A novel research approach is presented in which the acoustic signals are visualized at first, then the image features are extracted for the classification. For speech signals 0~9 and three types of traffic noise signals, their spectrograms are given, and pulse coupled neural network is used to process the images, then average entropy and consistent degrees as image features are extracted, and BP neural network is used to achieve classification. The results show that this method has high recognition rate.
| 
推荐 
点击下列相关研究机构和相关文献作者，可以直接查到这些机构和作者被《中国知识资源总库》收录的其它文献，使您全面了解该机构和该作者的研究动态和历史。
