Bird Sound Recognition Based on MFCC-IMFCC and GA-SVM
CSTR:
Author:
  • Article
  • | |
  • Metrics
  • |
  • Reference [44]
  • |
  • Related [20]
  • |
  • Cited by
  • | |
  • Comments
    Abstract:

    In the research of bird sound recognition, the selection of sound features has a great impact on the accuracy of recognition and classification. To improve the accuracy of bird sound recognition, this study starts with the problem that the traditional Mel frequency cepstral coefficient (MFCC) characterizes the high-frequency information in bird sound insufficiently. Feature fusion of MFCC based on Fisher criterion and inverted MFCC (IMFCC) is proposed to obtain a new feature parameter MFCC-IMFCC that can be applied to bird sound recognition to improve the characterization of the high-frequency information in bird sound. Meanwhile, the penalty factor C and the kernel parameter g in the support vector machine (SVM) are optimized by a genetic algorithm (GA), and a GA-SVM classification model is trained. Experiments show that under the same conditions, the recognition rate of the MFCC-IMFCC approach is higher than that of the MFCC one.

    Reference
    [1] Gregory RD, Noble D, Field R, et al. Using birds as indicators of biodiversity. Ornis Hungarica, 2003, 12–13: 11–24.
    [2] 斯幸峰, 丁平. 欧美陆地鸟类监测的历史、现状与我国的对策. 生物多样性, 2011, 19(3): 303–310
    [3] 赵苏徽, 陈晓. 基于树莓派和云平台的智能灌溉系统. 计算机系统应用, 2022, 31(4): 123–129. [doi: 10.15888/j.cnki.csa.008456
    [4] 陈晓, 张凯. 嵌入式自动气象站故障检测系统研究. 电子测量技术, 2021, 44(23): 158–164
    [5] 荣百川, 陈晓. 基于蓝牙的智能防摔监测系统设计. 激光杂志, 2019, 40(7): 32–34
    [6] 邢玉品, 陈晓. 基于TDC-GP22的超声波测风仪设计. 现代电子技术, 2018, 41(21): 128–131, 136
    [7] 杨应鹏, 陈晓. 基于蓝牙的可穿戴式脉搏波形采集系统设计. 激光杂志, 2018, 39(6): 74–77
    [8] 陈晓. 基于无线通信的激光超声测量系统. 光学学报, 2009, 29(1): 203–207
    [9] 陈晓. 基于无线通信的脉搏信号采集系统. 通信技术, 2008, 41(12): 268–270, 273. [doi: 10.3969/j.issn.1002-0802.2008.12.093
    [10] 陈晓. 基于通用串行总线的高速脉搏信号检测系统. 中国组织工程研究与临床康复, 2008, 12(39): 7653–7656
    [11] 陈晓. 基于压电传感器和个人计算机构成的脉搏信号实时监测系统. 中国组织工程研究与临床康复, 2008, 12(35): 6847–6850
    [12] 陈晓. 便携式电子脉搏计的设计. 中国组织工程研究与临床康复, 2008, 12(17): 3349–3352
    [13] 王家盛, 郭其威, 吴松, 等. 基于特征相对贡献度对加权Mel倒谱的改进. 声学技术, 2021, 40(3): 408–414
    [14] 杨瑶, 陈晓. 基于神经网络的说话人识别实验设计. 实验室研究与探索, 2020, 39(9): 38–41, 50. [doi: 10.3969/j.issn.1006-7167.2020.09.008
    [15] Li Q, Yang YZ, Lan TX, et al. MSP-MFCC: Energy-efficient MFCC feature extraction method with mixed-signal processing architecture for wearable speech recognition applications. IEEE Access, 2020, 8: 48720–48730. [doi: 10.1109/ACCESS.2020.2979799
    [16] 程龙, 张华清. 基于改进MFCC的鸟鸣声识别方法研究. 中国传媒大学学报: 自然科学版, 2017, 24(3): 41–46
    [17] 徐淑正, 孙忆南, 皇甫丽英, 等. 基于MFCC和时频图等多种特征的综合鸟声识别分类器设计. 实验室研究与探索, 2018, 37(9): 81–86, 91. [doi: 10.3969/j.issn.1006-7167.2018.09.020
    [18] 张赛花, 赵兆, 许志勇, 等. 基于Mel子带参数化特征的自动鸟鸣识别. 计算机应用, 2017, 37(4): 1111–1115. [doi: 10.11772/j.issn.1001-9081.2017.04.1111
    [19] 陈莎莎, 李应. 结合时-频纹理特征的随机森林分类器应用于鸟声识别. 计算机应用与软件, 2014, 31(1): 154–157, 161. [doi: 10.3969/j.issn.1000-386x.2014.01.040
