2009
IEEE
A conventional automatic speech recognizer does not perform well in the presence of noise, while human listeners are able to segregate and recognize speech in noisy conditions. We...
76
Voted
ICASSP
2010
IEEE
14 years 9 months ago
2010
IEEE
Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approa...
67
Voted
ICASSP
2010
IEEE
14 years 9 months ago
2010
IEEE
In this paper, we use information retrieval (IR) techniques to improve a speech recognition (ASR) system. The potential benefits include improved speed, accuracy, and scalability...
WCE
2007
14 years 10 months ago
2007
—One problem of generating a model to recognize any string is how to generate one that is generalized enough to accept strings with similar patterns and, at the same time, is spe...
106
Voted
IJCNN
2006
IEEE
15 years 3 months ago
2006
IEEE
— 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...