SleepGAN: Towards Personalized Sleep Therapy Music

Sleep deficiency and disorders are one of the most unsolved public health challenges of modern times. Music therapy is a promising approach, offering a cheap and non-invasive solution to improve sleep quality. However, the choice of therapeutic sleep music is highly limited for users because such music needs to be specially chosen and made by sleep therapists. It could potentially lead to the inefficiency of music therapy if users get bored after listening to the same set of music repeatedly. In this paper, we take the first step towards generating personalized sleep therapy music. Firstly, through an in-depth feature analysis, we investigate the importance of various musical and acoustic features of therapy music. Grounded on our findings, we design a style transfer framework called SleepGAN which induces therapeutic features into music from different genres. We show that, compared to baselines, the music generated by SleepGAN has a higher similarity to the sleep music designed by experts.

1. INTRODUCTION

Sleep is an essential function of the human body and has a direct impact on our physical and mental well-being. Research has shown that sleep disruption and disorders have a strong causal link to major lifestyle diseases such as memory loss, obesity, diabetes, and cancer [1], [2]. Unfortunately, sleep disorders are highly prevalent in our society — studies show that nearly 40% of United Kingdom adults and roughly 50–70 million American adults experience them [3], [4]. Cognitive Behavior Therapy and pharmaceutical sleep aids are two common clinical interventions to alleviate sleep disorders. However, they are expensive and have potentially harmful side-effects [5], which has led to research in designing non-invasive, low-cost interventions to address sleep disorders.