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

页数：5

共 50 条

[31] Multimodal Emotion Recognition using Deep Continuous Conditional Recurrent Neural Fields
Banda, Ntombikayise
Engelbrecht, Andries
2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2018,
[32] Evaluation of Gated Recurrent Neural Networks in Music Classification Tasks
Jakubik, Jan
INFORMATION SYSTEMS ARCHITECTURE AND TECHNOLOGY, PT I, 2018, 655 : 27 - 37
[33] Static Music Emotion Recognition Using Recurrent Neural Networks
Grekow, Jacek
FOUNDATIONS OF INTELLIGENT SYSTEMS (ISMIS 2020), 2020, 12117 : 150 - 160
[34] Combining Very Deep Convolutional Neural Networks and Recurrent Neural Networks for Video Classification
Kiziltepe, Rukiye Savran
Gan, John Q.
Escobar, Juan Jose
ADVANCES IN COMPUTATIONAL INTELLIGENCE, IWANN 2019, PT II, 2019, 11507 : 811 - 822
[35] Acceleration of Deep Recurrent Neural Networks with an FPGA cluster
Sun, Yuxi
Ben Ahmed, Akram
Amano, Hideharu
PROCEEDINGS OF THE 10TH INTERNATIONAL SYMPOSIUM ON HIGHLY EFFICIENT ACCELERATORS AND RECONFIGURABLE TECHNOLOGIES (HEART), 2019,
[36] Deep Recurrent Neural Networks for Nonlinear System Identification
Schuessler, Max
Muenker, Tobias
Nelles, Oliver
2019 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2019), 2019, : 448 - 454
[37] Deep Recurrent Neural Networks for Human Activity Recognition
Murad, Abdulmajid
Pyun, Jae-Young
SENSORS, 2017, 17 (11)
[38] Time series generation by recurrent neural networks
Priel, A
Kanter, I
ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE, 2003, 39 (03) : 315 - 332
[39] SINGING VOICE DETECTION WITH DEEP RECURRENT NEURAL NETWORKS
Leglaive, Simon
Hennequin, Romain
Badeau, Roland
2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 121 - 125
[40] Audio Scene Classification with Deep Recurrent Neural Networks
Huy Phan
Koch, Philipp
Katzberg, Fabrice
Maass, Marco
Mazur, Radoslaw
Mertins, Alfred
18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 3043 - 3047

← 1 2 3 4 5 →