一种音频分类算法

An Algorithm for Real-time Audio Classification

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.