Design considerations in an automatic classification system for bird vocalisations using the Two-dimensional Geometric Distance and cluster analysis

Michihiro Jinnai; Neil J. Boucher; Jeremy Robertson; Sonia Kleindorfer

Design considerations in an automatic classification system for bird vocalisations using the Two-dimensional Geometric Distance and cluster analysis

Michihiro Jinnai, Neil J. Boucher, Jeremy Robertson, Sonia Kleindorfer

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We have been developing an automatic classification system for bird vocalisations. Many biologists have been using the early one-dimensional version of our system and we have been working on a two-dimensional method. The software extracts a spectrogram from the bird vocalisation using the LPC spectrum analysis and classifies the images of spectrogram using a similarity scale and cluster analysis. We use the new similarity scale called the "Two-dimensional Geometric Distance" that has been developed by Jinnai and Boucher. In this paper, we introduce the principles of the Two-dimensional Geometric Distance, demonstrate the two-dimensional pattern matching software, and describe design considerations in a new automatic classification system for bird vocalisations. Testing has shown an order of magnitude improvement in accuracy over the one-dimensional method.

Original language	English
Title of host publication	Proceedings of 20th International Congress on Acoustics, ICA 2010
Pages	4102-4108
Number of pages	7
Publication status	Published - 1 Dec 2010
Event	20th International Congress on Acoustics 2010, ICA 2010 - Incorporating the 2010 Annual Conference of the Australian Acoustical Society - Sydney, NSW, Australia Duration: 23 Aug 2010 → 27 Aug 2010

Conference

Conference	20th International Congress on Acoustics 2010, ICA 2010 - Incorporating the 2010 Annual Conference of the Australian Acoustical Society
Country/Territory	Australia
City	Sydney, NSW
Period	23/08/10 → 27/08/10

Cite this

@inproceedings{26e4b30b3d824937a4bd58aba7fdd082,

title = "Design considerations in an automatic classification system for bird vocalisations using the Two-dimensional Geometric Distance and cluster analysis",

abstract = "We have been developing an automatic classification system for bird vocalisations. Many biologists have been using the early one-dimensional version of our system and we have been working on a two-dimensional method. The software extracts a spectrogram from the bird vocalisation using the LPC spectrum analysis and classifies the images of spectrogram using a similarity scale and cluster analysis. We use the new similarity scale called the {"}Two-dimensional Geometric Distance{"} that has been developed by Jinnai and Boucher. In this paper, we introduce the principles of the Two-dimensional Geometric Distance, demonstrate the two-dimensional pattern matching software, and describe design considerations in a new automatic classification system for bird vocalisations. Testing has shown an order of magnitude improvement in accuracy over the one-dimensional method.",

author = "Michihiro Jinnai and Boucher, {Neil J.} and Jeremy Robertson and Sonia Kleindorfer",

year = "2010",

month = dec,

day = "1",

language = "English",

isbn = "9781617827457",

pages = "4102--4108",

booktitle = "Proceedings of 20th International Congress on Acoustics, ICA 2010",

note = "20th International Congress on Acoustics 2010, ICA 2010 - Incorporating the 2010 Annual Conference of the Australian Acoustical Society ; Conference date: 23-08-2010 Through 27-08-2010",

}

Jinnai, M, Boucher, NJ, Robertson, J & Kleindorfer, S 2010, Design considerations in an automatic classification system for bird vocalisations using the Two-dimensional Geometric Distance and cluster analysis. in Proceedings of 20th International Congress on Acoustics, ICA 2010. pp. 4102-4108, 20th International Congress on Acoustics 2010, ICA 2010 - Incorporating the 2010 Annual Conference of the Australian Acoustical Society, Sydney, NSW, Australia, 23/08/10.

Design considerations in an automatic classification system for bird vocalisations using the Two-dimensional Geometric Distance and cluster analysis. / Jinnai, Michihiro; Boucher, Neil J.; Robertson, Jeremy et al.
Proceedings of 20th International Congress on Acoustics, ICA 2010. 2010. p. 4102-4108.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Design considerations in an automatic classification system for bird vocalisations using the Two-dimensional Geometric Distance and cluster analysis

AU - Jinnai, Michihiro

AU - Boucher, Neil J.

AU - Robertson, Jeremy

AU - Kleindorfer, Sonia

PY - 2010/12/1

Y1 - 2010/12/1

N2 - We have been developing an automatic classification system for bird vocalisations. Many biologists have been using the early one-dimensional version of our system and we have been working on a two-dimensional method. The software extracts a spectrogram from the bird vocalisation using the LPC spectrum analysis and classifies the images of spectrogram using a similarity scale and cluster analysis. We use the new similarity scale called the "Two-dimensional Geometric Distance" that has been developed by Jinnai and Boucher. In this paper, we introduce the principles of the Two-dimensional Geometric Distance, demonstrate the two-dimensional pattern matching software, and describe design considerations in a new automatic classification system for bird vocalisations. Testing has shown an order of magnitude improvement in accuracy over the one-dimensional method.

AB - We have been developing an automatic classification system for bird vocalisations. Many biologists have been using the early one-dimensional version of our system and we have been working on a two-dimensional method. The software extracts a spectrogram from the bird vocalisation using the LPC spectrum analysis and classifies the images of spectrogram using a similarity scale and cluster analysis. We use the new similarity scale called the "Two-dimensional Geometric Distance" that has been developed by Jinnai and Boucher. In this paper, we introduce the principles of the Two-dimensional Geometric Distance, demonstrate the two-dimensional pattern matching software, and describe design considerations in a new automatic classification system for bird vocalisations. Testing has shown an order of magnitude improvement in accuracy over the one-dimensional method.

UR - http://www.scopus.com/inward/record.url?scp=84869103327&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84869103327

SN - 9781617827457

SP - 4102

EP - 4108

BT - Proceedings of 20th International Congress on Acoustics, ICA 2010

T2 - 20th International Congress on Acoustics 2010, ICA 2010 - Incorporating the 2010 Annual Conference of the Australian Acoustical Society

Y2 - 23 August 2010 through 27 August 2010

ER -

Design considerations in an automatic classification system for bird vocalisations using the Two-dimensional Geometric Distance and cluster analysis

Abstract

Conference

Other files and links

Fingerprint

Cite this