Learning to Generate Music With Sentiment
This addresses the challenge of guiding automated music composition for desired emotional effects, though it is incremental as it builds on existing deep learning approaches.
The paper tackles the problem of controlling deep learning models to generate music with a specific sentiment, presenting a model that achieves good prediction accuracy on a new dataset of video game soundtracks and generates music that human subjects agree has the intended sentiment, though negative pieces can be ambiguous.
Deep Learning models have shown very promising results in automatically composing polyphonic music pieces. However, it is very hard to control such models in order to guide the compositions towards a desired goal. We are interested in controlling a model to automatically generate music with a given sentiment. This paper presents a generative Deep Learning model that can be directed to compose music with a given sentiment. Besides music generation, the same model can be used for sentiment analysis of symbolic music. We evaluate the accuracy of the model in classifying sentiment of symbolic music using a new dataset of video game soundtracks. Results show that our model is able to obtain good prediction accuracy. A user study shows that human subjects agreed that the generated music has the intended sentiment, however negative pieces can be ambiguous.