This paper presents a novel method of the speech recognition in combining the empirical mode decomposition with radical basis function neural network. Speech signals which pretreated are decomposed by empirical mode d...
详细信息
ISBN:
(纸本)9783037859155
This paper presents a novel method of the speech recognition in combining the empirical mode decomposition with radical basis function neural network. Speech signals which pretreated are decomposed by empirical mode decomposition to get a set of intrinsic mode functions. It extracts mel frequency cepstrum coefficient from intrinsic mode function. Features parameters are made up of the coefficients. For BP neuralnetwork, RBF neuralnetwork has advantages on approximating ability and learning speed. So using RBF neuralnetwork as a recognition model is a good method. Experiments show that this new method has good robustness and adaptability. The speech recognition rate of this method reach ninety-one percents accurately under no noise environment. Speech signal recognition is feasible and effective in noisy environment.
In order to achieve high motion accuracy and better robustness of the rocket launcher position servo system driven by a permanent magnet synchronous motor, a passivity-based controller based on improved active disturb...
详细信息
In order to achieve high motion accuracy and better robustness of the rocket launcher position servo system driven by a permanent magnet synchronous motor, a passivity-based controller based on improved active disturbance rejection control is proposed in this article. The convenient method of interconnection and damping assignment and passivity-based control is adopted to establish the port-controlled Hamiltonian system with dissipation model of permanent magnet synchronous motor. To further enhance the robustness and adaptability of the traditional active disturbance rejection controller, an improved active disturbance rejection control strategy-based radical basis function neural network is introduced to on-line update the proportional and derivative gains of improved active disturbance rejection controller. The results of numerical simulation and bench test indicate that the proposed improved active disturbance rejection control passivity-based control algorithm has advantages of smaller overshoot, fast response, small steady-state error, and strong robustness. It proves that the proposed control scheme is effective and suitable.
The nonlinear characteristic of Chinese speech signal is further studied, combined with radical basis function neural network, a nonlinear prediction model is designed. Firstly, delay time, embed dimension and maximum...
详细信息
ISBN:
(纸本)9781510868755
The nonlinear characteristic of Chinese speech signal is further studied, combined with radical basis function neural network, a nonlinear prediction model is designed. Firstly, delay time, embed dimension and maximum lyapunov exponent of Chinese speech phoneme are calculated by using C-C algorithm, false neatest neighbor algorithm and wolf algorithm, it is found out that Chinese speech signal has nonlinear characteristic. Secondly, combined with delay time and embed dimension, radical basis function neural network analysis method is applied successfully to design nonlinear prediction model. Lastly, compared with adaptive differential pulse code modulation linear prediction model and back propagation neuralnetwork nonlinear prediction model, prediction error of the nonlinear prediction model is significantly reduced, and the prediction performance gets much better.
Considering the advantages and limitations of traditional RBF in prediction,an improved BRF based on ant colony clustering algorithm is introduced in this paper. This method is used to predict the demand of emergency ...
详细信息
Considering the advantages and limitations of traditional RBF in prediction,an improved BRF based on ant colony clustering algorithm is introduced in this paper. This method is used to predict the demand of emergency *** of artificial neuralnetwork algorithm's advantages,such as strong learning ability and non-linear aproximation of various levels of accuracy,this method is widely adopted in prediction.A RBF network is developed in this paper by adding ant colony clustering algorithm with can search in the local *** the weights of the connections between hidden layer and output layer are desinged by linear approach base on the expected outputs of the hidden and output ***,the approach in predicting the demand of emergency logistics is established. And a case study has been made to show the validity of this approach,where this method was adopted in predicting the demand of emergency logistics in anti-tropical cyclone *** experimental studies were conducted by MATLAB.
暂无评论