    [20] 王萌, 王福龙. 基于端点检测和高斯滤波器组的MFCC说话人识别. 计算机系统应用, 2016, 25(10): 218–224. [doi: 10.15888/j.cnki.csa.005425
    [21] 朱春媚, 黎萍. 基于子带能量变换改进MFCC的咳嗽识别. 计算机工程与应用, 2016, 52(11): 148–151, 157. [doi: 10.3778/j.issn.1002-8331.1511-0062
    [22] Chen GH, Zeng XP. Multi-modal emotion recognition by fusing correlation features of speech-visual. IEEE Signal Processing Letters, 2021, 28: 533–537. [doi: 10.1109/LSP.2021.3055755
    [23] Shi YY, Bai J, Xue PY, et al. Fusion feature extraction based on auditory and energy for noise-robust speech recognition. IEEE Access, 2019, 7: 81911–81922. [doi: 10.1109/ACCESS.2019.2918147
    [24] Ferras M, Leung CC, Barras C, et al. Comparison of speaker adaptation methods as feature extraction for SVM-based speaker recognition. IEEE Transactions on Audio, Speech, and Language Processing, 2010, 18(6): 1366–1378. [doi: 10.1109/TASL.2009.2034187
    [25] 王恩泽, 何东健. 基于MFCC和双重GMM的鸟类识别方法. 计算机工程与设计, 2014, 35(5): 1868–1871. [doi: 10.3969/j.issn.1000-7024.2014.05.071
    [26] 陈晓, 杨瑶. 基于长期递归卷积网络的无创血压测量. 电子测量技术, 2022, 45(4): 139–146
    [27] 孙超文, 陈晓. 基于多尺度特征融合反投影网络的图像超分辨率重建. 自动化学报, 2021, 47(7): 1689–1700
    [28] 陈晓, 倪龙. 用分数阶微分实现时频重叠多模式兰姆波的模式分离. 声学学报, 2020, 45(2): 205–214
    [29] 任晓晔, 陈晓, 郭妍. 基于Fluent和LSTM神经网络的超声波测风仪阴影效应补偿研究. 计算机应用与软件, 2019, 36(7): 89–98. [doi: 10.3969/j.issn.1000-386x.2019.07.016
    [30] 朱娟, 陈晓. 改进胶囊网络的有序重叠手写数字识别方法. 激光杂志, 2019, 40(7): 43–46
    [31] 任晓晔, 陈晓, 郭妍. 超声波测风换能器对风速的影响研究. 电子测量技术, 2019, 42(7): 118–124
    [32] 郭妍, 陈晓, 任晓晔. 一种优化随机森林模型的室内定位方法. 激光杂志, 2018, 39(10): 70–74
    [33] 倪龙, 陈晓. 基于频散补偿和分数阶微分的多模式兰姆波分离. 物理学报, 2018, 67(20): 204301.34.
    [34] 徐畅, 陈晓, 季仟亿. 基于稀疏编码的Shearlet域图像去噪. 激光杂志, 2017, 38(10): 96–100.
    [35] 邹胜男, 陈晓, 陈霞. 基于改进的UKF算法的室内测距定位. 激光杂志, 2017, 38(4): 61–65
    [36] 陈霞, 陈晓, 邹胜男. 基于正态检验的室内定位算法. 激光杂志, 2017, 38(3): 41–45
    [37] 胡春杰, 陈晓, 陈霞. 基于改进广义Arnold映射的多混沌图像加密算法. 包装工程, 2017, 38(3): 144–149
    [38] 胡春杰, 陈晓, 郭银. 基于多混沌映射的光学图像加密算法. 激光杂志, 2017, 38(1): 110–114
    [39] 沈千里, 陈晓, 支亚京, 等. 一种新的人脸图像去噪算法. 传感器与微系统, 2015, 34(11): 133–136
    [40] 陈晓, 汪陈龙. 基于赛利斯模型和分数阶微分的兰姆波信号消噪. 物理学报, 2014, 63(18): 184301
    [41] 支亚京, 陈晓, 蔡婷婷. 单通道时频重叠高斯调幅通信信号盲分离方法. 科学技术与工程, 2016, 16(1): 204–208
    [42] 陈晓, 徐晓庆. 卫星图像码率控制方法的改进. 光电工程, 2012, 39(9): 7–11
    [43] 卢明乔, 陈晓. 基于ZigBee组网的智能照明系统的研究与设计. 信息技术, 2013, (12): 106–109. [doi: 10.3969/j.issn.1009-2552.2013.12.028
    [44] 吴祖慷, 朱晓冬, 刘元宁, 等. 基于GA-SVM模型的虹膜质量评估方法. 吉林大学学报(理学版), 2022, 60(1): 89–98
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

韩鹏飞,陈晓.基于MFCC-IMFCC和GA-SVM的鸟声识别.计算机系统应用,2022,31(11):393-399

Copy
Share
Article Metrics
  • Abstract:870
  • PDF: 1769
  • HTML: 1757
  • Cited by: 0
History
  • Received:February 22,2022
  • Revised:March 23,2022
  • Online: July 14,2022
Article QR Code
You are the first990577Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-3
Address:4# South Fourth Street, Zhongguancun,Haidian, Beijing,Postal Code:100190
Phone:010-62661041 Fax: Email:csa (a) iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063