musicinformationretrieval.com is a collection of instructional materials for music information retrieval (MIR). These materials contain a mix of casual conversation, technical discussion, and Python code.
These pages, including the one you're reading, are authored using Jupyter notebooks. They are statically hosted using GitHub Pages. The GitHub repository is found here: stevetjoa/stanford-mir.
This material is used during the annual Summer Workshop on Music Information Retrieval at CCRMA, Stanford University. Click here for workshop description and registration.
This site is maintained by Steve Tjoa. For questions, please email steve@stevetjoa.com. Do you have any feedback? Did you find errors or typos? Are you a teacher or researcher and would like to collaborate? Please let me know.
"You guys put together a really fantastic workshop."
"I really enjoyed the workshop. It was very well executed and exceeded my expectations in the scope of material covered."
"Well planned and thoughtful."
"My own participation in this course started me down a path that I couldn't have foreseen and landed me several music tech jobs with startups and now an established company. Highly recommend this workshop!"
"It was a fun week. I learned a lot, and met some very cool people. That week helped shape where I am now in a couple of ways."
"I'd take this course again, if my schedule permits. It's a very cool introduction to Information Retrieval and Machine Learning through Music, for sure. Definitely recommended!"
"This was a great introduction to the field of MIR which I am now applying to human studies of the cognitive neuroscience of music."
"This is a fantastic workshop. I'd also love to take it again when I find the time."
The MIR workshop teaches the underlying ideas, approaches, technologies, and practical design of intelligent audio systems using MIR algorithms. It lasts five full days, Monday through Friday. It was founded by Jay LeBoeuf (Real Industry, CCRMA consulting professor) in 2008.
The workshop is intended for students, researchers, and industry audio engineers who are unfamiliar with the field of music information retrieval (MIR). We demonstrate the technologies enabled by signal processing and machine learning. Lectures cover topics such as low-level feature extraction, higher-level features such as chord estimations, audio similarity clustering, search and retrieval, music synchronization, signal decomposition, rhythm and tempo, and design and evaluation of classification systems. Our goal is to make these interdisciplinary technologies and complex algorithms approachable.
Knowledge of basic digital audio principles is recommended. Experience with a scripting language such as Python or Matlab is desired. Students are encouraged to bring their own audio source material for course labs and demonstrations.
The workshop consists of half-day lectures, half-day supervised lab sessions, demonstrations, and discussions. Labs allow students to design basic "intelligent audio systems" leveraging existing MIR toolboxes, programming environments, and applications. Labs include creation and evaluation of basic instrument recognition, transcription, and real-time audio analysis systems.
Links redirect to that year's wiki page.