Automated Segmentation of Folk Song Field Recordings

Conference: Sprachkommunikation - Beiträge zur 10. ITG-Fachtagung
09/26/2012 - 09/28/2012 at Braunschweig, Deutschland

Proceedings: Sprachkommunikation

Pages: 4Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Müller, Meinard; Grosche, Peter (Saarland University and MPI Informatik, 66123 Saarbrücken, Germany)

In this paper, we introduce an automated procedure for segmenting a given folk song field recording into its constituent stanzas. One challenge arises from the fact that these recordings are performed by elderly non-professional singers under poor recording conditions such that the constituent stanzas may reveal significant temporal and spectral deviations. Unlike a previously described segmentation approach that relies on a manually transcribed reference stanza, we introduce a reference-free segmentation procedure, which is driven by an audio thumbnailing procedure in combination with enhanced similarity matrices. Our experiments on a Dutch folk song collection show that our segmentation results are comparable to the ones obtained by the reference-based method.