Static Sound Event Localization and Detection Using Bipartite Matching Loss for Emergency Monitoring
In this paper, we propose a method for estimating the classes and directions of static audio objects using stereo microphones in a drone environment. Drones are being increasingly used across various fields, with the integration of sensors such as cameras and microphones, broadening their scope of a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/4/1539 |
| _version_ | 1827344226813214720 |
|---|---|
| author | Chanjun Chun Hyung Jin Park Myoung Bae Seo |
| author_facet | Chanjun Chun Hyung Jin Park Myoung Bae Seo |
| author_sort | Chanjun Chun |
| collection | DOAJ |
| description | In this paper, we propose a method for estimating the classes and directions of static audio objects using stereo microphones in a drone environment. Drones are being increasingly used across various fields, with the integration of sensors such as cameras and microphones, broadening their scope of application. Therefore, we suggest a method that attaches stereo microphones to drones for the detection and direction estimation of specific emergency monitoring. Specifically, the proposed neural network is configured to estimate fixed-size audio predictions and employs bipartite matching loss for comparison with actual audio objects. To train the proposed network structure, we built an audio dataset related to speech and drones in an outdoor environment. The proposed technique for identifying and localizing sound events, based on the bipartite matching loss we proposed, works better than those of the other teams in our group. |
| first_indexed | 2024-03-07T22:43:59Z |
| format | Article |
| id | doaj.art-d5071f1a517241d2a4b523b6cedc4ee3 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-07T22:43:59Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-d5071f1a517241d2a4b523b6cedc4ee32024-02-23T15:06:20ZengMDPI AGApplied Sciences2076-34172024-02-01144153910.3390/app14041539Static Sound Event Localization and Detection Using Bipartite Matching Loss for Emergency MonitoringChanjun Chun0Hyung Jin Park1Myoung Bae Seo2Department of Computer Engineering, Chosun University, Gwangju 61452, Republic of KoreaDepartment of Future & Smart Construction Research, Korea Institute of Civil Engineering and Building Technology (KICT), Goyang-si 10223, Republic of KoreaDepartment of Future & Smart Construction Research, Korea Institute of Civil Engineering and Building Technology (KICT), Goyang-si 10223, Republic of KoreaIn this paper, we propose a method for estimating the classes and directions of static audio objects using stereo microphones in a drone environment. Drones are being increasingly used across various fields, with the integration of sensors such as cameras and microphones, broadening their scope of application. Therefore, we suggest a method that attaches stereo microphones to drones for the detection and direction estimation of specific emergency monitoring. Specifically, the proposed neural network is configured to estimate fixed-size audio predictions and employs bipartite matching loss for comparison with actual audio objects. To train the proposed network structure, we built an audio dataset related to speech and drones in an outdoor environment. The proposed technique for identifying and localizing sound events, based on the bipartite matching loss we proposed, works better than those of the other teams in our group.https://www.mdpi.com/2076-3417/14/4/1539deep learningsound event localization and detectionconvolutional neural networkbipartite matching loss |
| spellingShingle | Chanjun Chun Hyung Jin Park Myoung Bae Seo Static Sound Event Localization and Detection Using Bipartite Matching Loss for Emergency Monitoring Applied Sciences deep learning sound event localization and detection convolutional neural network bipartite matching loss |
| title | Static Sound Event Localization and Detection Using Bipartite Matching Loss for Emergency Monitoring |
| title_full | Static Sound Event Localization and Detection Using Bipartite Matching Loss for Emergency Monitoring |
| title_fullStr | Static Sound Event Localization and Detection Using Bipartite Matching Loss for Emergency Monitoring |
| title_full_unstemmed | Static Sound Event Localization and Detection Using Bipartite Matching Loss for Emergency Monitoring |
| title_short | Static Sound Event Localization and Detection Using Bipartite Matching Loss for Emergency Monitoring |
| title_sort | static sound event localization and detection using bipartite matching loss for emergency monitoring |
| topic | deep learning sound event localization and detection convolutional neural network bipartite matching loss |
| url | https://www.mdpi.com/2076-3417/14/4/1539 |
| work_keys_str_mv | AT chanjunchun staticsoundeventlocalizationanddetectionusingbipartitematchinglossforemergencymonitoring AT hyungjinpark staticsoundeventlocalizationanddetectionusingbipartitematchinglossforemergencymonitoring AT myoungbaeseo staticsoundeventlocalizationanddetectionusingbipartitematchinglossforemergencymonitoring |