Detection of Mysticete Calls: a Sparse Representation-Based Approach
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 captu...
Main Authors: | , |
---|---|
Other Authors: | , , , , , , , , , , , |
Format: | Report |
Language: | English |
Published: |
HAL CCSD
2017
|
Subjects: | |
Online Access: | https://hal.science/hal-01736178 https://hal.science/hal-01736178v2/document https://hal.science/hal-01736178v2/file/RAPPORT_SRD_2017_V1.1%20%281%29.pdf |
id |
ftenstabretagne:oai:HAL:hal-01736178v2 |
---|---|
record_format |
openpolar |
institution |
Open Polar |
collection |
ENSTA Bretagne: HAL (Ecole Nationale Supérieure de Techniques Avancées Bretagne) |
op_collection_id |
ftenstabretagne |
language |
English |
topic |
[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing |
spellingShingle |
[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing Socheleau, François-Xavier Samaran, Flore Detection of Mysticete Calls: a Sparse Representation-Based Approach |
topic_facet |
[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing |
description |
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. |
author2 |
Lab-STICC_IMTA_CACS_COM Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC) École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom Paris (IMT)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL)-IMT Atlantique (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom Paris (IMT)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL)-IMT Atlantique (IMT Atlantique) Institut Mines-Télécom Paris (IMT) Département Signal et Communications (IMT Atlantique - SC) IMT Atlantique (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT) Lab-STICC_ENSTAB_CID_TOMS 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) |
format |
Report |
author |
Socheleau, François-Xavier Samaran, Flore |
author_facet |
Socheleau, François-Xavier Samaran, Flore |
author_sort |
Socheleau, François-Xavier |
title |
Detection of Mysticete Calls: a Sparse Representation-Based Approach |
title_short |
Detection of Mysticete Calls: a Sparse Representation-Based Approach |
title_full |
Detection of Mysticete Calls: a Sparse Representation-Based Approach |
title_fullStr |
Detection of Mysticete Calls: a Sparse Representation-Based Approach |
title_full_unstemmed |
Detection of Mysticete Calls: a Sparse Representation-Based Approach |
title_sort |
detection of mysticete calls: a sparse representation-based approach |
publisher |
HAL CCSD |
publishDate |
2017 |
url |
https://hal.science/hal-01736178 https://hal.science/hal-01736178v2/document https://hal.science/hal-01736178v2/file/RAPPORT_SRD_2017_V1.1%20%281%29.pdf |
geographic |
Pacific |
geographic_facet |
Pacific |
genre |
Blue whale |
genre_facet |
Blue whale |
op_source |
https://hal.science/hal-01736178 [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 |
op_relation |
Report N°: RR-2017-04-SC hal-01736178 https://hal.science/hal-01736178 https://hal.science/hal-01736178v2/document https://hal.science/hal-01736178v2/file/RAPPORT_SRD_2017_V1.1%20%281%29.pdf |
op_rights |
info:eu-repo/semantics/OpenAccess |
_version_ |
1790598609436147712 |
spelling |
ftenstabretagne:oai:HAL:hal-01736178v2 2024-02-11T10:02:35+01:00 Detection of Mysticete Calls: a Sparse Representation-Based Approach Socheleau, François-Xavier Samaran, Flore Lab-STICC_IMTA_CACS_COM Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC) École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom Paris (IMT)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL)-IMT Atlantique (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom Paris (IMT)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL)-IMT Atlantique (IMT Atlantique) Institut Mines-Télécom Paris (IMT) Département Signal et Communications (IMT Atlantique - SC) IMT Atlantique (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT) Lab-STICC_ENSTAB_CID_TOMS 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) 2017-10 https://hal.science/hal-01736178 https://hal.science/hal-01736178v2/document https://hal.science/hal-01736178v2/file/RAPPORT_SRD_2017_V1.1%20%281%29.pdf en eng HAL CCSD Report N°: RR-2017-04-SC hal-01736178 https://hal.science/hal-01736178 https://hal.science/hal-01736178v2/document https://hal.science/hal-01736178v2/file/RAPPORT_SRD_2017_V1.1%20%281%29.pdf info:eu-repo/semantics/OpenAccess https://hal.science/hal-01736178 [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 [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing info:eu-repo/semantics/report Reports 2017 ftenstabretagne 2024-01-17T17:10:52Z 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. Report Blue whale ENSTA Bretagne: HAL (Ecole Nationale Supérieure de Techniques Avancées Bretagne) Pacific |