Sound Event Detection in Urban Audio With Single and Multi-Rate PCEN
This work aims to improve sound event detection performance in urban audio for various applications, particularly addressing the challenge of cross-class performance with PCEN.
This paper explores the use of Per-Channel Energy Normalization (PCEN) for sound event detection (SED) in urban audio, showing per-class improvements with parameter configuration. It then introduces Multi-Rate PCEN (MRPCEN) to address cross-class performance, demonstrating improvements over traditional single-rate PCEN.
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 multi-class 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.