Pacific-Asia Workshop on Computational Intelligence and Industrial Application, IEEE (2008)
Dec. 19, 2008 to Dec. 20, 2008
This paper proposes a new approach for speaker-independent continuous Chinese digit speech recognition based on multi-weighted neural network. By analyzing the geometrical meaning of the multi-weighted neuron function and on the principle of continuity point of view, this approach constructs a multi-weighted neural network. This network shows better recognition results when applied in digit speech recognition. Its correct recognition rate is higher than HMM.
Multi-weighted Neural Network, Speech Recognition
S. Wang, C. Xu and X. Wang, "Research on Chinese Digit Speech Recognition Based on Multi-Weighted Neural Network," 2008 Pacific-Asia Workshop on Computational Intelligence and Industrial Application. PACIIA 2008(PACIIA), Wuhan, 2008, pp. 400-403.