Hello and welcome to the Paper of the Day (Po’D): Computational Ethnomusicology Edition. Today’s paper is a contribution that is quite relevant to our project DaCaRyH.
G. Tzanetakis, A. Kapur, W. A. Schloss, and M. Wright, “Computational Ethnomusicology,” Journal of Interdisciplinary Music Studies, vol. 1 (2), pp. 1-24, 2007.
Tzanetakis et al. provide an overview of “Computational Ethnomusicology,” which they define: “the design, development and usage of computer tools that have the potential to assist in ethnomusicological research.” They focus in particular on the potential contributions of “music information retrieval” (MIR) research. Two advantages they highlight are accuracy in tasks that are difficult by hand (e.g., “the timing of music”) and scalability (e.g., finding patterns in large datasets).
They review past work in applying computers to analysing music transcriptions, including learning grammars of tabla, statistics of pitches and pattern searching in gamelan music transcriptions, and clustering of melodic characteristics in folk songs from Germany and China. Another application of the computer is for automatic transcription, which is not necessarily common practice notation. They review fascinating work in using sound synthesis “in the field” to study how particular groups conceive of pitches and scales. And they review some of the work occurring in MIR (up to that point).
This article also presents some guidelines for doing computational ethnomusicology. These include:
- collaborate across disciplines, computer science and musicology
- use large collections
- customise the algorithms/systems to the style under investigation
This article appears in the first issue of the Journal of Interdisciplinary Music Studies, which now appears defunct. However, other articles published during its brief existence look quite interesting:
Measuring musical rhythm similarity: Transformation versus feature-based methods
Godfried T. Toussaint, Luke Matthews, Malcolm Campbell, and Naor Brown
Imitation of animal sound patterns in Serbian folk music
Milena Petrovic and Nenad Ljubinkovic
Drawing a parallel between the gaida (bagpipe) and the Zonaradikos line dance through statistics
Haris Sarris, Angelos Velegrakis and Tassos Kolydas
Collaboration perspectives for folk song research and music information retrieval: The indispensable role of computational musicology
Peter van Kranenburg, Jörg Garbers, Anja Volk, Frans Wiering, Louis P. Grijp, and Remco C. Veltkamp
Style-Independent Computer-Assisted Exploratory Analysis of Large Music Collections
Cory McKay, Ichiro Fujinaga