Developing a Machine Learning Approach to Controlling Musical Synthesizer Parameters in Real-Time Live Performance

Musicians who play synthesizers often adjust synthesis parameters during live performance to achieve a more expressive sound. Training a computer to make automatic parameter adjustments based on examples provided by the performer frees the performer from this responsibility while maintaining an expressive sound in line with the performer’s desired aesthetic. This paper is an overview of ongoing research to explore the effectiveness of using Long Short-Term Memory (LSTM) recurrent neural networks to accomplish this task.