基于基频的梅尔倒谱系数在车辆识别中的应用
DOI:
作者:
作者单位:

中国科学院上海微系统与信息技术研究所 微系统技术重点实验室

作者简介:

通讯作者:

中图分类号:

TN912.16

基金项目:

微系统技术重点实验室基金项目


The application of Mel-Frequency Cepstral Coefficients technology based on fundamental frequency in vehicle recognition
Author:
Affiliation:

Science and Technology on Microsystem Laboratory,Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences

Fund Project:

the Foundation of Science and Technology on Microsystem Laboratory

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    用传统的梅尔倒谱系数作为特征进行车辆识别时,识别效果易受噪声干扰。为了增强特征鲁棒性,本文提出一种加权的基频自适应梅尔倒谱系数特征提取算法。首先用能熵比法对车辆声音信号进行端点检测;然后提取车辆信号的基频,基于基频自适应地构建三角滤波器组,从而提高滤波器对基频的感知敏感度;最后对基频自适应梅尔倒谱系数进行F比加权。实验结果表明,与传统的梅尔倒谱系数相比,在识别车辆时,加权的基频自适应梅尔倒谱系数识别准确率提高7.10%,虚警率降低3.93%,漏警率降低7.10%。

    Abstract:

    The Mel-Frequency Cepstral Coefficients are susceptible to noise in field vehicle recognition. To enhance the robustness of features, this paper proposed a weighted and adaptive feature extraction algorithm, which was based on the MFCC method. Firstly, the energy to entropy ratio method was used to detect the endpoint of field vehicle's acoustic signal. Secondly, we extracted the fundamental frequency of vehicle's acoustic signal. The triangular filter bank was adaptively constructed according to the fundamental frequency, so that filter’s sensitivity to the fundamental frequency can be improved. Finally, weighted the obtained frequency with fisher’s ratio. Compared with the traditional MFCCs, the experimental results show that the improved MFCCs improve the recognition accuracy by 7.10%, reduce the false alarm rate by 3.93% and reduce the leakage alarm rate by 7.10% in field vehicle recognition.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2019-11-01
  • 最后修改日期:2020-01-02
  • 录用日期:2020-01-03
  • 在线发布日期:
  • 出版日期: