Onset and offset weighted loss function for sound event detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Song, Tao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913273472876544
author Song, Tao
author_facet Song, Tao
contents In a typical sound event detection (SED) system, the existence of a sound event is detected at a frame level, and consecutive frames with the same event detected are combined as one sound event. The median filter is applied as a post-processing step to remove detection errors as much as possible. However, detection errors occurring around the onset and offset of a sound event are beyond the capacity of the median filter. To address this issue, an onset and offset weighted binary cross-entropy (OWBCE) loss function is proposed in this paper, which trains the DNN model to be more robust on frames around (a) onsets and offsets. Experiments are carried out in the context of DCASE 2022 task 4. Results show that OWBCE outperforms BCE when different models are considered. For a basic CRNN, relative improvements of 6.43% in event-F1, 1.96% in PSDS1, and 2.43% in PSDS2 can be achieved by OWBCE.
format Preprint
id arxiv_https___arxiv_org_abs_2403_13254
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Onset and offset weighted loss function for sound event detection
Song, Tao
Sound
Audio and Speech Processing
In a typical sound event detection (SED) system, the existence of a sound event is detected at a frame level, and consecutive frames with the same event detected are combined as one sound event. The median filter is applied as a post-processing step to remove detection errors as much as possible. However, detection errors occurring around the onset and offset of a sound event are beyond the capacity of the median filter. To address this issue, an onset and offset weighted binary cross-entropy (OWBCE) loss function is proposed in this paper, which trains the DNN model to be more robust on frames around (a) onsets and offsets. Experiments are carried out in the context of DCASE 2022 task 4. Results show that OWBCE outperforms BCE when different models are considered. For a basic CRNN, relative improvements of 6.43% in event-F1, 1.96% in PSDS1, and 2.43% in PSDS2 can be achieved by OWBCE.
title Onset and offset weighted loss function for sound event detection
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2403.13254