A Closer Look at Weak Label Learning for Audio Events

Abstract

Audio content analysis in terms of sound events is an important research problem for a variety of applications. Recently, the development of weak labeling approaches for audio or sound event detection (AED) and availability of large scale weakly labeled dataset have finally opened up the possibility of large scale AED. However, a deeper understanding of how weak labels affect the learning for sound events is still missing from literature. In this work, we first describe a CNN based approach for weakly supervised training of audio events. The approach follows some basic design principle desirable in a learning method relying on weakly labeled audio. We then describe important characteristics, which naturally arise in weakly supervised learning of sound events. We show how these aspects of weak labels affect the generalization of models. More specifically, we study how characteristics such as label density and corruption of labels affects weakly supervised training for audio events. We also study the feasibility of directly obtaining weak labeled data from the web without any manual label and compare it with a dataset which has been manually labeled. The analysis and understanding of these factors should be taken into picture in the development of future weak label learning methods. Audioset, a large scale weakly labeled dataset for sound events is used in our experiments.

arXiv comment10 pages

References in corpus (1)

• Very Deep Convolutional Networks for Large-Scale Image Recognition

Cited by in corpus (15)

• PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation
• Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition
• AclNet: efficient end-to-end audio classification CNN
• Addressing Missing Labels in Large-Scale Sound Event Recognition Using a Teacher-Student Framework With Loss Masking
• Joint framework with deep feature distillation and adaptive focal loss for weakly supervised audio tagging and acoustic event detection
• Training Sound Event Detection On A Heterogeneous Dataset
• Secost: Sequential co-supervision for large scale weakly labeled audio event detection
• Training image classifiers using Semi-Weak Label Data
• Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset
• Power Pooling Operators and Confidence Learning for Semi-Supervised Sound Event Detection
• Triple Attention Network architecture for MovieQA
• The Impact of Label Noise on a Music Tagger
• Compression of Acoustic Event Detection Models With Quantized Distillation
• Power pooling: An adaptive pooling function for weakly labelled sound event detection
• Self-supervised Attention Model for Weakly Labeled Audio Event Classification