{"data":[{"source":"bio.acousti.ca","id":"47889","type":"article","title":"Automatic recognition of animal vocalizations using averaged MFCC and linear discriminant analysis","author":"Lee, Chang-Hsing; Chou, Chih-Hsun; Han, Chin-Chuan; Huang, Ren-Zhuang","editor":null,"year":"2006","month":null,"journal":"Pattern Recognition Letters","booktitle":null,"series":null,"howpublished":null,"volume":"27","number":"2","pages":"93 - 101","chapter":null,"edition":null,"publisher":null,"organization":null,"institution":null,"school":null,"address":null,"type_of_work":null,"note":null,"isbn":null,"issn":"01678655","doi":"10.1016\/j.patrec.2005.07.004","url":"http:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167865505001959","attachments":"https:\/\/bio.acousti.ca\/sites\/default\/files\/1-s2.0-S0167865505001959-main.pdf","keywords":"linear discriminant analysis; Mel-frequency cepstral coefficients","abstract":"In this paper we propose a method that uses the averaged Mel-frequency cepstral coefficients (MFCCs) and linear discriminant anal- ysis (LDA) to automatically identify animals from their sounds. First, each syllable corresponding to a piece of vocalization is segmented. The averaged MFCCs over all frames in a syllable are calculated as the vocalization features. Linear discriminant analysis (LDA), which finds out a transformation matrix that minimizes the within-class distance and maximizes the between-class distance, is utilized to increase the classification accuracy while to reduce the dimensionality of the feature vectors. In our experiment, the average classification accuracy is 96.8% and 98.1% for 30 kinds of frog calls and 19 kinds of cricket calls, respectively.","type_name":"Journal Article","journal_abbreviation":"Pattern Recognition Letters","pmid":null,"info_url":"https:\/\/bio.acousti.ca\/node\/47889"}]}