Noise-Robust Speech Recognition Based on RBF Neural Network

Xue Mei Hou

doi:10.4028/www.scientific.net/AMR.217-218.413

Paper Titles

The Asymptotic Homogenization Method of the Settlement Calculation of the Cement-Soil Pile Composite Foundation
p.390

The Research on Image Segmentation for Fingerprint Identification
p.396

Measurement of Dynamic and Static Modulus for Thin Particleboard
p.402

Determining Modulus of Elasticity of Ancient Structural Timber
p.407

Noise-Robust Speech Recognition Based on RBF Neural Network
p.413

The Influencing Factors in Acoustic Nonlinearity Parameter B/A Measurement
p.419

Scraper Conveyor Dynamic Modeling and Simulation
p.426

Optimization Research on Structure Improvement of Stirring System for Preparation of Recycled Glass / Aluminum Matrix Composites with Stirring Casting Technique
p.431

Improved Thermal Conductivity of Compostie Particles Filled Epoxy Resin
p.439

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 217-218Noise-Robust Speech Recognition Based on RBF...

Noise-Robust Speech Recognition Based on RBF Neural Network

Abstract:

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.