Towards duration robust weakly supervised sound event detection

Abstract

Sound event detection (SED) is the task of tagging the absence or presence of audio events and their corresponding interval within a given audio clip. While SED can be done using supervised machine learning, where training data is fully labeled with access to per event timestamps and duration, our work focuses on weakly-supervised sound event detection (WSSED), where prior knowledge about an event's duration is unavailable. Recent research within the field focuses on improving segment- and event-level localization performance for specific datasets regarding specific evaluation metrics. Specifically, well-performing event-level localization requires fully labeled development subsets to obtain event duration estimates, which significantly benefits localization performance. Moreover, well-performing segment-level localization models output predictions at a coarse-scale (e.g., 1 second), hindering their deployment on datasets containing very short events (< 1 second). This work proposes a duration robust CRNN (CDur) framework, which aims to achieve competitive performance in terms of segment- and event-level localization. This paper proposes a new post-processing strategy named "Triple Threshold" and investigates two data augmentation methods along with a label smoothing method within the scope of WSSED. Evaluation of our model is done on the DCASE2017 and 2018 Task 4 datasets, and URBAN-SED. Our model outperforms other approaches on the DCASE2018 and URBAN-SED datasets without requiring prior duration knowledge. In particular, our model is capable of similar performance to strongly-labeled supervised models on the URBAN-SED dataset. Lastly, ablation experiments to reveal that without post-processing, our model's localization performance drop is significantly lower compared with other approaches.

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Decoupled Weight Decay Regularization
• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Large-Margin Softmax Loss for Convolutional Neural Networks
• Sound Event Detection and Time-Frequency Segmentation from Weakly Labelled Data
• Weakly Labelled AudioSet Tagging with Attention Neural Networks
• Sound event detection using weakly labeled dataset with stacked convolutional and recurrent neural network
• Surrey-cvssp system for DCASE2017 challenge task4
• Duration robust weakly supervised sound event detection
• End-to-End Polyphonic Sound Event Detection Using Convolutional Recurrent Neural Networks with Learned Time-Frequency Representation Input

Cited by in corpus (7)

• You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection
• Voice activity detection in the wild: A data-driven approach using teacher-student training
• Enhance Temporal Relations in Audio Captioning with Sound Event Detection
• A Multi-grained based Attention Network for Semi-supervised Sound Event Detection
• Text-to-Audio Grounding: Building Correspondence Between Captions and Sound Events
• An empirical study of weakly supervised audio tagging embeddings for general audio representations
• Streaming Anchor Loss: Augmenting Supervision with Temporal Significance