SVR BASED DOUBLE-SCALE REGRESSION FOR DYNAMIC EMOTION PREDICTION IN MUSIC

被引：0

作者：

Xianyu, Haishu ^{[1
]}

Li, Xinxing ^{[1
]}

Chen, Wenxiao ^{[1
]}

Meng, Fanhang ^{[1
]}

Tian, Jiashen ^{[1
]}

Xu, Mingxing ^{[1
]}

Cai, Lianhong ^{[1
]}

机构：

[1] Tsinghua Univ, Dept Comp Sci & Technol, Tsinghua Natl Lab Informat Sci & Technol TNList, Key Lab Pervas Comp,Minist Educ, Beijing, Peoples R China

来源：

2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS | 2016年

关键词：

Music; Emotion; Multi-scale; Double-scale Support Vector Regression;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Dynamic music emotion prediction is to recognize the continuous emotion contained in music, and has various applications. In recent years, dynamic music emotion recognition is widely studied, while the inside structure of the emotion in music remains unclear. We conduct a data observation based on the database provided by Free Music Archive (FMA), and find that emotion dynamic shows different properties under different scales. According to the data observation, we propose a new method, Double-scale Support Vector Regression (DSSVR), to dynamically recognize the music emotion. The new method decouples two scales of emotion dynamics apart, and recognizes them separately. We apply the DS-SVR to MediaEval 2015, Emotion in Music database, and achieve an outstanding performance, significantly better than the baseline provided by organizer.

引用

页码：549 / 553

页数：5

共 6 条

[1] DBLSTM-BASED MULTI-SCALE FUSION FOR DYNAMIC EMOTION PREDICTION IN MUSIC
Li, Xinxing
Tian, Jiashen
Xu, Mingxing
Ning, Yishuang
Cai, Lianhong
2016 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO (ICME), 2016,
[2] A DEEP BIDIRECTIONAL LONG SHORT-TERM MEMORY BASED MULTI-SCALE APPROACH FOR MUSIC DYNAMIC EMOTION PREDICTION
Li, Xinxing
Xianyu, Haishu
Tian, Jiashen
Chen, Wenxiao
Meng, Fanhang
Xu, Mingxing
Cai, Lianhong
2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 544 - 548
[3] LINEAR REGRESSION-BASED ADAPTATION OF MUSIC EMOTION RECOGNITION MODELS FOR PERSONALIZATION
Chen, Yu-An
Wang, Ju-Chiang
Yang, Yi-Hsuan
Chen, Homer
2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
[4] Machine Learning-based Modeling and Prediction of the Intrinsic Relationship between Human Emotion and Music
Su, Jun
Zhou, Peng
ACM TRANSACTIONS ON APPLIED PERCEPTION, 2022, 19 (03)
[5] Emotion-Based Music Recommendation from Quality Annotations and Large-Scale User-Generated Tags
Moscati, Marta
Strauss, Hannah
Jacobsen, Peer-Ole
Peintner, Andreas
Zangerle, Eva
Zentner, Marcel
Schedl, Markus
PROCEEDINGS OF THE 32ND ACM CONFERENCE ON USER MODELING, ADAPTATION AND PERSONALIZATION, UMAP 2024, 2024, : 159 - 164
[6] 3D Skeleton-Based Human Motion Prediction Using Dynamic Multi-Scale Spatiotemporal Graph Recurrent Neural Networks
Lovanshi, Mayank
Tiwari, Vivek
Jain, Swati
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2024, 8 (01): : 164 - 174

← 1 →