Cochleogram-based approach for detecting perceived emotions in music
作者：
Highlights：
• Emotion-based approach for efficient search and media management represents an important part of personalized music information retrieval.
• Efficient system for detecting affective music content on a dimensional model of emotions is developed.
• Proposed approach uses human cochlear model and Convolutional neural network to extract relevant music features.
• The experimental results prove the effectiveness of our proposal in all aspects of music emotion recognition.
摘要
•Emotion-based approach for efficient search and media management represents an important part of personalized music information retrieval.•Efficient system for detecting affective music content on a dimensional model of emotions is developed.•Proposed approach uses human cochlear model and Convolutional neural network to extract relevant music features.•The experimental results prove the effectiveness of our proposal in all aspects of music emotion recognition.
论文关键词：Music information retrieval,Affective content prediction,Cochlea,ConvNet
论文评审过程：Received 26 September 2019, Revised 30 March 2020, Accepted 14 April 2020, Available online 28 April 2020, Version of Record 28 April 2020.
论文官网地址：https://doi.org/10.1016/j.ipm.2020.102270
