Page 214 - 《应用声学）》2023年第5期

第 42 卷 第 5 期 Vol. 42, No. 5
2023 年 9 月 Journal of Applied Acoustics September, 2023

⋄ 研究报告 ⋄

基于子频带能量特征提取的汽车鸣笛声识别 ∗

侯晓飞 1 穆瑞林 1,2† 周 晋 3 贾自杰 1

(1 天津科技大学机械工程学院 天津 300222)
(2 天津市轻工与食品工程机械装备集成设计与在线监控重点实验室 天津 300222)
(3 天津市房地产市场服务中心 天津 300222)

摘要：为了快速准确地识别城市中汽车违法鸣笛声并将不同种鸣笛声进行分类，该文应用子频带能量提取鸣
笛声的特征，利用 BP 神经网络对提取的子频带能量特征值矩阵进行学习训练，且在神经网络学习过程中利用
可变学习速度的方法，减小了神经网络的迭代次数。实验表明，利用此种子频带能量特征提取法使鸣笛声与非
鸣笛声的平均识别率达到了 94.889%；使不同鸣笛声之间的分类正确率最大达到了 93.75%，实现了不同鸣笛
声之间的分类。利用子频带能量法，能够很好地满足不同种鸣笛声识别与分类的需求。
关键词：鸣笛声识别分类；子频带能量；特征提取；神经网络
中图法分类号: TN912.34 文献标识码: A 文章编号: 1000-310X(2023)05-1106-09
DOI: 10.11684/j.issn.1000-310X.2023.05.025

Recognition of automobile whistle sound based on sub-frequency band energy

feature extraction

HOU Xiaofei 1 MU Ruilin 1,2 ZHOU Jin 3 JIA Zijie 1

(1 College of Mechanical Engineering, Tianjin University of Science & Technology, Tianjin 300222, China)
(2 Tianjin Key Laboratory of Integrated Design and Online Monitoring for Light Industry & Food Machinery and Equipment,
Tianjin University of Science & Technology, Tianjin 300222, China)
(3 Tianjin Real Estate Market Service Center, Tianjin 300222, China)

Abstract: In order to identify different kinds of illegal car whistling in cities quickly and accurately, the method
of sub-frequency band energy feature extraction was applied in the classification and recognition of whistles.
And the extracted sub-frequency band energy eigenvalue matrix was trained by BP neural network, and the
number of iterations of the neural network in the process of learning was reduced by used the method of variable
learning speed. The experiment shows that the average recognition rate of whistle and other sounds is 94.889%;
and the classification accuracy rate of different car whistle sound is 93.75%, the classification among different
whistles can realized by the method of sub-frequency band energy. The requirements of different whistle sound
identification and classification can be well satisfied by using the sub-frequency band energy method.
Keywords: Identification and classification of whistle; Sub-frequency band energy; Feature extraction; Neural
network

2022-07-20 收稿; 2022-09-20 定稿
天津市建委科技项目 (2017-10)
∗
作者简介: 侯晓飞 (1996– ), 男, 河北衡水人, 硕士研究生, 研究方向: 机械测试理论与技术。
通信作者 E-mail: mrl3667@tust.edu.cn
†