Project DetailsThe work deals with converting a sound segment of the humming into a sound segment of a selected musical instrument. This conversion relies on established and proven models developed on the basis of deep network algorithms in combination with digital signal processing methods and techniques.
The two main models we worked with are DDSP, developed by google, and the other model, that was inspired by it was developed by Dr. Lior Wolf from Tel Aviv University. Later we will expand and detail these models and how they work.
We note that originally these models are intended for converting a section of one musical instrument to a section of another musical instrument and do not support converting the hum to a section of a musical instrument (and vice versa). Hence, our main goal in this project was to enable the algorithm to successfully convert a hum segment into a segment of a musical instrument selected by the user, thereby improving the generalizability of the existing model and allowing a good basis for further work in the same direction.
