zwei Microsoft-Forscher (Dan Morris, Sumit Basu) und ein Student (Ian Simon) experimentieren mit einem neuartigen Musikprogramm namens MySong herum. Die Idee ist einfach: Man singt in ein Mikro und das Programm versucht, die passende Musik dazu zu generieren, die man von der Grundrichtung her vorgeben kann.
Creating music with MySong begins with recording a vocal melody; the user presses a „record“? button and sings along with acomputer-generated beat at a user-specified tempo. When the user stops singing, MySong immediately generates a chord sequence that is appropriate for the performed melody. The user can listen to these chords as a piano accompaniment, along with the recorded vocal audio, using familiar „play“? and „stop“? buttons. Because there are many accompaniments that are appropriate for a given melody, MySong allows the user to adjust the chords chosen by the system using parameters that are intuitive to non-musicians. One slider allows the user to make the accompaniment happier or sadder; this slider is called the „happy factor“?. Another slider, the „jazz factor“?, allows the user to bias the system toward chord patterns that are more traditional or more adventurous. Regeneration of chord sequences is immediate when adjusting these sliders, so users can rapidly explore a variety of accompaniments (Quelle, pdf)
Crazy? Hört sich so an, aber hören und hören sind zweierlei. Es hört sich nämlich ziemlich gut an, was dabei herauskommt:
Neue Stellenangebote
|
Mitarbeiter*in (m/w/d) für Social Media, Öffentlichkeitsarbeit und Städtepartnerschaft (m/w/d) meinestadt.de in Sachsenheim |
|
|
Content Creator / Social Media / Marketing (m/w/d) Delitzscher Schokoladenfabrik GmbH in Delitzsch |
|
|
Content Creator / Social Media / Marketing (m/w/d) Halloren Schokoladenfabrik AG in Delitzsch |
The program works by identifying the 12 standard musical notes in a sung melody, and then feeding those notes into an algorithm that has been trained by listening to 300 songs in varying genres and learning how to identify chords and melody fragments that work well together. The result is a series of musical accompaniments that users can adjust via sliders for „happy factor“ and „jazz factor.“
Im Papier MySong: Automatic Accompaniment Generation for Vocal Melodies (.pdf) wird das Verfahren genauer beschrieben.
Read Write Web hat völlig Recht, diese Anwendung könnte online einen großen Spaß versprechen!
You can draw your own conclusions, but we were very impressed and hope that someone brings the MySong technology to a web browser in the future. We have a feeling this thing would kill as a Facebook or OpenSocial application.
