Pitch tracking algorithm based on evolutionary computing with regularisation in very low SNR

The Journal of Engineering

Yongming Li¹  Xiaoheng Zhang² 

[1] TV University , Chongqing 400052 , People'Chongqing Radio &Communication Engineering of Chongqing University , Chongqing 400030 , People's Republic of China

关键词: two-norm term;    evolutionary algorithms;    pitch tracking algorithm;    pitch enhancement;    genetic algorithm;    matched filter;    very low SNR;    tracking rate;    particle swarm optimisation;    representative algorithms;    regularisation constraint;    evolutionary computing;    extraction model;    PTEAR_VLSNR;    voicing decision;    high signal-to-noise ratios;   

DOI  :  10.1049/joe.2018.8290

学科分类：工程和技术（综合）

来源: IET

【 摘 要 】

The authors present PTEAR_VLSNR (Pitch Tracking basing on Evolutionary Algorithm with Regularization at Very Low SNR), a pitch tracking algorithm for speech in strong noise. The algorithm builds a pitch enhancement and extraction model, which enhance the pitch by a matched filter, and to further deal with strong noise, the optimal factor was proposed, which can be optimised globally by the evolutionary computing. Specially, regularisation constraint of fitness function was applied to enhance the generalisation ability. Temporal dynamics constraints are used to improve the tracking rate and the voicing decision can be optimal by evolutionary computing similarly. In addition, the balance of optimisation accuracy and time cost were considered. In experiments, genetic algorithm and particle swarm optimisation with two-norm term were represented as evolutionary algorithms with regularisation. At last, they compare the performance of the algorithm and other representative algorithms. The experimental results show that this proposed algorithm performs well in both high and low signal-to-noise ratios (SNRs).

【 授权许可】

CC BY