Program
Thursday 6 June 2013
09.15 registration
09.50 opening
10.00 oral session Methodological Considerations in FMA (details)
11.40 break
12.00 oral session Computational Approaches to Specific Musical Cultures 1 (details)
13.15 1-minute poster presentations
13.30 lunch & poster session (details)
15.00 e-Humanities meeting & keynote talk by Dr. Emilia Gómez (details)
16.30 continuation poster session & drinks
Friday 7 June 2013
09.00 oral session Computational Approaches to Specific Musical Cultures 2 (details)
10.40 break
11.00 oral session Computational Models of Specific Musical Aspects (details)
12.15 lunch and posters
14.00 panel session on transcription
c.16.00 Demonstration by Naomi Sato (Sho) and Harrie Starreveld (Shakuhachi). (details)
c.16.30 closing
During the panel session, we will confront and compare various transcription methods, computational as well as traditional. Panelists are: John Ashley Burgoyne, moderator (University of Amsterdam), Kofi Agawu (Princeton University), Dániel P. Biró (University of Victoria), Olmo Cornelis (University College Ghent, Belgium), Emilia Gómez (Universitat Pompeu Fabra, Barcelona), and Barbara Titus (Utrecht University).
Keynote talk: Towards Computer-Assisted Transcription and Description of Music Recordings
By Dr. Emilia Gómez (Universitat Pompeu Fabra)
Abstract
Automatic transcription, i.e. computing a symbolic musical representation from a music recording, is one of the main research challenges in the field of sound and music computing. For monophonic music material the obtained transcription is a single musical line, usually a melody, and in polyphonic music there is an interest in transcribing the predominant melodic line. In addition to transcribing, current technologies are able to extract other musical descriptions related to tonality, rhythm or instrumentation from music recordings. Automatic description could potentially complement traditional methodologies for music analysis.
In this talk I will first present the state-of-the art on automatic transcription and description of music audio signals. I will illustrate it with our own research on tonality estimation, melodic transcription and rhythmic characterization. I will show that, although current research is promising, current algorithms are still limited in accuracy and there is a semantic gap between automatic feature extractors and expert analyses.
Finally, I will present some strategies to address these challenges by developing methods adapted to different repertoire and defining strategies to integrate expert knowledge into computational models, as a way to build systems following a “computer-assisted” paradigm.
Dr. Emilia Gómez is postdoc researcher and assistant professor at the Music Technology Group (MTG), ICT Department in Universitat Pompeu Fabra (UPF), and graduated as a Telecommunication Engineer specialised in Signal Processing at Universidad de Sevilla. In July 2006, Emilia completed her PhD in Computer Science and Digital Communication at the UPF, on the topic of Tonal Description of Music Audio Signals. Her main research interests are related to melodic and tonal description of music audio signals, computer-assisted music analysis and computational ethnomusicology.
Oral session Methodological Considerations in FMA
Thursday 6 June, 10.00-11.40
- Stephanie Weisser and Didier Demolin
The variability as a key concept: when different is the same (and vice versa) - Darrell Conklin
Folk tune classification with multiple viewpoints - Peter Van Kranenburg
On Computational Modeling in Ethnomusicological Research: Beyond the Tool - Stephanie Weisser and Olivier Lartillot
Investigating non-Western musical timbre: a need for joint approaches
Oral session Computational Approaches to Specific Musical Cultures 1
Thursday 6 June, 12.00-13.15
- André Holzapfel
Tempo in Turkish taksim improvisation - Rytis Ambrazevičius and Robertas Budrys
Traces of equidistant scale in Lithuanian traditional songs
- Olivier Lartillot, Funda Yazıcı, and Esra Mungan
A pattern-expectation, non-flattening accentuation model, empirically compared with segmentation models on traditional Turkish music
Oral session Computational Approaches to Specific Musical Cultures 2
Friday 7 June, 9.00-10.40
- Kerstin Neubarth, Colin Johnson and Darrell Conklin
Descriptive rule mining of Basque folk music
- Christina Anagnostopoulou, Mathieu Giraud and Nick Poulakis
Melodic contour representations in the analysis of children’s songs - Athanasios Fouloulis, Aggelos Pikrakis and Emilios Cambouropoulos
Traditional asymmetric rhythms: A refined model of meter induction based on asymmetric meter templates - Ewa Dahlig
Analysis of “Polish Rhythms”
Oral session Computational Models of Specific Musical Aspects
Friday 7 June, 11.00-12.15
- Emilios Cambouropoulos, Andreas Katsiavalos and Costas Tsougras
Idiom-independent harmonic pattern recognition based on a novel chord transition representation - Polina Proutskova
MIR model of vocal timbre in world’s cultures – where do we start
- Zoltán Juhász
Graph representation and a physical model of note association paradigms in different folk music cultures
Poster sessions
- Joren Six and Olmo Cornelis
Computer-assisted Transcription of Ethnic Music - Mi Tian, Dawn Black, Gyorgy Fazekas and Mark Sandler
Emotion Categorization Analysis of Chinese Cultural Revolution songs based on Audio Features and Semantic Tags - Islah Ali-Maclachlan, Münevver Köküer, Peter Jančovič, Ian Williams and Cham Athwal
Quantifying Timbral Variations in Traditional Irish Flute Playing - Klaus Frieler, Martin Pfleiderer, Jakob Abesser and Wolf-Georg Zaddach
Introducing the Jazzomat project and the MeloPy library - Enric Guaus and Jaume Ayats
The churches’ tuning - Ciril Bohak and Matija Marolt
On Finding repeating stanzas in folk song recordings
- Jan Van Balen
A Computational Study of Choruses in Early Dutch Popular Music - Maria Panteli and Hendrik Purwins
Comparative description of pitch distribution in Cypriot melodies by analysing polyphonic music recordings - Dorian Cazau, Marc Chemillier and Olivier Adam
An original optical-based retrieval system for music analysis of the marovany cithara. Applications to music information retrieval in the trance “tromba” and to aesthetic questions in musical practice - Ndubuisi Emmanuel Nnamani
Making Sense and Making Meaning in Musical Creativity: beyond purely Artistic-Aesthetic Processing in Egwu Amala - Andreas Neocleous, Maria Panteli, Nicolai Petkov and Christos N. Schizas
Tonal similarities between the Turkish, Western and Cypriot monophonic songs using machine learning techniques - Olivier Lartillot and Mondher Ayari
A comprehensive and modular framework for music transcription and analysis - Rytis Ambrazevičius
Some quantitative indexes in the study of traditional musical scales and their genesis - Gissel Velarde, Tillman Weyde and David Meredith
Using wavelet-filtering of symbolic music representation for folk tune classification
Concert
Friday 7 June, c.16.00
Demonstration by Naomi Sato on the Sho and Harrie Starreveld on Shakuhachi.
These Japanese instruments are imported from China during the Tang dynasty (600-900) and were first used in the Gaguku orchestra.
They will perform traditional- and contemporary music.
Both players are member of the Atlas Ensemble.