Shahin Amiriparian, Maurice Gerczuk, Sandra Ottl, Lukas Stappen, Alice Baird, Lukas Koebe, Björn W. Schuller. Towards cross-modal pre-training and learning tempo-spatial characteristics for audio recognition with convolutional and recurrent neural networks. EURASIP J. Audio, Speech and Music Processing, 2020(1):19, 2020. [doi]
Abstract is missing.