| home | projects | teaching | cv/resume | coursework | music |
authors: Jason A. Hockman, Matthew E. P. Davies, Juan P. Bello, Mark D. Plumbley
abstract: Time-scale transformations of audio signals have traditionally relied exclusively upon manipulations of tempo. We present a novel technique for automatic mixing and synchronization between two musical signals. In this transformation, the original signal assumes the tempo, meter, and rhythmic structure of the model signal, while the extracted downbeats and salient intra-measure infrastructure of the original are maintained.
| Crossfade Between Genres | Original | Model | Crossfade |
|---|---|---|---|
| rhumba into breakbeat with rhumba rhythm |
AUTOREPLACED
|
AUTOREPLACED
|
AUTOREPLACED
|
| Original Transformed | Original | Model | Individual |
|---|---|---|---|
| pop with reggae rhythm |
AUTOREPLACED
|
AUTOREPLACED
|
AUTOREPLACED
|
| electronic dance with 2-step rhythm |
AUTOREPLACED
|
AUTOREPLACED
|
AUTOREPLACED
|
| Comparison of Original and Transformed | Original | Model | Mixed** |
|---|---|---|---|
| electronic dance with jazz rhythm |
AUTOREPLACED
|
AUTOREPLACED
|
AUTOREPLACED
|
| rock with electronic dance rhythm |
AUTOREPLACED
|
AUTOREPLACED
|
AUTOREPLACED
|
| hip hop with rumba rhythm |
AUTOREPLACED
|
AUTOREPLACED
|
AUTOREPLACED
|
| drum & bass with rock rhythm |
AUTOREPLACED
|
AUTOREPLACED
|
AUTOREPLACED
|
| rock with drum & bass rhythm |
AUTOREPLACED
|
AUTOREPLACED
|
AUTOREPLACED
|