Title :
A Novel Scheme of Speech Enhancement Based on Quantum Neural Network
Author :
Li, Fei ; Xu, Guobiao
Author_Institution :
Inst. of Signal Process. & Transm., Nanjing Univ. of Posts & Telecommun., Nanjing, China
Abstract :
Quantum neural network (QNN) gives us some advantages unattainable by classical artificial neural network. A model of quantum neuron composed of quantum gates is described. A model of quantum back propagation neural network (QBPNN) based on the quantum neuron and its training algorithm is investigated. A novel approach toward speech enhancement which adopts QBPNN is proposed. For comparison, evaluations were also done for classical NN and other methods. The experiments results show that the scheme of speech enhancement based on QBPNN has better denoising effect and robustness than the traditional methods.
Keywords :
backpropagation; neural nets; quantum computing; speech enhancement; QBPNN; classical artificial neural network; quantum back propagation neural network; quantum gates; quantum neuron; speech enhancement; training algorithm; Artificial neural networks; Asia; Computer networks; Electronic mail; Neural networks; Neurons; Quantum computing; Quantum mechanics; Signal processing algorithms; Speech enhancement;
Conference_Titel :
Intelligent Interaction and Affective Computing, 2009. ASIA '09. International Asia Symposium on
Conference_Location :
Wuhan
Print_ISBN :
978-0-7695-3910-2
Electronic_ISBN :
978-1-4244-5406-8
DOI :
10.1109/ASIA.2009.36