Large-scale weakly supervised audio classification using gated convolutional neural network
arXiv:1710.00343
Abstract
In this paper, we present a gated convolutional neural network and a temporal attention-based localization method for audio classification, which won the 1st place in the large-scale weakly supervised sound event detection task of Detection and Classification of Acoustic Scenes and Events (DCASE) 2017 challenge. The audio clips in this task, which are extracted from YouTube videos, are manually labeled with one or a few audio tags but without timestamps of the audio events, which is called as weakly labeled data. Two sub-tasks are defined in this challenge including audio tagging and sound event detection using this weakly labeled data. A convolutional recurrent neural network (CRNN) with learnable gated linear units (GLUs) non-linearity applied on the log Mel spectrogram is proposed. In addition, a temporal attention method is proposed along the frames to predicate the locations of each audio event in a chunk from the weakly labeled data. We ranked the 1st and the 2nd as a team in these two sub-tasks of DCASE 2017 challenge with F value 55.6\% and Equal error 0.73, respectively.
submitted to ICASSP2018, summary on the 1st place system in DCASE2017 task4 challenge
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Language Modeling with Gated Convolutional Networks
- Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
- Automatic tagging using deep convolutional neural networks
- Audio Event Detection using Weakly Labeled Data
Cited by in corpus (4)
- Multi-level Attention Model for Weakly Supervised Audio Classification
- Multiscale CNN based Deep Metric Learning for Bioacoustic Classification: Overcoming Training Data Scarcity Using Dynamic Triplet Loss
- DCASE 2018 Challenge Surrey Cross-Task convolutional neural network baseline
- Audio Set classification with attention model: A probabilistic perspective