南京大学学报(自然科学版) ›› 2015, Vol. 51 ›› Issue (6): 12341239.
陈海兰1*,孙海信2,齐洁2,高春仙2,颜佳泉2
Chen Hailan1*, Sun Haixin2, Qi Jie2, Gao Cunxian2, Yuan Jiaquan2
摘要: 湿地不但具有丰富的资源,还有巨大的环境调节功能和生态效益.随着人类社会的发展,湿地生态保护日益受到人们的重视,其中鸟类监测经常作为湿地环境质量的有效指标.目前国内外对于鸟类监测技术主要通过大量人力统计手段,严重浪费宝贵的人力资源.基于此种状况,且传统的语音识别方法主要采用基于时域特征或频域特征的识别方法,根据不同种鸟类鸣声的特点,提出一种将不同音节长度特征与多段式平均频谱法相结合的多维特征联合的鸟类鸣声识别方法.实验结果发现,将时域音节长度特征分类与频域多段式平均频谱法相结合的识别方法比只采用多段式平均频谱法的识别方法将辨识正确率由92.38%提高到100%,实验采用了湿地常见的17种鸟类,辨识效果非常准确,表明本文所提出的多特征结合识别方法对于提高识别正确率具有重要的参考价值.
[1] 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. [2] 石贵民. 武夷山九曲溪湿地鸟类联网监测及识别系统. 湖南大学工业学报, 2013(02):84-88. [3] Riede, K. Monitoring biodiversity. Analysis of Amazonian rainforest sounds. Ambio,1993, 22:546-548. [4] A. Taylor, G. Grigg, G. Watson and H. McCallum. Monitoring Frog Communities: An Application of Machine Learning. Proceeding of Eighth Innovative Applications of Artificial Intelligence Conference. 1996:1564-1569. [5] C.J. Huang, Y.J. Yangb, D.X. Yang, and Y.J. Chen. Frog classification using machine learning techniques. Expert Systems with Applications, 2000, 36:3737-3743. [6] C.H. Lee, C.H. Chou, C.C. Han and R.Z. Hunag. Automatic recognition of animal vocalizations using average MFCC and linear discriminant analysis. Pattern Recognition Letters, Jan, 2006, 27(2):93-106. [7] R.Koening, H.K.Dunn and L.Y.Lacey. The Sound Spectrograph. Journal of Acoustic Society America,1947, 18:19-49. [8] K.H. David. Automatic Recognition of spoken Digits, Journal of Acoustic Society America, 1952(24):437-465. [9] C.L.Li and K.C.Hui, “Feature recognition by template matching”. Computers & Graphics, 24(4), Aug. 2000:569-582. [10] T.K. Vintsyuk. Speech Discrimination by Dynamic Programming. Kibemetika, Jan.-Feb,1968,4(2):81-88. [11] T. Komori and S. Katagiri, S. Application of a generalized probabilistic descent method to dynamic time warping-based speech recognition. IEEE International Conference on Acoustics, Speech, and Signal Processing,1992:497-500. [12] P. Somervuo, A. Harma, and S. Fagerlund. Parametric Representations of Birds Sounds for Automatic Species Recognition. IEEE Transactions on Audio, Speech, and Language Processing, 2006, 14(6):2252-2263. [13] Cheng J, Sun Y, Ji L. A call-independent and automatic acoustic system for the individual recognition of animals. A novel model using four passerines. Psttern Recognition, 2010, 43(11):3846-3852. [14] 薛宇志. 依照鸟类鸣叫与鸣唱声识别其种类. 台湾:国立台北科技大学, 1998. [15] Sheng-BinHsu, Jau-LingShih, Chih-Hsun Chou. Continous Birdsong Recognition Using Gaussian Mixture Modeling of Image Shape Fetures. 2013,15(2):454-464. [16] S.B. Davis and P. Mermelstein. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustic, Speech, and Signal Processing, 1980, 28(4), 357-366. [17] 王恩泽. 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. [18] 林清贤,陈小麟,林鹏. 厦门东屿红树林湿地鸟类资源及其分布. 厦门大学学报(自然科学版), 2005,44:37-40. |
No related articles found! |
|