一种音频分类算法  

An Algorithm for Real-time Audio Classification

作　　者：梅铁民[1] 路瑞茜 

机构地区：[1]沈阳理工大学自动化与电气工程学院,沈阳110159

出　　处：《沈阳理工大学学报》2016年第5期23-27,共5页Journal of Shenyang Ligong University

摘　　要：在综合分析了不同音频信号的有效区别性特征后,根据低能量帧率和子带能量在不同音频信号中的特征,对音频信号分类算法进行了研究。提出了一种综合利用低能量帧率和子带能量比的音频信号分类算法。通过仿真和实验,对连续噪声信号、音乐信号、语音信号进行了分类,结果证明该算法具有较好的分类效果。Audio signal classification plays an important role in audio signal processing, and is an important previous job in many audio signal analysis progress. After a comprehensive analysis of the effective distinguishing features for different audio signals, audio classification research is carded out. A new audio classification algorithm is proposed according to the low-energy frame rate and sub-band energy in the different audio signals. Simulation results show that the proposed algorithm is of low complexity and high classification accuracy.

关 键 词：音频分类 低能量帧率 子带能量比 

分 类 号：TN911[电子电信—通信与信息系统]