Abstract
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.
Highlights
Ethnomusicological field recordings are recordings gathered in the field, capturing folk music performances, usually intertwined with interviews with performers or commentaries by the folklorist
While there is a large number of published works dedicated to speech/music classification, they mostly deal with broadcast recordings, where their per-frame classification accuracies reach over 90%
We presented a method for segmentation of field recordings into individual units
Summary
Ethnomusicological field recordings are recordings gathered in the field, capturing folk music performances, usually intertwined with interviews with performers (informants) or commentaries by the folklorist. As their role is to document the legacy of folk musicians in their actual environment, the recordings are usually taken in non-ideal spaces (e.g., a performer’s home) and may contain environmental noises (e.g., people entering and leaving the room, background talking) or interruptions. One of the first tasks that ethnomusicologists (or algorithms) face when studying a field recording, is its segmentation into smaller coherent units, such as units containing speech or individual folk song performances. Segmentation approaches relied on hand-crafted features, tuned to discriminate between speech and music, which were the two categories most works aimed to
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
