|
| 摘要: |
| 在声音识别系统中，特征参数的获取对声音识别和训练有着重要的影响；MFCC算法作为典型的声音特征参数提取方法，性能稳定，识别率高；针对MFCC算法存在较大计算量的情况，提出一种改进的特征参数提取算法MFCC_E；相比于标准的MFCC算MFCC_E算法减少了约50%的运算量,并且易于硬件实现；实验结果表明MFCC_E算法与MFCC算法的识别率大致相同,而计算复杂度却小很多。 |
| 关键词: 声音识别 特征提取 MFCC MFCC_E GMM |
| DOI： |
| 分类号: |
| 基金项目: |
|
| Abnormal Audio Recognition Algorithm Based on Improved MFCC |
|
HE Ling-ling,ZHOU Yuan
|
| Abstract: |
| In audio recognition system,the acquisition of characteristic parameters has important influence on audio recognition and training.MFCC algorithm,as a typical audio characteristic parameter extraction method,has stable performance and high recognition rate.According to the situation that MFCC algorithm has larger amount of computation,a kind of improved characteristic parameter extraction algorithm,MFCC-E,was pointed out.Compared with... |
| Key words: audio recoginition characteristic extraction MFCC MFCC_E GMM |
