Large-Scale Weakly Labeled Semi-Supervised Sound Event Detection in Domestic Environments

Abstract

This paper presents DCASE 2018 task 4. The task evaluates systems for the large-scale detection of sound events using weakly labeled data (without time boundaries). The target of the systems is to provide not only the event class but also the event time boundaries given that multiple events can be present in an audio recording. Another challenge of the task is to explore the possibility to exploit a large amount of unbalanced and unlabeled training data together with a small weakly labeled training set to improve system performance. The data are Youtube video excerpts from domestic context which have many applications such as ambient assisted living. The domain was chosen due to the scientific challenges (wide variety of sounds, time-localized events.. .) and potential industrial applications .

Cited by in corpus (27)

• Duration robust weakly supervised sound event detection
• Joint Analysis of Sound Events and Acoustic Scenes Using Multitask Learning
• Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection
• Training Sound Event Detection On A Heterogeneous Dataset
• Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization
• Guided Learning Convolution System for DCASE 2019 Task 4
• Weakly Labeled Sound Event Detection Using Tri-training and Adversarial Learning
• Specialized Decision Surface and Disentangled Feature for Weakly-Supervised Polyphonic Sound Event Detection
• GISE-51: A scalable isolated sound events dataset
• Polyphonic sound event detection based on convolutional recurrent neural networks with semi-supervised loss function for DCASE challenge 2020 task 4
• A Transformer-based Audio Captioning Model with Keyword Estimation
• Guided learning for weakly-labeled semi-supervised sound event detection
• Active Learning for Sound Event Detection
• Cosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection
• Sound Event Detection Using Duration Robust Loss Function
• Power Pooling Operators and Confidence Learning for Semi-Supervised Sound Event Detection
• Text-to-Audio Grounding: Building Correspondence Between Captions and Sound Events
• A Joint Framework for Audio Tagging and Weakly Supervised Acoustic Event Detection Using DenseNet with Global Average Pooling
• A Global-local Attention Framework for Weakly Labelled Audio Tagging
• Sound event detection using weakly-labeled semi-supervised data with GCRNNS, VAT and Self-Adaptive Label Refinement
• Hodge and Podge: Hybrid Supervised Sound Event Detection with Multi-Hot MixMatch and Composition Consistence Training
• Adaptive Multi-scale Detection of Acoustic Events
• Overcoming label noise in audio event detection using sequential labeling
• Sound Event Detection Based on Curriculum Learning Considering Learning Difficulty of Events
• Impact of Sound Duration and Inactive Frames on Sound Event Detection Performance
• Semi-supervised Sound Event Detection using Random Augmentation and Consistency Regularization
• Power pooling: An adaptive pooling function for weakly labelled sound event detection