ON-LINE CONTINUOUS-TIME MUSIC MOOD REGRESSION WITH DEEP RECURRENT NEURAL NETWORKS

被引：0
作者：
Weninger, Felix [1 ]
Eyben, Florian [1 ]
Schuller, Bjoern [1 ]
机构：
[1] Tech Univ Munich, MMK, Machine Intelligence & Signal Proc Grp, D-80290 Munich, Germany
来源：
2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2014年
关键词：
music information retrieval; emotion recognition; recurrent neural networks;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
This paper proposes a novel machine learning approach for the task of on-line continuous-time music mood regression, i.e., low-latency prediction of the time-varying arousal and valence in musical pieces. On the front-end, a large set of segmental acoustic features is extracted to model short-term variations. Then, multi-variate regression is performed by deep recurrent neural networks to model longer-range context and capture the time-varying emotional profile of musical pieces appropriately. Evaluation is done on the 2013 MediaEval Challenge corpus consisting of 1 000 pieces annotated in continous time and continuous arousal and valence by crowd-sourcing. In the result, recurrent neural networks outperform SVR and feedforward neural networks both in continuous-time and static music mood regression, and achieve an R-2 of up to .70 and .50 with arousal and valence annotations.
引用
收藏
页数：5
相关论文
共 50 条
  • [41] FPGA implementation of a Recurrent Neural Fuzzy Network for on-line temperature control
    Juang, CF
    Hsu, CH
    Liou, YC
    2005 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), VOLS 1-6, CONFERENCE PROCEEDINGS, 2005, : 3043 - 3046
  • [42] Learning to Learn and Compositionality with Deep Recurrent Neural Networks
    de Freitas, Nando
    KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, : 3 - 3
  • [43] Time Series Generation by Recurrent Neural Networks
    A. Priel
    I. Kanter
    Annals of Mathematics and Artificial Intelligence, 2003, 39 : 315 - 332
  • [44] Statistical Regression Models for Noise Robust F0 Estimation Using Recurrent Deep Neural Networks
    Kato, Akihiro
    Kinnunen, Tomi H.
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2019, 27 (12) : 2336 - 2349
  • [45] Recurrent Convolutional Deep Neural Networks for Modeling Time-Resolved Wildfire Spread Behavior
    Burge, John
    Bonanni, Matthew R.
    Hu, R. Lily
    Ihme, Matthias
    FIRE TECHNOLOGY, 2023, 59 (06) : 3327 - 3354
  • [46] Recurrent Convolutional Deep Neural Networks for Modeling Time-Resolved Wildfire Spread Behavior
    John Burge
    Matthew R. Bonanni
    R. Lily Hu
    Matthias Ihme
    Fire Technology, 2023, 59 : 3327 - 3354
  • [47] Continuous Attractors of Lotka-Volterra Recurrent Neural Networks
    Zhang, Haixian
    Yu, Jiali
    Yi, Zhang
    ARTIFICIAL NEURAL NETWORKS - ICANN 2009, PT I, 2009, 5768 : 287 - +
  • [48] On the improvement of the real time recurrent learning algorithm for recurrent neural networks
    Mak, MW
    Ku, KW
    Lu, YL
    NEUROCOMPUTING, 1999, 24 (1-3) : 13 - 36
  • [49] Binary Emotion Classification of Music Using Deep Neural Networks
    Revathy, V. R.
    Pillai, Anitha S.
    PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING AND PATTERN RECOGNITION (SOCPAR 2021), 2022, 417 : 484 - 492
  • [50] Music emotion recognition using recurrent neural networks and pretrained models
    Jacek Grekow
    Journal of Intelligent Information Systems, 2021, 57 : 531 - 546
12345