Music Technology Seminar (MUMT621)

Music Information Acquisition, Preservation, and Retrieval

Outline for Winter 2017

ISMIR Paper submission deadline: 21 April 2017 (topics)




HTML presentations (20 min)

  • Tim: EchoNest & Spotify
  • Zored: Musicbrainz
  • Aditya:
  • Classifiers (genre, instrument, mood, performer, composer, rhythm, beat tracking, etc.)
  • Ian: IMSLP
  • Martha: DIAMM & CMME
  • Behrad: Aria Database
  • Yaolong: McGill Billboard Dataset

Slide-based presentation I

  • Tim: FLAC
  • Ian: MPEG-4
  • Aditya: MQA & DSD
  • Zored: Ogg Vorbis
  • Yaolong: MIDI
  • Martha: MEI & MusicXML
  • Behrad: MPEG-1

Slide-based presentation II

  • Zored: Gaussian Mixture Models
  • Aditya: Boosting and bagging
  • Tim: Genetic algorithms
  • Ian: Neural networks and deep learning
  • Yaolong: HMM
  • Martha: Dynamic programming
  • Behrad: Support Vector Machines
  • Reading Week: No class

Slide-based presentation III

  • Tim: Source separation for music transcription
  • Ian: Real-time pitch tracking



Final project proposal due

  • Aditya: Noise reduction using HMM
  • Zored: Beat/tempo tracking
  • Yaolong: Harmonic analysis (symbolic)
  • Martha: Singing transcription




Special guests (1:30-3:00pm):

  • Gabriel Vigliensoni: Discovering music listening patterns in scrobble data
  • Claire Arthur: Symbolic encoding of musical and non-musical information: Sample questions and approaches
  • Behrad: Timbre recognition

Slide-based presentation IV

  • Martha: VIS and Mensural MEI
  • Tim: Self-similarity and automatic detection of musical structure
  • Aditya: Source separation using RNNs
  • Yaolong: Harmonic similarity: A possible evaluation metric for automatic harmonic analysis?


  • Berad: Brain-based timbre recognition
  • Zored: Usability and music interfaces
  • Ian: Music generation using neural networks

Final project bibliography due

Final project presentation

  • Tim: Geometrical model for music segmentation
  • Ian: Monophonic (and polyphonic) automatic instrument identification using neural networks
  • Zored: Web activity-based music recommendation project
  • Aditya: Noise deduction with deep learning
  • Martha: Study of vertical sonorities of music encoded in Mensural MEI
  • Yaolong: Automatic harmonic analysis
  • Behrad: Musical instrument recognition using modulation power spectra


Assignment #1 (Due 01/19) 4%

Subscribe to the ISMIR Google Community Announcements:!forum/community

HTML presentation of existing music databases. Describe the content, history, and uses of the database (20 min.):

Assignment #2 (Due 02/02) 6% Slide-based presentation I (20 min.)
  • Slide-based presentation of MPEG formats (MPEG1, MPEG4, MPEG7, MPEG21), Ogg Vorbis / Opus, symbolic formats (MEI, MusicXML, etc.), or audio compression techniques
  • Annotated bibliography HTML page (use links, if avialable) (Chicago style, Documentation II: Author-Date References, 16th edition)

Assignment #3 (Due 2/16) 10% Slide-based presentation II (20 min.)
  • Slide-based presentation of review of topics related to classifiers, e.g.: Neural Networks, Support Vector Machines, Gaussian Mixture Models, Hidden Markov Models, AdaBoost, or Dynamic Programming; include music information retrieval applications.
  • Written summary (2–3 pages) with an annontated bibliography (Chicago style, Documentation II: Author-Date References,16th edition)

Assignment #4 (Due 03/09) 10% Slide-based presentation III (20 min.)
  • Slide-based presentation on topics of trascription, recognition, annotation, and classification. It may include general review of transcription systems (monophonic, polyphonic, separation): Beat-box transcription, singing transcription, beat/tempo tracking using audio, beat/tempo tracking using MIDI, blackboard polyphonic transcription, Goto's works, historical overviews, real-time pitch tracking, piano music transcription, timbre recognition, genre classification, review of a component of jMIR.
  • Written summary (2–3 pages) with an extensive bibliography (Chicago style, Documentation II: Author-Date References, 16th edition)

Assignment #5 (Due 03/16) 5%
  • Final project proposal (1–2 pages with a partial bibliography in Chicago style, Documentation II: Author-Date References, 16th edition; inlcude sub goals)

Assignment #6 (Due 03/30) 10% Slide-based presentation IV (20 min.)
  • Slide-based presentation on review of topics related to similarity, query systems, recommendation / playlist systems, or exploratory research on topics related to your final project.
  • Written summary (2–3 pages) with an extensive bibliography (Chicago style, Documentation II: Author-Date References: 16th edition)

Assignment #7 (Due 04/06) 5%

  • Final project presentation (10 min.)
  • Final project abstract (1 page) with a full bibliography (Chicago style, Documentation II: Author-Date References, 16th edition)

Final project (Due 05/05) 40%
  • Software project with description (2–3 pages) (Reposit on Github)


  • Research paper (5–10 pages) (ISMIR style)

Reading list


  • Zored Ahmer
  • Timothy De Reuse
  • Yaolong Ju
  • Behrad Madahi
  • Ian Marci
  • Martha Thomae
  • Aditya Tirumala Bukkapatnam
Created: 2004-01-02 Modified: Ichiro Fujinaga <
McGill Crest