CRNNs for Urban Sound Tagging with spatiotemporal context
arXiv:2008.10413
Abstract
This paper describes CRNNs we used to participate in Task 5 of the DCASE 2020 challenge. This task focuses on hierarchical multilabel urban sound tagging with spatiotemporal context. The code is available on our GitHub repository at https://github.com/multitel-ai/urban-sound-tagging.
arXiv comment4 pages, 5 figures, DCASE2020 Challenge - DCASE
References in corpus (9)
- mixup: Beyond Empirical Risk Minimization
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- Large Batch Training of Convolutional Networks
- Lookahead Optimizer: k steps forward, 1 step back
- Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
- PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition
- Time2Vec: Learning a Vector Representation of Time
- SONYC-UST-V2: An Urban Sound Tagging Dataset with Spatiotemporal Context
- Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization