Pacific-Asia Workshop on Computational Intelligence and Industrial Application

Quantum BP Neural Network for speech enhancement

Fei Li, Guobiao Xu

Published Nov 1, 2009• 13 citations

Abstract

Quantum Neural Network (QNN), a burgeoning new field which integrates quantum computation with classical neural network, can improve the inadequacies of artificial neural network. A model of quantum neuron and Quantum Back Propagation (BP) Neural Network based on quantum neuron are investigated. A novel approach toward speech enhancement which adopts Quantum BP Neural Network is proposed. The numerical simulation results show that the proposed speech enhancement scheme resulted in better performance than traditional spectral subtraction, Wiener filtering method and RBF neural network.

DOI: 10.1109/paciia.2009.5406577

Related papers

Research on Quantum Neuron Characteristics Based on Ack Propagation(BP)

Shengmei Zhao

Quantum Neural Networks(QNN) Integrates the characteristics of artificial neural networks by quantum neuron computing,and becomes a promising field in information processing.A quantum neuron model by the conventional back propagation with learning rule,is established based on the phase-shift gate and thecontrolled-Not gate acted as the basic computational component.Finally its convergence performance curve of the quantum neuron is given by the numerical simulation.

Journal of Jiangsu Radio & Television UniversityJan 1, 20060 citations

Quantum BP Neuron and Its Application in Recognition of Noisy English Letter

Guangqiang Zhang

Quantum Neural Networks(QNN),which integrates the characteristics of artificial neural networks with quantum computing,will become a promising field of information processing.In this paper,a quantum neuron model based on the phase-shift gate and controlled-not gate is constructed with the conventional back propagation learning rule.Its convergence performance is discussed by numerical simulations.Based on this model,a three-layers quantum networks is proposed.The numerical experiments of the identification of noisy English letters show that the proposed quantum networks can identify the noisy English letters efficaciously when the noise variance is less than 0.35,and has more improvement performance in anti-noise than that of conventional Back-Propagation Neural Network.

Journal of Nanjing University of Posts and TelecommunicationsJan 1, 20070 citations

Quantum-Inspired Neural Network with Quantum Weights and Real Weights

Fuhua Shang

To enhance the approximation ability of neural networks, by introducing quantum rotation gates to the traditional BP networks, a novel quantum-inspired neural network model is proposed in this paper. In our model, the hidden layer consists of quantum neurons. Each quantum neuron carries a group of quantum rotation gates which are used to update the quantum weights. Both input and output layer are composed of the traditional neurons. By employing the back propagation algorithm, the training algorithms are designed. Simulation-based experiments using two application examples of pattern recognition and function approximation, respectively, illustrate the availability of the proposed model.

Open Journal of Applied SciencesJan 1, 20159 citations

Quantum neural network in speech recognition

Fei Li, Shengmei Zhao, Baoyu Zheng

This paper describes a new kind of neural network - quantum neural network (QNN) and its application to recognition of continuous digits. QNN combines the advantages of neural modeling and fuzzy theoretic principles. Experiment results show that more than 15% error reduction is achieved on a speaker-independent continuous digits recognition task compared with the backpropagation (BP) network.

Oct 1, 200336 citations

Research of Image Compression Based on Quantum BP Network

Qigao Feng, Haoyu Zhou

Quantum Neural Network (QNN), which integrates the characteristics of Artificial Neural Network (ANN) with quantum theory, is a new study field. It takes advantages of ANN and quantum computing and has a high theoretical value and potential applications. Based on quantum neuron model with a quantum input and output quantum and artificial neural network theory, at the same time, QBP algorithm is proposed on the basis of the complex BP algorithm, the network of a 3-layer quantum BP which implements image compression and image reconstruction is built. The simulation results show that QBP can obtain the reconstructed images with better quantity compared with BP in spite of the less learning iterations.

TELKOMNIKA Indonesian Journal of Electrical EngineeringDec 2, 20134 citations

Recognition of Noisy English Letter by Quantum Back Propagation Network

Shengmei Zhao, Jianhua Huang, Baoyu Zheng

It is suggested that a type of artificial neural network can be built using the principles of quantum information processing. A new technique for the recognition of noisy English letter using quantum neural network is proposed in this paper. A qubit neuron model based on quantum mechanics, constructed the quantum back propagation learning rule network (QBP) is given, and a high reliability has been achieved. The numerical experiments of the identification of noisy English letters based on the quantum network has been performed, it is shown that QBP can identify the noised English letters efficaciously; the recognition rate may reach the 100% when the variance of the noise is less than 0.35, and has more improvement performance in anti-noise than that of conventional back propagation neural network, the error recognition rate decreases from 20.46% to 3 % when the noise variance is set to 0.40

Jan 1, 20062 citations