Advanced

Robust feature representation for classification of bird song syllables

Sandsten, Maria LU ; Große Ruse, Mareile LU and Jönsson, Martin (2016) In Eurasip Journal on Advances in Signal Processing 2016(1).
Abstract

A novel feature set for low-dimensional signal representation, designed for classification or clustering of non-stationary signals with complex variation in time and frequency, is presented. The feature representation of a signal is given by the first left and right singular vectors of its ambiguity spectrum matrix. If the ambiguity matrix is of low rank, most signal information in time direction is captured by the first right singular vector while the signal’s key frequency information is encoded by the first left singular vector. The resemblance of two signals is investigated by means of a suitable similarity assessment of the signals’ respective singular vector pair. Application of multitapers for the calculation of the ambiguity... (More)

A novel feature set for low-dimensional signal representation, designed for classification or clustering of non-stationary signals with complex variation in time and frequency, is presented. The feature representation of a signal is given by the first left and right singular vectors of its ambiguity spectrum matrix. If the ambiguity matrix is of low rank, most signal information in time direction is captured by the first right singular vector while the signal’s key frequency information is encoded by the first left singular vector. The resemblance of two signals is investigated by means of a suitable similarity assessment of the signals’ respective singular vector pair. Application of multitapers for the calculation of the ambiguity spectrum gives an increased robustness to jitter and background noise and a consequent improvement in performance, as compared to estimation based on the ordinary single Hanning window spectrogram. The suggested feature-based signal compression is applied to a syllable-based analysis of a song from the bird species Great Reed Warbler and evaluated by comparison to manual auditive and/or visual signal classification. The results show that the proposed approach outperforms well-known approaches based on mel-frequency cepstral coefficients and spectrogram cross-correlation.

(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Ambiguity spectrum, Bird song, Multitaper, Singular value decomposition, Time-frequency analysis
in
Eurasip Journal on Advances in Signal Processing
volume
2016
issue
1
publisher
Hindawi Publishing Corporation
external identifiers
  • Scopus:84974711990
ISSN
1687-6172
DOI
10.1186/s13634-016-0365-8
language
English
LU publication?
yes
id
dd5cc599-bf26-4280-8c6d-87384e788ae5
date added to LUP
2016-10-12 12:21:35
date last changed
2016-11-14 12:48:24
@misc{dd5cc599-bf26-4280-8c6d-87384e788ae5,
  abstract     = {<p>A novel feature set for low-dimensional signal representation, designed for classification or clustering of non-stationary signals with complex variation in time and frequency, is presented. The feature representation of a signal is given by the first left and right singular vectors of its ambiguity spectrum matrix. If the ambiguity matrix is of low rank, most signal information in time direction is captured by the first right singular vector while the signal’s key frequency information is encoded by the first left singular vector. The resemblance of two signals is investigated by means of a suitable similarity assessment of the signals’ respective singular vector pair. Application of multitapers for the calculation of the ambiguity spectrum gives an increased robustness to jitter and background noise and a consequent improvement in performance, as compared to estimation based on the ordinary single Hanning window spectrogram. The suggested feature-based signal compression is applied to a syllable-based analysis of a song from the bird species Great Reed Warbler and evaluated by comparison to manual auditive and/or visual signal classification. The results show that the proposed approach outperforms well-known approaches based on mel-frequency cepstral coefficients and spectrogram cross-correlation.</p>},
  author       = {Sandsten, Maria and Große Ruse, Mareile and Jönsson, Martin},
  issn         = {1687-6172},
  keyword      = {Ambiguity spectrum,Bird song,Multitaper,Singular value decomposition,Time-frequency analysis},
  language     = {eng},
  month        = {12},
  number       = {1},
  publisher    = {ARRAY(0x9803290)},
  series       = {Eurasip Journal on Advances in Signal Processing},
  title        = {Robust feature representation for classification of bird song syllables},
  url          = {http://dx.doi.org/10.1186/s13634-016-0365-8},
  volume       = {2016},
  year         = {2016},
}