The Sousta corpus: Beat-informed automatic transcription of traditional dance tunes

Abstract

In this paper, we present a new corpus for research in computational ethnomusicology and automatic music transcription, consisting of traditional dance tunes from Crete. This rich dataset includes audio recordings, scores transcribed by ethnomusicologists and aligned to the audio performances, and meter annotations. A second contribution of this paper is the creation of an automatic music transcription system able to support the detection of multiple pitches produced by lyra (a bowed string instrument). Furthermore, the transcription system is able to cope with deviations from standard tuning, and provides temporally quantized notes by combining the output of the multi-pitch detection stage with a state-of-the-art meter tracking algorithm. Experiments carried out for note tracking using 25ms onset tolerance reach 41.1% using information from the multi-pitch detection stage only, 54.6% when integrating beat information, and 57.9% when also supporting tuning estimation. The produced meter aligned transcriptions can be used to generate staff notation, a fact that increases the value of the system for studies in ethnomusicology.