Monophonic Music Generation With a Given Emotion Using Conditional Variational Autoencoder
Open Access
- 17 September 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 129088-129101
Abstract
The rapid increase in the importance of human-machine interaction and the accelerating pace of life pose various challenges for the creators of digital environments. Continuous improvement of human-machine interaction requires precise modeling of the physical and emotional state of people. By implementing emotional intelligence in machines, robots are expected not only to recognize and track emotions when interacting with humans, but also to respond and behave appropriately. The machine should match its reaction to the mood of the user as precisely as possible. Music generation with a given emotion can be a good start to fulfilling such a requirement. This article presents the process of building a system generating music content of a specified emotion. As the emotion labels, four basic emotions: happy, angry, sad, relaxed, corresponding to the four quarters of Russell’s model, were used. Conditional variational autoencoder using a recurrent neural network for sequence processing was used as a generative model. The obtained results in the form of the generated music examples with a specific emotion are convincing in their structure and sound. The generated examples were evaluated with two methods, in the first using metrics for comparison with the training set and in the second using expert annotation.Keywords
Funding Information
- Ministry of Science and Higher Education through Bialystok University of Technology (WZ/WI-IIT/2/2020)
This publication has 32 references indexed in Scilit:
- Labeling data and developing supervised framework for hindi music mood analysisJournal of Intelligent Information Systems, 2016
- Audio Features Dedicated to the Detection of Four Basic Emotions2015
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- Machine Recognition of Music EmotionACM Transactions on Intelligent Systems and Technology, 2012
- Towards Affective-Psychophysiological Foundations for Music ProductionLecture Notes in Computer Science, 2007
- Automatic mood detection and tracking of music audio signalsIEEE Transactions on Audio, Speech, and Language Processing, 2005
- Emotion perceived and emotion felt: Same or different?Musicae Scientiae, 2001
- A circumplex model of affect.Journal of Personality and Social Psychology, 1980
- The significance probability of the smirnov two-sample testArkiv för Matematik, 1958
- Coefficient Alpha and the Internal Structure of TestsPsychometrika, 1951