AENet: Learning Deep Audio Features for Video Analysis
This work addresses the problem of audio event recognition and video analysis for researchers and practitioners, offering incremental improvements through a novel network and feature combination.
The authors tackled audio event recognition by proposing AENet, a deep network that incorporates long-time frequency structure and data augmentation, achieving a 16% improvement in audio event detection. They also demonstrated that using AENet features with visual features significantly boosts performance in video tasks, such as an 8% improvement in video highlight detection.
We propose a new deep network for audio event recognition, called AENet. In contrast to speech, sounds coming from audio events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time period due to the lack of clear sub-word units that are present in speech. In order to incorporate this long-time frequency structure of audio events, we introduce a convolutional neural network (CNN) operating on a large temporal input. In contrast to previous works this allows us to train an audio event detection system end-to-end. The combination of our network architecture and a novel data augmentation outperforms previous methods for audio event detection by 16%. Furthermore, we perform transfer learning and show that our model learnt generic audio features, similar to the way CNNs learn generic features on vision tasks. In video analysis, combining visual features and traditional audio features such as MFCC typically only leads to marginal improvements. Instead, combining visual features with our AENet features, which can be computed efficiently on a GPU, leads to significant performance improvements on action recognition and video highlight detection. In video highlight detection, our audio features improve the performance by more than 8% over visual features alone.