TR-I-0122 :Nov. 7,1989

川端豪

構成的ニューラルネットによる音声認識

Abstract:A new method to combine phone TDNNs for constructing word or continuous speech networks is proposed. The method is called Constructive Neural Network (CNN). The CNN method has the following important features: (1) Any word network can be composed of neural phone verifiers according to its phonetic representation. (2) Non-linear time warping is realized using only a network structure including FIR filters which control the duration between each phone pairs independently. (3) Word-level backpropagation learning can be used for training the TDNN phone recognizers.