电子学报 ›› 2018, Vol. 46 ›› Issue (11): 2705-2713.DOI: 10.3969/j.issn.0372-2112.2018.11.018

• 学术论文 • 上一篇    下一篇

基于多随机森林的低信噪比声音事件检测

李应1,2, 印佳丽1,2   

  1. 1. 福州大学数学与计算机科学学院, 福建福州 350116;
    2. 网络系统信息安全福建省高校重点实验室, 福建福州 350116
  • 收稿日期:2016-12-02 修回日期:2018-06-03 出版日期:2018-11-25
    • 作者简介:
    • 李应 男,1964年出生,福建闽清人,福州大学数学与计算机科学教授,主要研究领域为信息安全,多媒体数据检索.E-mail:fj_liying@fzu.edu.cn;印佳丽 女,1993年出生,江苏盐城人,硕士,主要研究领域为模式识、环境声音检测.
    • 基金资助:
    • 国家自然科学基金 (No.61075022); 福建省自然科学基金 (No.2018J01793)

Sound Event Detection at Low SNR Based on Multi-random Forests

LI Ying1,2, YIN Jia-li1,2   

  1. 1.College of Mathematics and Computer Science, Fuzhou University, Fuzhou, Fujian 350116, China;
    2.Key Lab of Information Security of Network Systems (Fuzhou University), Fuzhou, Fujian 350116, China
  • Received:2016-12-02 Revised:2018-06-03 Online:2018-11-25 Published:2018-11-25
    • Supported by:
    • National Natural Science Foundation of China (No.61075022); Natural Science Foundation of Fujian Province (No.2018J01793)

摘要: 论文针对各种背景声音中低信噪比声音事件的检测问题,提出把背景声音与声音事件混合,形成带噪声样本来训练分类器.在预处理阶段,使用基于经验模态分解与2-6级固有模态函数的投票方法,对背景声音与声音事件端点进行预测并估算信噪比.接着使用子带能量分布方法,提取声音数据的特征.最后,论文将背景声音与声音事件样本库中所有声音样本按照估算的信噪比相混合,生成混合声音特征训练多随机森林,用于低信噪比声音事件的检测.实验证实,所提出的方法可以用于各种声场景下低信噪比声音事件的检测,并能在信噪比为-5dB的情况下保持67.1%的平均检测率.

关键词: 声音事件检测, 信噪比, 经验模态分解, 子带能量分布, 随机森林

Abstract: For sound event detection under various background noises at low SNR, this paper proposes a method that mixes the background noises with sound events into noisy samples to train classifiers. In the pre-processing stage, we use a voting method based on 2th to 6th intrinsic mode functions (IMFs) that generated from empirical mode decomposition (EMD), to detect the endpoint of sound events and estimate the SNR. Then subband power distribution (SPD) is used to extract features from audio data. Finally, we mix the background noise and all the sound event samples in the sound event database according to the estimated SNR, and then extract the noisy samples features to train multi-random forests (M-RF) for the detection of the sound events in low SNR environment. The experiment proves that the proposed method has the ability to recognize sound events in various acoustic scenes at low SNR, and can remain an average accuracy rate of 67.1% at-5dB.

Key words: sound event detection, signal-to-noise ratio (SNR), empirical mode decomposition, subband power distribution, random forests

中图分类号: