Sleep musicalization

Perceive your sleep as a unique musical experience!
Musicalization turns data into a genuine piece of composed music.

Try it on your Beddit data!


Sleep musicalization is a novel way of perceiving and experiencing sleep measurement data. The goal is to help users understand and analyze their sleeping patterns and eventually improve their sleep.

The musicalization process follows musicological principles when composing a melody, designing the rhythm and changes in tempo, arranging the accompaniment, and playing out the music at different levels of volume. These aspects are inspired but not dictated by the data. The result of musicalization of eight hours of sleep is an origianal piece of couple of minutes of music.

Musicalization of data provides a whole new way to experience data as a music. Music has a unique capability to invoke emotions, giving users a novel opportunity to perceive their data also as innate feelings. In the case of sleep measurements, musicalization complements the more informative, no-nonsense visual results with an emotional component towards one's own sleep.

Sleep analysis in this service is based on the Beddit sleep measurement device, which measures sleep with a thin sensor installed under the mattress. Sleep measurements are retrieved from the Beddit service, by the user's authorization, and then musicalized by composing a novel piece of music.


Tulilaulu, A., Paalasmaa, J., Waris, M. & Toivonen, H. 2012. Sleep Musicalization: Automatic Music Composition from Sleep Measurements. In The Eleventh International Symposium on Intelligent Data Analysis (IDA 2012), LNCS 7619, 392-403. Springer 2012. [PDF]

Paalasmaa, J., Waris, M., Toivonen, H., Leppäkorpi, L. & Partinen, M., 2012. Unobtrusive Online Monitoring of Sleep at Home. In 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'12. [PDF]

Press coverage

Click to show press coverage

Listen to latest samples

  • Listen

    Vonnegut: Player Piano (Venturing Outside the Beaten Path)

    Contributed by discovery

  • Listen

    Dream on, baby, dream on...

    Contributed by discovery

  • Listen

    Sleeper Agent

    Contributed by UFOPOLI

  • Listen

    Wild Trances

    Contributed by UFOPOLI

  • Listen

    Deep dreams

    Contributed by discovery

View all (29)

Tell your friends


Aurora Tulilaulu
Music composition algorithms
Joonas Paalasmaa
Sleep data analysis methods
Mikko Waris
Hannu Toivonen

Source codes

Python source codes of the musicalization implementation and this website are available.


The musicalization project has been carried out in the Discovery Research Group at the University of Helsinki.

A big thank you to the Algorithmic Data Analysis (Algodan) Centre of Excellence of the Academy of Finland, and to the Department of Computer Science of the University of Helsinki for their financial support. Thanks also to Tomi Jylhä-Ollila for help with the Kunquat system used to render the music!


Data mining and musicalization research: Prof. Hannu Toivonen. Sleep analysis methods and services: Beddit Ltd.

comments powered by Disqus