| Paper ID | AUD-31.5 |
| Paper Title |
SOUND EVENT DETECTION IN URBAN AUDIO WITH SINGLE AND MULTI-RATE PCEN |
| Authors |
Christopher Ick, Brian McFee, New York University, United States |
| Session | AUD-31: Detection and Classification of Acoustic Scenes and Events 6: Events |
| Location | Gather.Town |
| Session Time: | Friday, 11 June, 13:00 - 13:45 |
| Presentation Time: | Friday, 11 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Audio and Acoustic Signal Processing: [AUD-CLAS] Detection and Classification of Acoustic Scenes and Events |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Recent literature has demonstrated that the use of per-channel energy normalization (PCEN), has significant performance improvements over traditional log-scaled mel-frequency spectrograms in acoustic sound event detection (SED) in a multiclass setting with overlapping events. However, the configuration of PCEN's parameters is sensitive to the recording environment, the characteristics of the class of events of interest, and the presence of multiple overlapping events. This leads to improvements on a class-by-class basis, but poor cross-class performance. In this article, we experiment using PCEN spectrograms as an alternative method for SED in urban audio using the UrbanSED dataset, demonstrating per-class improvements based on parameter configuration. Furthermore, we address cross-class performance with PCEN using a novel method, Multi-Rate PCEN (MRPCEN). We demonstrate cross-class SED performance with MRPCEN, demonstrating improvements to cross-class performance compared to traditional single-rate PCEN. |
