基于APR—SVM的音频分类方法

音频分类在多媒体应用中十分广泛，主要有时域分析和频域分析方法。文中提出了一种基于自适应间距比（APR）算法和支持向量机（svrd）算法的音频分类方法，先用APR算法区分语音与非语音；对于非语音，再通过SVM进行音频分类。APR算法是比较PR参数和阈值来区分语音和非语音，它和信噪比密切相关；而将非语音分成四组：音乐，汽车，会议，雨声，提取特征因子。实验结果表明：文中设计的分类器的精度达到93．75％以上，能很好地把各类型音频分开。

Audio Classification Based on APR-SVM

Audio classification is widely applied in multimedia applications, which mainly has time domain analysis and frequency domain analysis methods. In this paper,an audio classification method based on APR algorithm and SVM algorithm is proposed,first use the APR algorithm to distinguish between voice and non voice,for non-voice take audio classification by SVM. APR algorithm is to compare the PR parameters and thresholds to distinguish between voice and non voice,is closely related to SNR ,and non-voiee is divided into four groups：music,cars,meeting, rain, extract the feature factor. The experimental results show that：the accuracy of the classifier designed in this paper is to reach over 93.75% ,good separation of various types of audio.