Noisy Speech Recognition Based on RBF Neural Network
2011 ◽
Vol 271-273
◽
pp. 597-602
Keyword(s):
A noisy speech recognition method based on improved RBF neural network is presented, which the parameters of hidden layer are trained dynamically, and Akaike’s final prediction error standard (FPE) is employed to simplify the network. Comparing with two other training methods of RBF network, experimental results based on noisy speech samples show that this method achieves excellent performance in terms of recognition rate and recognition speed.
2011 ◽
Vol 217-218
◽
pp. 413-418
Keyword(s):
2017 ◽
Vol 8
(2)
◽
pp. 667
◽
Keyword(s):
2014 ◽
Vol 543-547
◽
pp. 2333-2336
Keyword(s):
2014 ◽
Vol 971-973
◽
pp. 1816-1819
◽
Keyword(s):
2014 ◽
Vol 596
◽
pp. 245-250
Keyword(s):
Keyword(s):