Automatic segmentation of ethnomusicological field recordings

Marolt, Matija (avtor), Bohak, Ciril (avtor), Kavčič, Alenka (avtor), Pesek, Matevž (avtor)

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.

• Jezik: Angleški jezik
• Ključne besede: audio segmentation, field recordings, deep learning, music information retrieval
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FRI - Fakulteta za računalništvo in informatiko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2019
• Št. strani: 12 str.
• Številčenje: Vol. 9, iss. 3, art. 439
• PID: 20.500.12556/RUL-131958
• UDK: 004:78
• ISSN pri članku: 2076-3417
• DOI: 10.3390/app9030439
• COBISS.SI-ID: 1538109123
• Datum objave v RUL: 07.10.2021

MAROLT, Matija, BOHAK, Ciril, KAVČIČ, Alenka in PESEK, Matevž, 2019, Automatic segmentation of ethnomusicological field recordings. Applied sciences [na spletu]. 2019. Vol. 9, no. 3,  439. [Dostopano 9 april 2025]. DOI 10.3390/app9030439. Pridobljeno s: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=slv&id=131958

Gradivo je del revije

• Naslov: Applied sciences
• Skrajšan naslov: Appl. sci.
• Založnik: MDPI
• ISSN: 2076-3417
• COBISS.SI-ID: 522979353

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.
• Začetek licenciranja: 01.02.2019

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: segmentacija zvočnih posnetkov, terenski posnetki, globoko učenje, pridobivanje informacij iz glasbe

Projekti

• Financer: ARRS - Agencija za raziskovalno dejavnost Republike Slovenije
• Številka projekta: J7-9426
• Naslov: Misliti folkloro: folkloristične, etnološke in računske perspektive in pristopi k narečju