Skip to main content
placeholder image

Detection of ground parrot vocalisation: A multiple instance learning approach

Journal Article


Abstract


  • Ground parrot vocalisation can be considered as an audio event. Test-based diverse density multiple instance learning (TB-DD-MIL) is proposed for detecting this event in audio files recorded in the field. The proposed method is motivated by the advantages of multiple instance learning from incomplete training data. Spectral features suitable for encoding the vocal source information of the ground parrot vocalization are also investigated. The proposed method was benchmarked against a dataset collected in various environmental conditions and an audio detection evaluation scheme is proposed. The evaluation includes a study on performance of the various vocal source features and comparison with other classification techniques. Experimental results indicated that the most appropriate feature to encode ground parrot calls is the spectral bandwidth and the proposed TB-DD-MIL method outperformed other existing classification methods.

Authors


  •   Nguyen, Duc Thanh (external author)
  •   Ogunbona, Philip O.
  •   Li, Wanqing
  •   Tasker, Liz M. (external author)
  •   Yearwood, John (external author)

Publication Date


  • 2017

Citation


  • Nguyen, D., Ogunbona, P., Li, W., Tasker, E. & Yearwood, J. (2017). Detection of ground parrot vocalisation: A multiple instance learning approach. Journal of the Acoustical Society of America, 142 (3), 1281-1290.

Scopus Eid


  • 2-s2.0-85029148387

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/706

Number Of Pages


  • 9

Start Page


  • 1281

End Page


  • 1290

Volume


  • 142

Issue


  • 3

Place Of Publication


  • United States

Abstract


  • Ground parrot vocalisation can be considered as an audio event. Test-based diverse density multiple instance learning (TB-DD-MIL) is proposed for detecting this event in audio files recorded in the field. The proposed method is motivated by the advantages of multiple instance learning from incomplete training data. Spectral features suitable for encoding the vocal source information of the ground parrot vocalization are also investigated. The proposed method was benchmarked against a dataset collected in various environmental conditions and an audio detection evaluation scheme is proposed. The evaluation includes a study on performance of the various vocal source features and comparison with other classification techniques. Experimental results indicated that the most appropriate feature to encode ground parrot calls is the spectral bandwidth and the proposed TB-DD-MIL method outperformed other existing classification methods.

Authors


  •   Nguyen, Duc Thanh (external author)
  •   Ogunbona, Philip O.
  •   Li, Wanqing
  •   Tasker, Liz M. (external author)
  •   Yearwood, John (external author)

Publication Date


  • 2017

Citation


  • Nguyen, D., Ogunbona, P., Li, W., Tasker, E. & Yearwood, J. (2017). Detection of ground parrot vocalisation: A multiple instance learning approach. Journal of the Acoustical Society of America, 142 (3), 1281-1290.

Scopus Eid


  • 2-s2.0-85029148387

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/706

Number Of Pages


  • 9

Start Page


  • 1281

End Page


  • 1290

Volume


  • 142

Issue


  • 3

Place Of Publication


  • United States