Stacked convolutional and recurrent neural networks for music emotion recognition

Autor:	Miroslav Malik, Sharath Adavanne, Konstantinos Drosos, Tuomas Oskari Virtanen, Dasa Ticha, Roman Jarina
Přispěvatelé:	Tampere University, Signal Processing, Research group: Audio research group - ARG
Jazyk:	angličtina
Rok vydání:	2017
Předmět:	FOS: Computer and information sciences Computer Science - Learning Sound (cs.SD) 113 Computer and information sciences Computer Science - Sound Machine Learning (cs.LG)
Zdroj:	Scopus-Elsevier Tampere University
Popis:	This paper studies the emotion recognition from musical tracks in the 2-dimensional valence-arousal (V-A) emotional space. We propose a method based on convolutional (CNN) and recurrent neural networks (RNN), having significantly fewer parameters compared with the state-of-the-art method for the same task. We utilize one CNN layer followed by two branches of RNNs trained separately for arousal and valence. The method was evaluated using the 'MediaEval2015 emotion in music' dataset. We achieved an RMSE of 0.202 for arousal and 0.268 for valence, which is the best result reported on this dataset. Comment: Accepted for Sound and Music Computing (SMC 2017)
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a4444bd0d1cf059339688ed6c4c7b01 https://trepo.tuni.fi/handle/10024/129168 Zobrazit plný text záznamu