ohun: An R package for diagnosing and optimizing automatic sound event detection
Abstract Animal acoustic signals are widely used in diverse research areas due to the relative ease with which sounds can be registered across a wide range of taxonomic groups and research settings. However, bioacoustics research can quickly generate large data sets, which might prove challenging to...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-09-01
|
| Series: | Methods in Ecology and Evolution |
| Subjects: | |
| Online Access: | https://doi.org/10.1111/2041-210X.14170 |
| _version_ | 1827824154153320448 |
|---|---|
| author | Marcelo Araya‐Salas Grace Smith‐Vidaurre Gloriana Chaverri Juan C. Brenes Fabiola Chirino Jorge Elizondo‐Calvo Alejandro Rico‐Guevara |
| author_facet | Marcelo Araya‐Salas Grace Smith‐Vidaurre Gloriana Chaverri Juan C. Brenes Fabiola Chirino Jorge Elizondo‐Calvo Alejandro Rico‐Guevara |
| author_sort | Marcelo Araya‐Salas |
| collection | DOAJ |
| description | Abstract Animal acoustic signals are widely used in diverse research areas due to the relative ease with which sounds can be registered across a wide range of taxonomic groups and research settings. However, bioacoustics research can quickly generate large data sets, which might prove challenging to analyse promptly. Although many tools are available for the automated detection of sounds, choosing the right approach can be difficult and only a few tools provide a framework for evaluating detection performance. Here, we present ohun, an R package intended to facilitate automated sound event detection. ohun provides functions to diagnose and optimize detection routines, compare performance among different detection approaches and evaluate the accuracy in inferring the temporal location of events. The package uses reference annotations containing the time position of target sounds in a training data set to evaluate detection routine performance using common signal detection theory indices. This can be done both with routine outputs imported from other software and detections run within the package. The package also provides functions to organize acoustic data sets in a format amenable to detection analyses. In addition, ohun includes energy‐based and template‐based detection methods, two commonly used automatic approaches in bioacoustics research. We show how ohun can be used to automatically detect vocal signals with case studies of adult male zebra finch Taenopygia gutata songs and Spix's disc‐winged bat Thyroptera tricolor ultrasonic social calls. We also include examples of how to evaluate the detection performance of ohun and external software. Finally, we provide some general suggestions to improve detection performance. |
| first_indexed | 2024-03-12T02:21:55Z |
| format | Article |
| id | doaj.art-3a68ebac31c64f2982c5dfbc2e4b9d81 |
| institution | Directory Open Access Journal |
| issn | 2041-210X |
| language | English |
| last_indexed | 2024-03-12T02:21:55Z |
| publishDate | 2023-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | Methods in Ecology and Evolution |
| spelling | doaj.art-3a68ebac31c64f2982c5dfbc2e4b9d812023-09-06T04:43:40ZengWileyMethods in Ecology and Evolution2041-210X2023-09-011492259227110.1111/2041-210X.14170ohun: An R package for diagnosing and optimizing automatic sound event detectionMarcelo Araya‐Salas0Grace Smith‐Vidaurre1Gloriana Chaverri2Juan C. Brenes3Fabiola Chirino4Jorge Elizondo‐Calvo5Alejandro Rico‐Guevara6Centro de Investigación en Neurociencias Universidad de Costa Rica San José Costa RicaLaboratory of Neurogenetics of Language Rockefeller University New York New York USASede del Sur Universidad de Costa Rica Golfito Costa RicaCentro de Investigación en Neurociencias Universidad de Costa Rica San José Costa RicaEscuela de Biología Universidad de Costa Rica San José Costa RicaEscuela de Biología Universidad de Costa Rica San José Costa RicaDepartment of Biology University of Washington Seattle Washington USAAbstract Animal acoustic signals are widely used in diverse research areas due to the relative ease with which sounds can be registered across a wide range of taxonomic groups and research settings. However, bioacoustics research can quickly generate large data sets, which might prove challenging to analyse promptly. Although many tools are available for the automated detection of sounds, choosing the right approach can be difficult and only a few tools provide a framework for evaluating detection performance. Here, we present ohun, an R package intended to facilitate automated sound event detection. ohun provides functions to diagnose and optimize detection routines, compare performance among different detection approaches and evaluate the accuracy in inferring the temporal location of events. The package uses reference annotations containing the time position of target sounds in a training data set to evaluate detection routine performance using common signal detection theory indices. This can be done both with routine outputs imported from other software and detections run within the package. The package also provides functions to organize acoustic data sets in a format amenable to detection analyses. In addition, ohun includes energy‐based and template‐based detection methods, two commonly used automatic approaches in bioacoustics research. We show how ohun can be used to automatically detect vocal signals with case studies of adult male zebra finch Taenopygia gutata songs and Spix's disc‐winged bat Thyroptera tricolor ultrasonic social calls. We also include examples of how to evaluate the detection performance of ohun and external software. Finally, we provide some general suggestions to improve detection performance.https://doi.org/10.1111/2041-210X.14170animal vocalizationsbioacousticssound event detection |
| spellingShingle | Marcelo Araya‐Salas Grace Smith‐Vidaurre Gloriana Chaverri Juan C. Brenes Fabiola Chirino Jorge Elizondo‐Calvo Alejandro Rico‐Guevara ohun: An R package for diagnosing and optimizing automatic sound event detection Methods in Ecology and Evolution animal vocalizations bioacoustics sound event detection |
| title | ohun: An R package for diagnosing and optimizing automatic sound event detection |
| title_full | ohun: An R package for diagnosing and optimizing automatic sound event detection |
| title_fullStr | ohun: An R package for diagnosing and optimizing automatic sound event detection |
| title_full_unstemmed | ohun: An R package for diagnosing and optimizing automatic sound event detection |
| title_short | ohun: An R package for diagnosing and optimizing automatic sound event detection |
| title_sort | ohun an r package for diagnosing and optimizing automatic sound event detection |
| topic | animal vocalizations bioacoustics sound event detection |
| url | https://doi.org/10.1111/2041-210X.14170 |
| work_keys_str_mv | AT marceloarayasalas ohunanrpackagefordiagnosingandoptimizingautomaticsoundeventdetection AT gracesmithvidaurre ohunanrpackagefordiagnosingandoptimizingautomaticsoundeventdetection AT glorianachaverri ohunanrpackagefordiagnosingandoptimizingautomaticsoundeventdetection AT juancbrenes ohunanrpackagefordiagnosingandoptimizingautomaticsoundeventdetection AT fabiolachirino ohunanrpackagefordiagnosingandoptimizingautomaticsoundeventdetection AT jorgeelizondocalvo ohunanrpackagefordiagnosingandoptimizingautomaticsoundeventdetection AT alejandroricoguevara ohunanrpackagefordiagnosingandoptimizingautomaticsoundeventdetection |