Music Information Retrieval

Size: px

Start display at page:

Download "Music Information Retrieval"

Derek Craig
5 years ago
Views:

1 Music Information Retrieval Informative Experiences in Computation and the Archive David De David De

2 Four quadrants Big Data Scientific Computing Machine Learning Automation More machines Distributed Computation Conventional Digital Scholarship Social Cybersecurity Citizen Science Science 2.0 Computation Networks Web 2.0 More

3 Social Machines Real life is and must be full of all kinds of social constraint the very processes from which society arises. Computers can help if we use them to create abstract social machines on the Web: processes in which the people do the creative work and the machine does the administration... The stage is set for an evolutionary growth of new social engines. The ability to create new forms of social process would be given to the world at large, and development would be rapid. Berners-Lee, Weaving the Web, 1999 (pp )

5 Defining Music Information Retrieval? n Music Information Retrieval (MIR) is the process of searching for, and finding, music objects, or parts of music objects, via a query framed musically and/or in musical terms n Music Objects: Scores, Parts, Recordings (WAV, MP3, etc.), etc. n Musically framed query: Singing, Humming, Keyboard, Notation-based, MIDI file, Sound file, etc. n Musical terms: Genre, Style, Tempo, etc.

6 What is MIR? n Born ca s in IR research n Major recent growth precipitated by advent of networked digital music collections n Informed by multiple disciplines and literatures n ISMIR started in 2000

7 Music representation is VERY heterogeneous!

8 MIREX Overview n Began as MIREX in 2005 n Tasks defined by community debate n Data sets collected and/or donated n Participants submit code to IMIRSEL n Code rarely works first try J n Huge labour consumption getting programmes to work n Meet at ISMIR to discuss results n Non-consumptive research

2018 Tasks Audio Beat Tracking Audio Chord Estimation Audio Cover Song Identification Audio Downbeat Estimation Audio Fingerprinting Audio Key Detection Audio Onset Detection Audio Tempo Estimation

9 2018 Tasks Audio Beat Tracking Audio Chord Estimation Audio Cover Song Identification Audio Downbeat Estimation Audio Fingerprinting Audio Key Detection Audio Onset Detection Audio Tempo Estimation Automatic Lyrics-to-Audio Alignment Drum Transcription Multiple Fundamental Frequency Estimation & Tracking Real-time Audio to Score Alignment (Score Following) Patterns for Prediction Set List Identification Audio Melody Extraction Music and/or Speech Detection

10 2017 Results

11 SALAMI 23,000 hours of recorded music Digital Music Collections Music Information Retrieval Community Student-sourced ground truth Community Software Supercomputer Linked Data Repositories

12 salami.music.mcgill.ca Jordan B. L. Smith, J. Ashley Burgoyne, Ichiro Fujinaga, David De Roure, and J. Stephen Downie Design and creation of a large-scale database of structural annotations. In Proceedings of the International Society for Music Information Retrieval Conference, Miami, FL,

13 Ashley Burgoyne

15 The world of music has changed for good in the digital age. This revolution must be matched by a transformation of the means by which music is studied. While preserving the best traditional values and practices of musicology we must take advantage of the immense opportunities offered by music information retrieval Three parallel musicological investigations 1. 16th-century vocal and lute music 2. Wagner's leitmotifs 3. Musicology of the social media Ensure sustainability and repeatability by embedding the above research activities in a framework enabling data, methods and results to be shared permanently as Linked Data Enhance Semantic Web workflow description methods for musicology

16 Carolin Rindfleisch

18 Digital Music Objects David De AES, Berlin, May

21 Discussion points 1. Construction and use of the archive seen as a social machine 2. Computational methods and linked data used in Search and Discovery 3. Adding value through use 4. Increasingly working with born digital content, use of provenance

Thanks to J. Stephen Downie (Illinois), Tim Crawford (Goldsmiths), Mark Sandler (QMUL) and all our colleagues david.deroure@oerc.ox.

22 Thanks to J. Stephen Downie (Illinois), Tim Crawford (Goldsmiths), Mark Sandler (QMUL) and all our colleagues

SIMSSA DB: A Database for Computational Musicological Research

SIMSSA DB: A Database for Computational Musicological Research Cory McKay Marianopolis College 2018 International Association of Music Libraries, Archives and Documentation Centres International Congress,