Automatically predicting giant panda mating success based on acoustic features
As a solitary species, giant pandas do not frequently vocalize. However, they make significantly more vocalizations during the breeding season, implying that vocalizations are essential for coordinating their reproduction and expression of mating preference. Previous studies have also shown that gia...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-12-01
|
| Series: | Global Ecology and Conservation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2351989420308428 |
| _version_ | 1818664497674452992 |
|---|---|
| author | Weiran Yan Maolin Tang Zeyuan Chen Peng Chen Qijun Zhao Pinjia Que Kongju Wu Rong Hou Zhihe Zhang |
| author_facet | Weiran Yan Maolin Tang Zeyuan Chen Peng Chen Qijun Zhao Pinjia Que Kongju Wu Rong Hou Zhihe Zhang |
| author_sort | Weiran Yan |
| collection | DOAJ |
| description | As a solitary species, giant pandas do not frequently vocalize. However, they make significantly more vocalizations during the breeding season, implying that vocalizations are essential for coordinating their reproduction and expression of mating preference. Previous studies have also shown that giant panda vocalizations are correlated with mating results and reproduction. This paper makes the first attempt to devise an automatic method for predicting the mating success of giant pandas based on their vocalizations. Using audio recordings of mating giant pandas collected during breeding encounters, we firstly isolated the vocalizations, and normalized their decibels and duration. We then extracted acoustic features from the audio segments and fed the acoustic features into a deep neural network, which classified the mating result into a success or a failure. The proposed deep neural network employs convolution layers followed by bidirectional gated recurrent units to extract features relevant to mating preference. Evaluation experiments on a data set collected during the past nine years obtained promising results, demonstrating the potential of audio-based automatic mating success prediction in assisting giant panda reproduction. |
| first_indexed | 2024-12-17T05:33:41Z |
| format | Article |
| id | doaj.art-5c13c2f6832448068bf93c5b38da6696 |
| institution | Directory Open Access Journal |
| issn | 2351-9894 |
| language | English |
| last_indexed | 2024-12-17T05:33:41Z |
| publishDate | 2020-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Global Ecology and Conservation |
| spelling | doaj.art-5c13c2f6832448068bf93c5b38da66962022-12-21T22:01:41ZengElsevierGlobal Ecology and Conservation2351-98942020-12-0124e01301Automatically predicting giant panda mating success based on acoustic featuresWeiran Yan0Maolin Tang1Zeyuan Chen2Peng Chen3Qijun Zhao4Pinjia Que5Kongju Wu6Rong Hou7Zhihe Zhang8College of Computer Science, Sichuan University, ChengDu, SiChuan, PR ChinaCollege of Computer Science, Sichuan University, ChengDu, SiChuan, PR ChinaCollege of Computer Science, Sichuan University, ChengDu, SiChuan, PR ChinaChengdu Research Base of Giant Panda Breeding, Sichuan Key Laboratory of Conservation Biology for Endangered Wildlife, ChengDu, SiChuan, PR China; Sichuan Academy of Giant Panda, ChengDu, SiChuan, PR China; Corresponding author. Chengdu Research Base of Giant Panda Breeding, Sichuan Key Laboratory of Conservation Biology for Endangered Wildlife, ChengDu, SiChuan, PR China.College of Computer Science, Sichuan University, ChengDu, SiChuan, PR China; School of Information Science and Technology, Tibet University, Lhasa, Tibet, PR China; Corresponding author. College of Computer Science, Sichuan University, ChengDu, SiChuan, PR China.Chengdu Research Base of Giant Panda Breeding, Sichuan Key Laboratory of Conservation Biology for Endangered Wildlife, ChengDu, SiChuan, PR China; Sichuan Academy of Giant Panda, ChengDu, SiChuan, PR ChinaChengdu Research Base of Giant Panda Breeding, Sichuan Key Laboratory of Conservation Biology for Endangered Wildlife, ChengDu, SiChuan, PR China; Sichuan Academy of Giant Panda, ChengDu, SiChuan, PR ChinaChengdu Research Base of Giant Panda Breeding, Sichuan Key Laboratory of Conservation Biology for Endangered Wildlife, ChengDu, SiChuan, PR China; Sichuan Academy of Giant Panda, ChengDu, SiChuan, PR ChinaChengdu Research Base of Giant Panda Breeding, Sichuan Key Laboratory of Conservation Biology for Endangered Wildlife, ChengDu, SiChuan, PR China; Sichuan Academy of Giant Panda, ChengDu, SiChuan, PR ChinaAs a solitary species, giant pandas do not frequently vocalize. However, they make significantly more vocalizations during the breeding season, implying that vocalizations are essential for coordinating their reproduction and expression of mating preference. Previous studies have also shown that giant panda vocalizations are correlated with mating results and reproduction. This paper makes the first attempt to devise an automatic method for predicting the mating success of giant pandas based on their vocalizations. Using audio recordings of mating giant pandas collected during breeding encounters, we firstly isolated the vocalizations, and normalized their decibels and duration. We then extracted acoustic features from the audio segments and fed the acoustic features into a deep neural network, which classified the mating result into a success or a failure. The proposed deep neural network employs convolution layers followed by bidirectional gated recurrent units to extract features relevant to mating preference. Evaluation experiments on a data set collected during the past nine years obtained promising results, demonstrating the potential of audio-based automatic mating success prediction in assisting giant panda reproduction.http://www.sciencedirect.com/science/article/pii/S2351989420308428Giant pandaMating success predictionSpeech emotion recognitionDeep neural network |
| spellingShingle | Weiran Yan Maolin Tang Zeyuan Chen Peng Chen Qijun Zhao Pinjia Que Kongju Wu Rong Hou Zhihe Zhang Automatically predicting giant panda mating success based on acoustic features Global Ecology and Conservation Giant panda Mating success prediction Speech emotion recognition Deep neural network |
| title | Automatically predicting giant panda mating success based on acoustic features |
| title_full | Automatically predicting giant panda mating success based on acoustic features |
| title_fullStr | Automatically predicting giant panda mating success based on acoustic features |
| title_full_unstemmed | Automatically predicting giant panda mating success based on acoustic features |
| title_short | Automatically predicting giant panda mating success based on acoustic features |
| title_sort | automatically predicting giant panda mating success based on acoustic features |
| topic | Giant panda Mating success prediction Speech emotion recognition Deep neural network |
| url | http://www.sciencedirect.com/science/article/pii/S2351989420308428 |
| work_keys_str_mv | AT weiranyan automaticallypredictinggiantpandamatingsuccessbasedonacousticfeatures AT maolintang automaticallypredictinggiantpandamatingsuccessbasedonacousticfeatures AT zeyuanchen automaticallypredictinggiantpandamatingsuccessbasedonacousticfeatures AT pengchen automaticallypredictinggiantpandamatingsuccessbasedonacousticfeatures AT qijunzhao automaticallypredictinggiantpandamatingsuccessbasedonacousticfeatures AT pinjiaque automaticallypredictinggiantpandamatingsuccessbasedonacousticfeatures AT kongjuwu automaticallypredictinggiantpandamatingsuccessbasedonacousticfeatures AT ronghou automaticallypredictinggiantpandamatingsuccessbasedonacousticfeatures AT zhihezhang automaticallypredictinggiantpandamatingsuccessbasedonacousticfeatures |