Music Technology Seminar (MUMT621)

Music Information Acquisition, Preservation, and Retrieval


Outline for Winter 2021

ISMIR Abstract submission deadline:  8 May 2021 (topics)

01/12  
01/19

 

01/26

Slide or HTML presentation I (15 min)

  • Kasey: Spatial audio datasets 
  • Jake:  Databases for general sound events and spatial audio 
  • Junhao: IDMT-SMT-Guitar dataset
  • Gavin: IMSLP/Petrucci Library
02/02
  • Classifiers (genre, instrument, mood, performer, composer, rhythm, beat tracking, etc.)

Slide or HTML presentation I

  • Aybar: Spotify and the comparison to other music streaming services
  • Wan Yi: AIST Dance Video Database
  • Gabriel: MusicNet
  • Yinan: Free Music Archive
  • Shayan: Soundcloud and other online free music distribution platforms (e.g., Bandcamp, Audiomack, and Jamendo)
  • Sevag: The Harmonix Set 
  • Tara: McGill Billboard Project
02/09

Slide presentation II (15 min)

  • Gavin: Presevation issues in libraries and archives
  • Shayan: MP3: Perceptual coding for lossy compression
  • Kasey: MIDI / SMF
  • Jake: File formats and compression for spatial audio
  • Junhao: AIFF
02/16

Slide-based presentation II 

  • Wan Yi: MusicXML
  • Tara: MEI (Music Encoding Initiative)
  • Yinan: MPEG4 (AAC)
  • Aybar: FLAC and MPEG-H 3D audio
  • Sevag: Opus audio codec
02/23

Slide-based presentation III (15 min)

  • Gavin: Decesion Trees
  • Tara: Cluster Analysis
  • Kasey: HMM
  • Jake: Dimension Reduction for Feature Extraction (PCA, t-SNE, UMAP)
03/02
  • Study Week: No class

 

03/09

Slide-based presentation III 

  • Sevag: Dynamic Programming
  • Shayan: GMM
  • Wan Yi: Neural Networks
  • Yinan: Recurrent Neural Networks
  • Aybar: Deep Learning and its applications to audio analysis
  • Junhao: SVM
03/16

Slide-based presentation IV (15 min)

  • Shayan: Music audio source separation
  • Tara: Musical motion capture data analysis
  • Gavin: jMIR: ACE XML 2.0
  • Kasey: Beat/tempo tracking using MIDI

03/23

Slide-based presentation IV 

  • Jake: Environment sound classification
  • Junhao: Guitar transcriptions
  • Aybar: Reverberation identification methods
  • Wan Yi: Video and audio beat tracking
  • Yinan: Emotion recognition
  • Sevag: Pitch tracking

03/30

Evaluation of MIR: MIREX

Slide-based presentation V (10–15 min)

  • Gavin: Introduction to the new Library of Congress controlled vocabularies for music scores
  • Tara: Retrieving music-evoked brain activity
  • Kasey: Score following
  • Wan Yi: Dance movement analysis
  • Shayan: Evaluation of sound source separation

Submit a draft of the final project proposal (1–2 pages) plus a partial bibliography

04/06

Slide-based presentation V 

  • Aybar: Dereverberation
  • Yinan: Music mood detection using DNN
  • Sevag: State-of-the-art beat tracking
  • Jake: Conditional Neural Networks
  • Junhao: Instrument playing technique detection

 

04/13

 

Final project presentations (8 min)

  • Jake: Idiomatic feature set and neural network design for acoustic classification
  • Shayan: Phase-based harmonic/percussive separation
  • Tara: Predicting skill level from motion capture data
  • Kasey: Antescofo and Metronaut: Context and evaluation
  • Gavin: Classifying diversity: Composer identities and the composer diversity database
  • Yinan: Multimodal music emotion recognition using convolutional neural network
  • Junhao: Electric guitar transcription with excitation style classification
  • Sevag: headbang.py
  • Wan Yi: Dance movement segmentation
  • Aybar: Reverb matching systems
Submit the final project proposal (1–2 pages) with a full bibliography

Assignments

Assignment #1 (Due 01/26) 4%

Subscribe to the ISMIR Google Community Announcements: https://groups.google.com/a/ismir.net/forum/#!forum/community

HTML- or slide-based presentation of existing music databases. Describe the content, history, and uses of the database, highlighting any research conducted with it. (15 min):


Assignment #2 (Due 02/09) 6% Slide-based presentation II (15 min)
  • Slide-based presentation of audio file formats: AIFF, WAV/WMA, Opus (Ogg Vorbis), Lossless formats (FLAC), etc.; MPEG formats: MPEG1 (MP3), MPEG4 (AAC), MPEG7, & MPEG21; symbolic fille formats: MEI, MusicXML, MIDI, etc., or audio compression techniques
  • Annotated bibliography (short summary and evaluation) as an HTML page or a PDF file (use links, if avialable) (Chicago style, Documentation II: Author-Date References, 17th edition)

Assignment #3 (Due 2/23) 10% Slide-based presentation III (15 min)
  • Slide-based presentation of review of topics related to classifiers, e.g.: Feature extraction (audio or symbolic), Neural Networks (shallow, deep, CNN, RNN, LSTM, etc.), Support Vector Machines, Decision Tree (ID3), Random Forest, Gradient Boosting, Gaussian Mixture Models, Hidden Markov Models, AdaBoost, and Dynamic Programming; include music information retrieval applications.
  • Written summary (2–3 pages, single spaced, single or double columns, 1" margins) with an annotated bibliography (Chicago style, Documentation II: Author-Date References,17th edition)

Assignment #4 (Due 03/16) 10% Slide-based presentation IV (15 min)
  • Slide-based presentation on topics of transcription, 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, etc.
  • Written summary (2–3 pages) with an extensive bibliography (Chicago style, Documentation II: Author-Date References, 17th edition), which should include practically all significant papers on the subject. You do not need to annotated them but should reference each one of them in the summary paper.

Assignment #5 (Due 03/30) 10% Slide-based presentation V (10–15 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) plus an extensive bibliography (Chicago style, Documentation II: Author-Date References: 17th edition)

Assignment #6 (Due 03/30) 5%

  • A draft of the final project proposal (1–2 pages), including subgoals, plus a partial bibliography (Chicago style, Documentation II: Author-Date References, 17th edition)

Assignment #7 (Due 04/13) 5%

  • Final project presentation describing what you intend to do (5–8 min)
  • Final project proposal (1–2 pages) with the title and a full bibliography (Chicago style, Documentation II: Author-Date References, 17th edition)

Final project (Due 05/04) 40%
  • Software project with description (2–3 pages) (Repository on Github)

or

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

Improving writing skills for McGill graduate students: Graphos

Reading list

Participants

  • Jake Arujo-Simon
  • Aybar Aydin
  • Gavin Goodwin
  • Sevag Hanssian
  • Tara Henechowicz
  • Gabriel Lavoie Viau
  • Wan Yi Lin
  • Shayan Mozzaffari
  • Kasey Pocius
  • Junhao Wang
  • Yinan Zhou

Class Discord

Created: 2004-01-02 Modified: Ichiro Fujinaga <
McGill Crest