addressalign-toparrow-leftarrow-rightbackbellblockcalendarcameraccwcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-checkcircle-with-crosscircle-with-pluscrossdots-three-verticaleditemptyheartexporteye-with-lineeyefacebookfolderfullheartglobegmailgooglegroupshelp-with-circleimageimagesinstagramFill 1linklocation-pinm-swarmSearchmailmessagesminusmoremuplabelShape 3 + Rectangle 1ShapeoutlookpersonJoin Group on CardStartprice-ribbonShapeShapeShapeShapeImported LayersImported LayersImported Layersshieldstartickettrashtriangle-downtriangle-uptwitteruserwarningyahoo

Music Information Retrieval with Steve Tjoa

Music information retrieval (MIR) is an interdisciplinary field bridging the domains of statistics, signal processing, machine learning, musicology, biology, and more. MIR algorithms allow a computer to make sense of audio data in order to bridge the semantic gap between high-level musical information — e.g. tempo, key, pitch, instrumentation, chord progression, genre, song structure — and low-level audio data. In this talk, we will survey common research problems in MIR, including music fingerprinting, transcription, classification, and recommendation, and recently proposed solutions in the research literature. The talk will contain both a high-level overview as well as concrete examples of implementing MIR algorithms in Python using the IPython notebook. We will discuss concrete elements of prototyping an MIR system including data visualization, open-source tools, and evaluation.

Generously sponsored by O'Reilly Media. Special discount to Strata Conference  + Hadoop World in NYC this October for SF Data Science Members! Visit for details. 

About Steve Tjoa
Steve Tjoa ( is a researcher and engineer in the areas of signal processing and machine learning for music information retrieval (MIR). He currently works on the MIR team at Humtap in San Francisco. Before that, he worked on content-based audio recognition and recommendation as an NSF-sponsored postdoctoral fellow at iZotope and Imagine Research (acquired by iZotope). He has also worked as a consultant in the areas of audio/image signal processing, machine learning, and information retrieval.

Since 2011, he has co-instructed the annual summer workshop on MIR at the Center for Computer Research in Music and Acoustics (CCRMA) at Stanford University.

Join or login to comment.

  • Molly L.

    Reposting the video link to keep it at the top of the list:

    1 · October 2, 2014

  • Pras

    Ha the link for the video been taken down already ? I was hoping to review it again.

    September 21, 2014

  • Michael M.

    Hi! Will the video be posted soon? Thanks!


    September 18, 2014

    • Molly L.

      Just posted it above.

      October 1, 2014

  • Kunal

    I was wondering if video of this presentation is going to be available or not.


    September 22, 2014

  • Molly L.

    Hi Everyone - sorry for the delay. Here is the recording from Steve's talk!

    1 · October 1, 2014

  • Seemant K

    Really great presentation, Steve. Thank you for sharing your knowledge!

    September 17, 2014

  • Steve T.

    If it allows me to vote on my own talk, I intend to do so. FIVE STARS

    6 · September 17, 2014

  • Ken P.

    Steve introduced a dazzlingly complex subject with clear explanations and humor, and some pretty good violin solos. People kept saying "he's raised the bar on meetup presentations." He has.

    1 · September 17, 2014

  • Benjamin D.

    Great meetup. Thanks Steve

    September 16, 2014

  • Romy I.

    This was really fun! I enjoyed how the speaker & other data scientists were patient with me even though I didn't understand a lot of the key concepts at first since they were so unfamiliar. It was also cool seeing these sophisticated ideas broken down into steps with the essential library that a beginning python programmer like me could potentially work with and play with. at the same time, It was nice seeing the full on academic background that made tjoa cool like he is today instead of watering down a rich field into easily digestible business development powerpoint bullet points. I got the best of both worlds! and a starting point for horsing around in python.

    September 16, 2014

  • Deepak G.

    Hi the door is locked, is there a code? Thanks

    September 16, 2014

  • Pras

    Steve - I am forced to drop out tonight due to a late meeting that wouldn't allow me to make it on time. Feel free to use my slot reserved for (Pras Chaudhuri). Enjoy.

    September 16, 2014

    • Molly L.

      Hi Pras, please update your RSVP and it will admit someone from the waitlist. Thanks!

      September 16, 2014

  • Steve E.

    I'm on the wait list - should I come out anyway or is it definitely filled for tonight?

    September 16, 2014

    • Christian H.

      Same question here...

      September 16, 2014

    • Molly L.

      We will do our best, but we have a limit on the number of people allowed in. We have usually been able to let everyone in, but can't guarantee it.

      September 16, 2014

  • Marcus N.

    Will the talk start at 630 or be preceded by networking?

    September 16, 2014

    • Molly L.

      The talk will begin at 7 PM

      1 · September 16, 2014

  • Molly L.

    We will be recording the talk and will share the link here tomorrow or Thursday.

    2 · September 16, 2014

  • David B.

    Will this talk will be recorded?

    September 15, 2014

  • Pras

    Thanks, Steve. Love to know if we could explore possible similarity in approach to extracting metadata for video as well. Realizing I am pushing at the session scope.

    September 15, 2014

  • Emer N.

    Hi Steve, First and foremost, definitely look forward to your presentation. So I would like to learn more about what
    you've discovered at present - with machine learning integration of music retrieval as well as data visualization - err...combination of all three?

    Lastly, will you be demo'ing Humtap? Really cool app... Thanks!

    2 · September 15, 2014

  • Steve T.

    Hi! Steve here, tomorrow's speaker. If you have any last-minute requests for things you would like me to include related to MIR, feel free to comment here. If you see a topic you like from an existing comment, vote with the "like" button.

    September 15, 2014

    • Marcus N.

      Steve, one question/request in the area of audio recognition I have is: is there a robust solution for recognizing the beginning and end of the vocals in a song, to allow for automatically estimating the length of intro and outro of a song?

      September 15, 2014

  • Andrew B.

    Interested in music retrieval

    September 12, 2014

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy