Parameter influence on speech recognition rate of modified RBF neural network

2010 ◽  
Author(s):  
Xia Wang ◽  
Jian Tian ◽  
Mengjun Wang
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Rbf Neural Network ◽  
Recognition Rate ◽  
Parameter Influence

Noisy Speech Recognition Based on RBF Neural Network

2011 ◽  
Vol 271-273 ◽  
pp. 597-602
Author(s):  
Gang Yan ◽  
Hai Dong Kong ◽  
Yang Yu ◽  
Xiao Xia Zheng
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Rbf Neural Network ◽  
Recognition Rate ◽  
Training Methods ◽  
Noisy Speech ◽  
Rbf Network ◽  
Final Prediction Error ◽  
Noisy Speech Recognition ◽  
Hidden Layer

A noisy speech recognition method based on improved RBF neural network is presented, which the parameters of hidden layer are trained dynamically, and Akaike’s final prediction error standard (FPE) is employed to simplify the network. Comparing with two other training methods of RBF network, experimental results based on noisy speech samples show that this method achieves excellent performance in terms of recognition rate and recognition speed.

Speech Recognition Algorithm Based on Empirical Mode Decomposition and RBF Neural Network

2013 ◽  
Vol 831 ◽  
pp. 465-469
Author(s):  
Wei Wei Shi ◽  
Wei Hua Xiong ◽  
Wei Chen
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Empirical Mode Decomposition ◽  
Rbf Neural Network ◽  
Recognition Rate ◽  
Good Method ◽  
Recognition Algorithm ◽  
Intrinsic Mode Functions ◽  
Mode Decomposition ◽  
Learning Speed

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 Neural Network, RBF Neural Network has advantages on approximating ability and learning speed. So using RBF Neural Network 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.

Noise-Robust Speech Recognition Based on RBF Neural Network

2011 ◽  
Vol 217-218 ◽  
pp. 413-418
Author(s):  
Xue Mei Hou
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Clustering Algorithm ◽  
Rbf Neural Network ◽  
Recognition Rate ◽  
Recognition System ◽  
Robust Speech Recognition ◽  
Rbf Network ◽  
Noise Robust Speech Recognition ◽  
Noise Robust

Considering the actuality of current speech recognition and the characteristic of RBF neural network, a noise-robust speech recognition system based on RBF neural network is proposed with the entire-supervised algorithm. If the traditional clustering algorithm is employed, there is a flaw that the node center of hidden layer is always sensitive to the initial value, but if the entire-supervised algorithm is used, the flaw will not turn up, and the classification ability of RBF network will be enhanced. Experimental results show that, compared with the traditional clustering algorithm, the entire-supervised algorithm is of higher recognition rate in different SNRs than that of clustering algorithm.

scholarly journals Research on Speaker Recognition of DRNN in Different Noise Environment

2020 ◽  
Author(s):  
chaofeng lan ◽  
yuanyuan Zhang ◽  
hongyun Zhao
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Recurrent Neural Network ◽  
Speaker Recognition ◽  
Signal To Noise Ratio ◽  
Recognition Rate ◽  
Noisy Environment ◽  
Signal To Noise ◽  
Noise Ratio ◽  
Improved Model

Abstract This paper draws on the training method of Recurrent Neural Network (RNN), By increasing the number of hidden layers of RNN and changing the layer activation function from traditional Sigmoid to Leaky ReLU on the input layer, the first group and the last set of data are zero-padded to enhance the effective utilization of data such that the improved reduction model of Denoise Recurrent Neural Network (DRNN) with high calculation speed and good convergence is constructed to solve the problem of low speaker recognition rate in noisy environment. According to this model, the random semantic speech signal with a sampling rate of 16 kHz and a duration of 5 seconds in the speech library is studied. The experimental settings of the signal-to-noise ratios are − 10dB, -5dB, 0dB, 5dB, 10dB, 15dB, 20dB, 25dB. In the noisy environment, the improved model is used to denoise the Mel Frequency Cepstral Coefficients (MFCC) and the Gammatone Frequency Cepstral Coefficents (GFCC), impact of the traditional model and the improved model on the speech recognition rate is analyzed. The research shows that the improved model can effectively eliminate the noise of the feature parameters and improve the speech recognition rate. When the signal-to-noise ratio is low, the speaker recognition rate can be more obvious. Furthermore, when the signal-to-noise ratio is 0dB, the speaker recognition rate of people is increased by 40%, which can be 85% improved compared with the traditional speech model. On the other hand, with the increase in the signal-to-noise ratio, the recognition rate is gradually increased. When the signal-to-noise ratio is 15dB, the recognition rate of speakers is 93%.

A Finger Vein Recognition Method Based on PCA-RBF Neural Network

2013 ◽  
Vol 325-326 ◽  
pp. 1653-1658 ◽  
Author(s):  
Cheng Bo Yu ◽  
Jun Tan ◽  
Lei Yu ◽  
Yin Li Tian
Keyword(s):  
Neural Network ◽  
Rbf Neural Network ◽  
Recognition Rate ◽  
Back Propagation ◽  
Principal Component ◽  
Training Sample ◽  
Finger Vein ◽  
Simpler Algorithm ◽  
Vein Recognition ◽  
Finger Vein Recognition

This paper puts forward a finger vein classification algorithm which combines Principal Component Analysis (PCA) with Radial Basis Function (RBF) neural network algorithm, named the PCA-RBF algorithm. Use the training sample to reduce PCA dimensions, and abstract the main component of the image. Because of the advantages of RBF neural network classifying, put finger vein images into different classes, and then use the shortest distance to recognize. Through the experiment result comparing with Back Propagation (BP) neural network, PCA-RBF neural network is better in finger vein recognition. The result shows that PCA-RBF has faster training speed, simpler algorithm and higher recognition rate.

Comparison between BP and RBF Neural Network Pattern Recognition Process Applied in the Droplet Analyzer

2014 ◽  
Vol 543-547 ◽  
pp. 2333-2336
Author(s):  
Qing Song ◽  
Gao Jie Meng ◽  
Lu Yang ◽  
Dan Qing Du ◽  
Xue Fei Mao
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Liquid Droplet ◽  
Rbf Neural Network ◽  
Recognition Rate ◽  
Uncertain System ◽  
Training Data ◽  
Waveform Analysis ◽  
Bp Network ◽  
Rbf Network

Among various pattern recognition methods used for liquid identification, the method based on neural network has the advantages of robustness and fault tolerance, which can study and adapt to the uncertain system. The waveform analysis is exploited for feature extraction of the liquid droplet fingerprint (LDF) in this paper, and the liquid identification is carried out by means of BP and RBF neural network. The experimental results proved that the recognition rate is excellent in both of these two methods. In condition that the training data is limited, RBF network is better than BP network in recognition speed and rate.

Sign in / Sign up

Export Citation Format

Share Document