| Presentation | 2023-11-16 A consideration of a music detection method based on object detection for separating music events that overlap with each other Masaki Kitayama, Kazuhiro Onishi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We consider the music event detection which is based on the framework of object detection, for detecting individual music events that often overlap with each other in audio contents. Conventional music detection methods which perform frame-level classification have difficulty in detecting individual music events that overlap with each other. Since the object detection framework in computer vision directly regresses event intervals, these overlapping events can be individually detected at the event-level. We propose a music detection model based on Faster R-CNN, an object detection method, and evaluate it on a dataset simulating DJ mixing techniques, assuming commercial audio contents. This study will form the basis of technology that will contribute to more advanced analysis and content production for audio content currently in commercial use. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Audio event detection / Music detection / Object detection / Faster R-CNN / Event-level detection |
| Paper # | PRMU2023-22 |
| Date of Issue | 2023-11-09 (PRMU) |
| Conference Information | |
| Committee | PRMU / IPSJ-CVIM / IPSJ-DCC / IPSJ-CGVI |
|---|---|
| Conference Date | 2023/11/16(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Kunio Kashio(NTT) |
| Vice Chair | Takuya Funatomi(NAIST) / Go Irie(Tokyo Univ. of Science) |
| Secretary | Takuya Funatomi(Tokyo Inst. of Tech.) / Go Irie(Riken) |
| Assistant | Kei Shimonishi(Kyoto Univ.) / Kensho Hara(AIST) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media / Special Interest Group on Digital Contents Creation / Special Interest Group on Computer Graphics and Visual Informatics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A consideration of a music detection method based on object detection for separating music events that overlap with each other |
| Sub Title (in English) | |
| Keyword(1) | Audio event detection |
| Keyword(2) | Music detection |
| Keyword(3) | Object detection |
| Keyword(4) | Faster R-CNN |
| Keyword(5) | Event-level detection |
| 1st Author's Name | Masaki Kitayama |
| 1st Author's Affiliation | Hakuhodo Technologies Inc.(Hakuhodo Technologies) |
| 2nd Author's Name | Kazuhiro Onishi |
| 2nd Author's Affiliation | Hakuhodo Technologies Inc.(Hakuhodo Technologies) |
| Date | 2023-11-16 |
| Paper # | PRMU2023-22 |
| Volume (vol) | vol.123 |
| Number (no) | PRMU-266 |
| Page | pp.pp.37-42(PRMU), |
| #Pages | 6 |
| Date of Issue | 2023-11-09 (PRMU) |