Skip to Main content Skip to Navigation
Reports

Detection of Mysticete Calls: a Sparse Representation-Based Approach

François-Xavier Socheleau 1, 2 Flore Samaran 3
1 Lab-STICC_IMTA_CACS_COM
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
3 Lab-STICC_ENSTAB_CID_TOMS
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
Abstract : This paper presents a methodology for automatically detecting mysticete calls. This methodology relies on sparse representations of these calls combined with a detection metric that explicitly takes into account the possible presence of interfering transient signals. Sparse representations can capture the possible variability observed for some vocalizations and can automatically be learned from the time series of the digitized acoustic signals, without requiring prior transforms such as spectrograms, wavelets or cepstrums. The proposed framework is general and applicable to any mysticete call lying in a linear subspace described by a dictionary-based representation. The potential of the detector is illustrated on North Pacific blue whale D calls extracted from the DCLDE 2015 low frequency database as well as on ``Madagascar'' pygmy blue whale calls extracted from the OHASISBIO 2015 database. Receiver operating characteristic curves (ROC) are calculated and performance is compared with three other methods used for automatic call detection: the XBAT bank of matched spectrograms, a bank of matched filters derived from a generalized likelihood ratio approach and a kernel-based spectrogram detector. On the test data, the ROC curves show that the proposed detector outperforms these three methods.
Document type :
Reports
Complete list of metadatas

Cited literature [55 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01736178
Contributor : François-Xavier Socheleau <>
Submitted on : Thursday, October 11, 2018 - 3:03:49 PM
Last modification on : Wednesday, October 14, 2020 - 4:20:56 AM

File

RAPPORT_SRD_2017_V1.1 (1).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01736178, version 2

Citation

François-Xavier Socheleau, Flore Samaran. Detection of Mysticete Calls: a Sparse Representation-Based Approach. [Research Report] RR-2017-04-SC, Dépt. Signal et Communications (Institut Mines-Télécom-IMT Atlantique-UBL); Laboratoire en sciences et technologies de l'information, de la communication et de la connaissance (UMR 6285 - CNRS - IMT Atlantique - Université de Bretagne Occidentale - Université de Bretagne Sud - ENSTA Bretagne - Ecole Nationale d'ingénieurs de Brest); École nationale supérieure de techniques avancées Bretagne. (Ministère de la Défense). 2017. ⟨hal-01736178v2⟩

Share

Metrics

Record views

314

Files downloads

468