Duration robust weakly supervised sound event detection

Abstract

Task 4 of the DCASE2018 challenge demonstrated that substantially more research is needed for a real-world application of sound event detection. Analyzing the challenge results it can be seen that most successful models are biased towards predicting long (e.g., over 5s) clips. This work aims to investigate the performance impact of fixed-sized window median filter post-processing and advocate the use of double thresholding as a more robust and predictable post-processing method. Further, four different temporal subsampling methods within the CRNN framework are proposed: mean-max, alpha-mean-max, Lp-norm and convolutional. We show that for this task subsampling the temporal resolution by a neural network enhances the F1 score as well as its robustness towards short, sporadic sound events. Our best single model achieves 30.1% F1 on the evaluation set and the best fusion model 32.5%, while being robust to event length variations.

arXiv commentAccepted by ICASSP2020

References in corpus (4)

• Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
• Large-Scale Weakly Labeled Semi-Supervised Sound Event Detection in Domestic Environments
• Polyphonic audio tagging with sequentially labelled data using CRNN with learnable gated linear units
• Specialized Decision Surface and Disentangled Feature for Weakly-Supervised Polyphonic Sound Event Detection

Cited by in corpus (5)

• Towards duration robust weakly supervised sound event detection
• Voice activity detection in the wild: A data-driven approach using teacher-student training
• Joint framework with deep feature distillation and adaptive focal loss for weakly supervised audio tagging and acoustic event detection
• A Joint Framework for Audio Tagging and Weakly Supervised Acoustic Event Detection Using DenseNet with Global Average Pooling
• Impact of Sound Duration and Inactive Frames on Sound Event Detection Performance