Recurrent neural networks (RNNs) can be used to handle sequential patterns and have been used for speech recognition. To overcome the shortcomings of RNN, recurrent sub neural networks (RSNNs) are used, where an RSNN is built independently for each class. The training algorithm of the RSNN is based on the backpropagation algorithm. Speaker dependent connected Chinese digit-speech recognition experiments were carried out. Some factors influencing the performance of RSNNs have been studied. The experiments show that RSNN is easier to train and gives higher performance than RNN.<>
Recurrent sub neural networks applied to speech recognition
1994-01-01
328232 byte
Conference paper
Electronic Resource
English
Recurrent Sub Neural Networks Applied to Speech Recognition
British Library Conference Proceedings | 1994
|Visual speech recognition by recurrent neural networks
British Library Online Contents | 1998
|Parallel Neural Networks for Speaker-Independent All-Chinese-Syllable Speech Recognition
British Library Conference Proceedings | 1994
|