Registration
Registration is mandatory as seating is limited (35 seats): Workshop on symbolic music processing, semantic audio, and music information retrieval: Registration
Description
When the merger of the two journals IEEE Transactions on Audio, Speech, and Language Processing and ACM Transactions on Speech and Language Processing was announced in August 2013 to be jointly published as IEEE/AES Transactions on Audio, Speech, and Language Processing starting January 2014, a new category was created in their EDICS (Editors’ Information Classification Scheme): Music information Retrieval and Music Language Processing (AUD-MIR). Of particular interest is the inclusion of “symbolic music processing, grammar-based models, music composition and improvisation, score following and music accompaniment, music annotation and metadata, and symbolic music corpora” as part of the new category. This is the first time the engineering communities have explicitly included symbolic music (scores) as a topic of study.
Semantic audio refers to the extraction of symbols or meaning from an audio stream. In this workshop, we will discuss the role of symbolic music processing in the context of semantic audio and music information retrieval. There will be presentations about the extraction of symbols from audio, and about symbolic music processing.
Guests
- Christopher Antila, CIRMMT, McGill University
- Ichiro Fujinaga, CIRMMT, McGill University
- Julie Cumming, CIRMMT, McGill University
- Johanna Devaney, School of Music, Ohio State University, USA
- Andrew Hankinson, CIRMMT, McGill University
- Jason Hockman, CIRMMT, McGill University
- Michael Mandel, Department of Computer Science and Engineering, Ohio State University, USA
- Cory McKay, Liberal and Creative Arts and Humanities, Marianopolis College
- Alexander Morgan, CIRMMT, McGill University
- Mark Sandler, School of Electronic Engineering and Computer Science, Queen Mary University London, UK
- R. Michael Winters, CIRMMT, McGill University
Schedule
- 09:00-09:10 - Ichiro Fujinaga: Symbolic processing of music: Beyond notation
- 09:10-09:30 - Johanna Devaney: Developing a symbolic music representation inspired by speech recognition
- 09:30-09:50 - Cory McKay: Combining Symbolic and Audio Musical Data: A Music Classification Perspective
- 09:50-10:10 - Jason Hockman: Computational analysis of breakbeat manipulation in Hardcore, Jungle, and Drum & Bass
- 10:10-10:30 - Michael Mandel: Extracting descriptive tags from audio using restricted Boltzmann machines
- 10:30-10:50 - Julie Cumming: ELVIS: Searching for repeated contrapuntal patterns in individual pieces and large corpora
- 10:50-11:00 - BREAK
- 11:00-11:20 - Andrew Hankinson: Aligning audio, video, and symbolic notation using MEI
- 11:20-11:40 - Christopher Antila: Using the VIS Framework: Building a New Query: Chords in Their Context
- 11:40-12:00 - Alexander Morgan: Testing Tinctoris: Comparison of the Art of Counterpoint treatise with an Interval-Succession Corpus Study
- 12:00-12:20 - R. Michael Winters: Sonification in MIR: Corpora Analysis and Music Emotion Recognition Model Matching
- 12:20-12:40 - General discussion with Mark Sandler