The article presents a method for segmentation of ethnomusicological field recordings. Field recordings are integral documents of folk music performances captured in the field, and typically contain performances, intertwined with interviews and commentaries. As these are live recordings, captured in non-ideal conditions, they usually contain significant background noise. We present a segmentation method that segments field recordings into individual units labelled as speech, solo singing, choir singing, and instrumentals. Classification is based on convolutional deep networks, and is augmented with a probabilistic approach for segmentation. We describe the dataset gathered for the task and the tools developed for gathering the reference annotations. We outline a deep network architecture based on residual modules for labelling short audio segments and compare it to the more standard feature based approaches, where an improvement in classification accuracy of over 10% was obtained. We also present the SeFiRe segmentation tool that incorporates the presented segmentation method.
COBISS.SI-ID: 1538109123
The discusses various groups of itinerant singers in Slovenia in the period spanning from the times of former musicians called igrci to the rise of the radio. It analyses their creativity and observes the changes in their social roles. Critically considering primary sources and unknown or overlooked testimonies, the monograph gives a new view not only on the song creativity but also on the society where it flourished. Furthermore, it illuminates the historical background and social role of some narrative songs, broadsides, the development of newspaper information and the effect of the changing transport and communication channels on this kind of creativity. Looking at the folklorisation of songs sung by itinerant singers, the monograph changes the understanding of creators and carriers of folk traditions.
COBISS.SI-ID: 304331776