配电变压器环境噪声识别关键技术研究

针对配电变压器环境噪声复杂多变的特点,提出一种基于小波变换、支持向量机(Support Vector Machine,SVM)、噪声特征库的噪声识别方法。该方法首先采用小波变换对噪声信号进行预处理,其次利用SVM提取噪声特征并进行分类识别,最后结合噪声特征库综合判定噪声类型。实验结果表明,该方法的噪声识别精度、召回率、F1值等指标均优于传统方法,为配电变压器精准降噪提供了新思路。

SPEECH ENHANCEMENT METHOD FOR LPC AUTOREGRESSIVE MODEL AND SYSTEM IMPLEMENTATION OF COMMAND WORD RECOGNITION USED IN NOISY ENVIRONMENT

At present, almost all the systems and products for speech recognition are working in quiet environment and their performances are degraded or even can′t work when they are operated in high noisy environment. In this paper, after analyzing the features of speech and noise, a speech enhancement method for LPC autoregressive model for command words recognition used in noisy environment is proposed, and an experimental system is realized. In different background noisy environments, we conduct experiments about SNR, basic accuracy, noise resistant ability and system environment adaptability with different microphones. The experimental results show that the system has good recognition performance in high noisy environments. The system can resist many kinds of noises and meet the needs of application areas on the whole such as military, traffic, marketplace and factory etc.