Audio Event Detection using Weakly Labeled Data
This addresses the problem of expensive manual annotation for multimedia content analysis, offering a practical solution for researchers and practitioners, though it is incremental as it builds on existing MIL methods.
The paper tackles acoustic event detection by learning from weakly labeled data, formulating it as a Multiple Instance Learning problem and proposing SVM and neural network frameworks, achieving the ability to detect events and provide temporal locations without manual annotation.
Acoustic event detection is essential for content analysis and description of multimedia recordings. The majority of current literature on the topic learns the detectors through fully-supervised techniques employing strongly labeled data. However, the labels available for majority of multimedia data are generally weak and do not provide sufficient detail for such methods to be employed. In this paper we propose a framework for learning acoustic event detectors using only weakly labeled data. We first show that audio event detection using weak labels can be formulated as an Multiple Instance Learning problem. We then suggest two frameworks for solving multiple-instance learning, one based on support vector machines, and the other on neural networks. The proposed methods can help in removing the time consuming and expensive process of manually annotating data to facilitate fully supervised learning. Moreover, it can not only detect events in a recording but can also provide temporal locations of events in the recording. This helps in obtaining a complete description of the recording and is notable since temporal information was never known in the first place in weakly labeled data.