creator Patti, Anand advisor Williamson, Geoffrey A Many species of birds in Americas vocalize during nocturnal migration ights. Acoustic detection and classi cation of the calls show potential for study of the nat- ural history of these migrant birds. In particular, information about the species' composition and number of birds involved in migration movements may be obtain- able through acoustic techniques. Other methods such as radar monitoring may have capability only to assess the number, but not the composition. Mel Frequency Cep- stral Coe cients-Gaussian Mixture Model-based methods, Mel Frequency Cepstral Coe cients-Hidden Markov Model-based methods and spectrogram correlation-based methods have been proposed to automate the recognition/classi cation of the noctur- nal ight calls. Here we investigate the impact of choice of time-frequency representa- tions on Mel Frequency Cepstral Coe cients-Hidden Markov Model-based classi er and correlation based classi er performance. We use a collection of recordings of nocturnal ight calls of several species of thrushes and other bird species with similar calls to evaluate and compare classi ers. Submitted by Dana Lamparello (dlampare@iit.edu) on 2013-03-04T19:39:21Z No. of bitstreams: 1 MS_Thesis_Anand_Patti_A20246446_27July2012.pdf: 1701830 bytes, checksum: 4369b5411dd1a6cedc303e223e581c11 (MD5) Made available in DSpace on 2013-03-04T19:39:21Z (GMT). No. of bitstreams: 1 MS_Thesis_Anand_Patti_A20246446_27July2012.pdf: 1701830 bytes, checksum: 4369b5411dd1a6cedc303e223e581c11 (MD5) Previous issue date: 2012-07 M.S. in Electrical Engineering, July 2012e 2012-07-30 2012-07 http://hdl.handle.net/10560/2917 en Thesis born digital application/pdf In Copyright http://rightsstatements.org/page/InC/1.0/ Restricted Access ECE / Electrical and Computer Engineering Illinois Institute of Technology Affiliated department