The songsmith story, or how a small-town hidden Markov model dade it to the big time

Sumit Basu, Dan Morris, Ian SimonThe Journal of the Acoustical Society of America 2014 · DOI

Abstract

It all started with a simple idea—that perhaps lead sheets could be predicted from melodies, at least within a few options for each bar. Early experiments with conventional models led to compelling results, and by designing some user interactions along with an augmented model, we were able to create a potent tool with a range of options, from an automated backing band for musical novices to a flexible musical scratchpad for songwriters. The academic papers on the method and tool led to an unexpected level of external interest, so we decided to make a product for consumers, thus was Songsmith born. What came next surprised us all—from internet parodies to stock market melodies to over 600 000 downloads and a second life in music education, Songsmith has been an amazing lesson in what happens when research and the real world collide, sometimes with unintended consequences. In this talk, I’ll take you through our story, from the technical beginnings to the Internet-sized spectacle to the vast opportunities in future work, sharing with you the laughter, the heartbreak, the tears, and the joy of bringing Songsmith to the world.
BibTeX
@article{basu2014songsmith,
  author = {Sumit Basu and Dan Morris and Ian Simon},
  title = {{The songsmith story, or how a small-town hidden Markov model dade it to the big time}},
  journal = {The Journal of the Acoustical Society of America},
  year = {2014},
  doi = {10.1121/1.4877851},
}

Loading related content...

Figure