تقرير
Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNs
| العنوان: | Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNs |
|---|---|
| المؤلفون: | Koutini, Khaled, Chowdhury, Shreyan, Haunschmid, Verena, Eghbal-zadeh, Hamid, Widmer, Gerhard |
| سنة النشر: | 2019 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Sound, Computer Science - Machine Learning, Computer Science - Multimedia, Electrical Engineering and Systems Science - Audio and Speech Processing |
| الوصف: | We present CP-JKU submission to MediaEval 2019; a Receptive Field-(RF)-regularized and Frequency-Aware CNN approach for tagging music with emotion/mood labels. We perform an investigation regarding the impact of the RF of the CNNs on their performance on this dataset. We observe that ResNets with smaller receptive fields -- originally adapted for acoustic scene classification -- also perform well in the emotion tagging task. We improve the performance of such architectures using techniques such as Frequency Awareness and Shake-Shake regularization, which were used in previous work on general acoustic recognition tasks. Comment: MediaEval`19, 27-29 October 2019, Sophia Antipolis, France |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/1911.05833 |
| رقم الأكسشن: | edsarx.1911.05833 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |