Optimal pattern synthesis for speech recognition based on principal component analysis

2017 Workshop on Materials and Engineering in Aeronautics

材料科学;航空航天工程

Korsun, O.N.^1 ; Poliyev, A.V.^2

State Research Institute of Aviation Systems, Moscow

125319, Russia^1

Moscow Institute of Physics and Technology, Moscow

117303, Russia^2

关键词: Automatic speech recognition;    Multi-parameter optimizations;    Optimization algorithms;    Parameter optimization;    Pattern synthesis;    Principal Components;    Principal components decomposition;    Probability of correct recognition;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/312/1/012014/pdf
DOI  :  10.1088/1757-899X/312/1/012014

来源: IOP

【 摘 要 】

The algorithm for building an optimal pattern for the purpose of automatic speech recognition, which increases the probability of correct recognition, is developed and presented in this work. The optimal pattern forming is based on the decomposition of an initial pattern to principal components, which enables to reduce the dimension of multi-parameter optimization problem. At the next step the training samples are introduced and the optimal estimates for principal components decomposition coefficients are obtained by a numeric parameter optimization algorithm. Finally, we consider the experiment results that show the improvement in speech recognition introduced by the proposed optimization algorithm.