Notice
This item was automatically migrated from a legacy system. It's data has not been checked and might not meet the quality criteria of the present system.
Lidy, T., & Schindler, A. (2016). Parallel convolutional neural networks for music genre and mood classification. http://hdl.handle.net/20.500.12708/39105
E194-01 - Forschungsbereich Information und Software Engineering
-
Date (published):
2016
-
Number of Pages:
4
-
Keywords:
Audio; Classification; Deep learning; Neural networks; Music; Convolutional Neural Networks
-
Abstract:
Our approach to the MIREX 2016 Train/Test Classification Tasks for Genre, Mood and Composer detection is based on an approach combining Mel-spectrogram transformed audio and Convolutional Neural Networks (CNN). We utilize two different CNN architectures, a sequential one, and a parallel one, the latter aiming at capturing both temporal and timbral information in two different pipelines, which are merged on a later stage. In both cases, the crucial CNN parameters such as filter kernel sizes and pooling sizes were carefully chosen after a range of experiments.