An Efficient Model for a Vast Number of Bird Species Identification Based on Acoustic Features
Birds have been widely considered crucial indicators of biodiversity. It is essential to identify bird species precisely for biodiversity surveys. With the rapid development of artificial intelligence, bird species identification has been facilitated by deep learning using audio samples. Prior studi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/12/18/2434 |
| _version_ | 1797491956595556352 |
|---|---|
| author | Hanlin Wang Yingfan Xu Yan Yu Yucheng Lin Jianghong Ran |
| author_facet | Hanlin Wang Yingfan Xu Yan Yu Yucheng Lin Jianghong Ran |
| author_sort | Hanlin Wang |
| collection | DOAJ |
| description | Birds have been widely considered crucial indicators of biodiversity. It is essential to identify bird species precisely for biodiversity surveys. With the rapid development of artificial intelligence, bird species identification has been facilitated by deep learning using audio samples. Prior studies mainly focused on identifying several bird species using deep learning or machine learning based on acoustic features. In this paper, we proposed a novel deep learning method to better identify a large number of bird species based on their call. The proposed method was made of LSTM (Long Short−Term Memory) with coordinate attention. More than 70,000 bird−call audio clips, including 264 bird species, were collected from Xeno−Canto. An evaluation experiment showed that our proposed network achieved 77.43% mean average precision (mAP), which indicates that our proposed network is valuable for automatically identifying a massive number of bird species based on acoustic features and avian biodiversity monitoring. |
| first_indexed | 2024-03-10T00:55:44Z |
| format | Article |
| id | doaj.art-5f38fb4d0b984e2fa643ed306c6e5849 |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-03-10T00:55:44Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-5f38fb4d0b984e2fa643ed306c6e58492023-11-23T14:42:55ZengMDPI AGAnimals2076-26152022-09-011218243410.3390/ani12182434An Efficient Model for a Vast Number of Bird Species Identification Based on Acoustic FeaturesHanlin Wang0Yingfan Xu1Yan Yu2Yucheng Lin3Jianghong Ran4Key Laboratory of Bio-Resources and Eco-Environment (Ministry of Education), Sichuan University, Chengdu 610065, ChinaSchool of Informatics, University of Edinburgh, Edinburgh EH8 9YL, UKKey Laboratory of Bio-Resources and Eco-Environment (Ministry of Education), Sichuan University, Chengdu 610065, ChinaKey Laboratory of Bio-Resources and Eco-Environment (Ministry of Education), Sichuan University, Chengdu 610065, ChinaKey Laboratory of Bio-Resources and Eco-Environment (Ministry of Education), Sichuan University, Chengdu 610065, ChinaBirds have been widely considered crucial indicators of biodiversity. It is essential to identify bird species precisely for biodiversity surveys. With the rapid development of artificial intelligence, bird species identification has been facilitated by deep learning using audio samples. Prior studies mainly focused on identifying several bird species using deep learning or machine learning based on acoustic features. In this paper, we proposed a novel deep learning method to better identify a large number of bird species based on their call. The proposed method was made of LSTM (Long Short−Term Memory) with coordinate attention. More than 70,000 bird−call audio clips, including 264 bird species, were collected from Xeno−Canto. An evaluation experiment showed that our proposed network achieved 77.43% mean average precision (mAP), which indicates that our proposed network is valuable for automatically identifying a massive number of bird species based on acoustic features and avian biodiversity monitoring.https://www.mdpi.com/2076-2615/12/18/2434bird callsdeep learningspecies identificationavian biodiversity |
| spellingShingle | Hanlin Wang Yingfan Xu Yan Yu Yucheng Lin Jianghong Ran An Efficient Model for a Vast Number of Bird Species Identification Based on Acoustic Features Animals bird calls deep learning species identification avian biodiversity |
| title | An Efficient Model for a Vast Number of Bird Species Identification Based on Acoustic Features |
| title_full | An Efficient Model for a Vast Number of Bird Species Identification Based on Acoustic Features |
| title_fullStr | An Efficient Model for a Vast Number of Bird Species Identification Based on Acoustic Features |
| title_full_unstemmed | An Efficient Model for a Vast Number of Bird Species Identification Based on Acoustic Features |
| title_short | An Efficient Model for a Vast Number of Bird Species Identification Based on Acoustic Features |
| title_sort | efficient model for a vast number of bird species identification based on acoustic features |
| topic | bird calls deep learning species identification avian biodiversity |
| url | https://www.mdpi.com/2076-2615/12/18/2434 |
| work_keys_str_mv | AT hanlinwang anefficientmodelforavastnumberofbirdspeciesidentificationbasedonacousticfeatures AT yingfanxu anefficientmodelforavastnumberofbirdspeciesidentificationbasedonacousticfeatures AT yanyu anefficientmodelforavastnumberofbirdspeciesidentificationbasedonacousticfeatures AT yuchenglin anefficientmodelforavastnumberofbirdspeciesidentificationbasedonacousticfeatures AT jianghongran anefficientmodelforavastnumberofbirdspeciesidentificationbasedonacousticfeatures AT hanlinwang efficientmodelforavastnumberofbirdspeciesidentificationbasedonacousticfeatures AT yingfanxu efficientmodelforavastnumberofbirdspeciesidentificationbasedonacousticfeatures AT yanyu efficientmodelforavastnumberofbirdspeciesidentificationbasedonacousticfeatures AT yuchenglin efficientmodelforavastnumberofbirdspeciesidentificationbasedonacousticfeatures AT jianghongran efficientmodelforavastnumberofbirdspeciesidentificationbasedonacousticfeatures |