Acoustic classification of multiple simultaneous bird species: A multi-instance multi-label approach

被引:219
作者
Briggs, Forrest [1 ]
Lakshminarayanan, Balaji [1 ]
Neal, Lawrence [1 ]
Fern, Xiaoli Z. [1 ]
Raich, Raviv [1 ]
Hadley, Sarah J. K. [2 ]
Hadley, Adam S. [2 ]
Betts, Matthew G. [2 ]
机构
[1] Oregon State Univ, Dept Elect Engn & Comp Sci, Corvallis, OR 97331 USA
[2] Oregon State Univ, Dept Forest Ecosyst & Soc, Corvallis, OR 97331 USA
基金
美国国家科学基金会;
关键词
HIDDEN MARKOV-MODELS; PARAMETRIC REPRESENTATIONS; RECOGNITION; SIGNALS; RATES; SONG;
D O I
10.1121/1.4707424
中图分类号
O42 [声学];
学科分类号
070206 [声学];
摘要
Although field-collected recordings typically contain multiple simultaneously vocalizing birds of different species, acoustic species classification in this setting has received little study so far. This work formulates the problem of classifying the set of species present in an audio recording using the multi-instance multi-label (MIML) framework for machine learning, and proposes a MIML bag generator for audio, i.e., an algorithm which transforms an input audio signal into a bag-of-instances representation suitable for use with MIML classifiers. The proposed representation uses a 2D time-frequency segmentation of the audio signal, which can separate bird sounds that overlap in time. Experiments using audio data containing 13 species collected with unattended omnidirectional microphones in the H.J. Andrews Experimental Forest demonstrate that the proposed methods achieve high accuracy (96.1% true positives/negatives). Automated detection of bird species occurrence using MIML has many potential applications, particularly in long-term monitoring of remote sites, species distribution modeling, and conservation planning. (C) 2012 Acoustical Society of America. [http://dx.doi.org/10.1121/1.4707424]
引用
收藏
页码:4640 / 4650
页数:11
相关论文
共 58 条
[1]
Template-based automatic recognition of birdsong syllables from continuous recordings [J].
Anderson, SE ;
Dave, AS ;
Margoliash, D .
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1996, 100 (02) :1209-1219
[2]
[Anonymous], 2011, P IEEE INT C AC SPEE
[3]
[Anonymous], P IEEE INT C AC SPEE
[4]
[Anonymous], HERMIT WARBLER SETOP
[5]
[Anonymous], P INT S MUS INF RETR
[6]
[Anonymous], ARXIV08083231
[7]
[Anonymous], P IEEE INT C SYST MA
[8]
[Anonymous], 2011, EURASIP J ADV SIGNAL
[9]
[Anonymous], J ADV SIGNAL PROCESS
[10]
[Anonymous], ADV NEURAL INF PROCE