Margareta Ackerman: Algorithmic Songwriting
Abstract: Songwriting, the art of combining melodies and lyrics, poses new challenges to algorithmic composition. ALYSIA is a machine-learning system that learns the relationship between melodies and lyrics, and uses the resulting model to create new songs in the style of the corpus. While ALYSIA creates melodies for user-provided lyrics, another system, MABLE, creates computer generated lyrics that convey a coherent story. In addition to discussing both systems, an original song co-created by ALYSIA and music professor Joshua Palkki will be performed.
Joint work with David Loker, Chris Cassion, Rafael Perez y Perez, and Divya Singh.
Bio: Dr. Margareta Ackerman specializes in artificial intelligence, with an emphasis on computational creativity and machine learning, spanning from algorithmic composition to theoretical foundations of clustering. Her work has been featured on NBC Mach and New Scientist, and her research appears at top academic venues, including AAAI, NIPS, IJCAI, and JMLR. She received her PhD from the University of Waterloo and was a Postdoctoral Fellow at Caltech and UC San Diego, followed by two years as an Assistant Professor at Florida State University. Dr. Ackerman is currently an Assistant Professor at San Jose State University.