+高级检索
首页 > 过刊浏览>2021年第44卷第11期 >17-23. DOI:10.11835/j.issn.1000-582X.2021.11.003
PDF HTML阅读 XML下载 导出引用 引用提醒
基于基频的梅尔倒谱系数在车辆识别中的应用
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（614280401020617）。


The application of Mel-Frequency Cepstral Coefficients technology based on fundamental frequency in vehicle recognition
Author:
  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [20]
    • |
  • 相似文献 [20]
    • | | |
  • 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。为增强特征鲁棒性，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，自适应构建三角滤波器组，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(MFCC) are susceptible to noise in field vehicle recognition. To enhance the robustness of features, this paper proposed a weighted and adaptive feature extraction algorithm based on the MFCC method. Firstly, the energy to entropy ratio method was used to detect the endpoint of field vehicle's acoustic signal. Then, the fundamental frequency of vehicle's acoustic signal was extracted. The triangular filter bank was adaptively constructed according to the fundamental frequency so as to improve the filter’s sensitivity to the fundamental frequency. Finally, the obtained frequency was weighted 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
    [1] Shaikh F K, Zeadally S. Energy harvesting in wireless sensor networks: a comprehensive review[J]. Renewable and Sustainable Energy Reviews, 2016, 55: 1041-1054.
    [2] Kurt S, Yildiz H U, Yigit M, et al. Packet size optimization in wireless sensor networks for smart grid applications[J]. IEEE Transactions on Industrial Electronics, 2017, 64(3): 2392-2401.
    [3] Pandey M, Mishra G. Types of sensor and their applications, advantages, and disadvantages[C]//Emerging Technologies in Data Mining and Information Security, India: Springer, 2019: 791-804. DOI:10.1007/978-981-13-1501-5_69.
    [4] Witkowski M, Kacprzak S, Zelasko P, et al. Audio replay attack detection using high-frequency features[C]//Interspeech 2017. ISCA: Swedon, 2017: 27-31.
    [5] Juvela L, Bollepalli B, Wang X, et al. Speech waveform synthesis from MFCC sequences with generative adversarial networks[C]//2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). April 15-20, 2018, Calgary, AB, Canada: IEEE, 2018: 5679-5683.
    [6] Sharma R, Vignolo L, Schlotthauer G, et al. Empirical mode decomposition for adaptive AM-FM analysis of speech: a review[J]. Speech Communication, 2017, 88: 39-64.
    [7] Sharma R, Mahadeva Prasanna S R. A better decomposition of speech obtained using modified empirical mode decomposition[J]. Digital Signal Processing, 2016, 58: 26-39.
    [8] Huang J C, Zhang X, Guo F, et al. Design of an acoustic target classification system based on small-aperture microphone array[J]. IEEE Transactions on Instrumentation and Measurement, 2015, 64(7): 2035-2043.
    [9] Guo F, Huang J C, Zhang X, et al. A classification method for moving targets in the wild based on microphone array and linear sparse auto-encoder[J]. Neurocomputing, 2017, 241: 28-37.
    [10] Zhao Q, Guo F, Zu X S, et al. An acoustic-based feature extraction method for the classification of moving vehicles in the wild[J]. IEEE Access, 2019, 7: 73666-73674.
    [11] Al-Ali A K H, Dean D, Senadji B, et al. Enhanced forensic speaker verification using a combination of DWT and MFCC feature warping in the presence of noise and reverberation conditions[J]. IEEE Access, 2017, 5: 15400-15413.
    [12] Shahnawazuddin S, Deepak K T, Pradhan G, et al. Enhancing noise and pitch robustness of children’s ASR[C]//2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). March 5-9, 2017, New Orleans, LA, USA: IEEE, 2017: 5225-5229.
    [13] Bhattacharjee U, Gogoi S, Sharma R. A statistical analysis on the impact of noise on MFCC features for speech recognition[C]//2016 International Conference on Recent Advances and Innovations in Engineering (ICRAIE). December 23-25, 2016, Jaipur, India: IEEE, 2016: 1-5.
    [14] Palo H K, Chandra M, Mohanty M N. Recognition of human speech emotion using variants of mel-frequency cepstral coefficients advances in systems[J]. Control and Automation, 2018: 491-498. DOI:10.1007/978-981-10-4762-6_47.
    [15] Ludeña-Choez J, Gallardo-Antolín A. Feature extraction based on the high-pass filtering of audio signals for acoustic event classification[J]. Computer Speech & Language, 2015, 30(1): 32-42.
    [16] Kim J W, Salamon J, Li P, et al. Crepe: a convolutional representation for pitch estimation[C]//2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). April 15-20, 2018, Calgary, AB, Canada: IEEE, 2018: 161-165.
    [17] Jouvet D, Laprie Y. Performance analysis of several pitch detection algorithms on simulated and real noisy speech data[C]//2017 25th European Signal Processing Conference (EUSIPCO). August 28-September 2, 2017, Kos, Greece: IEEE, 2017: 1614-1618.
    [18] Huang J C, Guo F, Zu X S, et al. A novel multipitch measurement algorithm for acoustic signals of moving targets[J]. Mechanical Systems and Signal Processing, 2016, 81: 419-432.
    [19] Hegde S, K A K, Shetty S. Feature selection using fisher’s ratio technique for automatic speech recognition[J]. International Journal on Cybernetics & Informatics, 2015, 4(2): 45-52.
    [20] Chettri B, Sturm B L. A deeper look at Gaussian mixture model based anti-spoofing systems[C]//2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). April 15-20, 2018, Calgary, AB, Canada: IEEE, 2018: 5159-5163.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

李成娟,易强,李宝清,王国辉.基于基频的梅尔倒谱系数在车辆识别中的应用[J].重庆大学学报,2021,44(11):17-23.

复制
分享
文章指标
  • 点击次数:723
  • 下载次数: 862
  • HTML阅读次数: 674
  • 引用次数: 0
历史
  • 收稿日期:2020-10-21
  • 在线发布日期: 2021-12-02
文章二维码
您是第10941060 位访问者
主管单位：中华人民共和国教育部
主办单位：重庆大学
地址：重庆市沙坪坝正街174号
电话：
重庆大学学报 ® 2025 版权所有