计算机工程与应用 ›› 2015, Vol. 51 ›› Issue (2): 198-204.

• 信号处理 • 上一篇    下一篇

基于萤火虫算法的匹配追踪用于生态声音辨识

欧阳桢,李  应   

  1. 福州大学 数学与计算机科学学院,福州 350108
  • 出版日期:2015-01-15 发布日期:2015-01-12

Glowworm swarm optimization and matching pursuit sparse decomposition for ecological environmental sounds identification

OUYANG Zhen, LI Ying   

  1. College of Mathematics and Computer Science, Fuzhou University, Fuzhou 350108, China
  • Online:2015-01-15 Published:2015-01-12

摘要: 针对生态环境中背景噪声对声音辨识产生干扰的问题,提出利用萤火虫算法优化匹配追踪的方法进行生态声音辨识。利用匹配追踪(MP)稀疏分解声音信号,在保留信号主体结构的前提下对其进行重构,减小噪声的影响。使用萤火虫(GSO)算法优化搜索最佳匹配原子,实现MP快速分解。对重构信号提取Mel频率倒谱系数(MFCCs),MP时频特征及基音频率。结合支持向量机(SVM)对56种生态声音在不同环境和信噪比情况下进行分类识别。实验结果表明,与传统MFCC与SVM的方法相比,该方法对生态声音在不同信噪比下的识别性能得到不同程度的改善并且具有较好的抗噪性,尤其适合低信噪比(30 dB以下)噪声情境下使用。

关键词: 生态声音辨识, 匹配追踪, 萤火虫算法, 信号稀疏分解, Mel频率倒谱系数

Abstract: The paper proposes a robust ecological environmental sounds identification system by using optimized matching pursuit algorithm which is optimized by Glowworm Swarm Optimization(GSO) to improve the performance of sound recognition in real environmental noisy conditions. It uses the Matching Pursuit(MP) to decompose the sound signal sparsely, and reconstructs its inner structure to reduce the influence of the noise. GSO is employed to speed up the searching for the best atom in each process of decomposition. Different feature sets are extracted. As the performance of popular Mel-Frequency Cepstral Coefficients(MFCC) degrades due to sensitivity to noise, MP based time-frequency features and Pitch are adopted to supplant the MFCCs feature. Through the SVM classifier, 56 subclasses of 4 classes of ecological environmental sounds are tested for the comparison experiments in different environments under different SNRs. The experimental results show that this approach outperforms traditional methods of MFCCs and SVM, as the average identification accuracy and robustness for ecological environmental sounds are improved to a different degree, especially under the conditions of SNRs lower than 30 dB.

Key words: ecological environmental sounds recognition, matching pursuit, glowworm swarm optimization, sparse decomposition, mel-frequency cepstral coefficients