Resource building and classification of Mizo folk songs
Natural Language Processing · 2025
DOI: 10.1017/nlp.2024.23 ↗Kurz gefasst
Fachartikel in der Zeitschrift Natural Language Processing, 2025. Verfasst von Esther Ramdinmawii und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Folk culture represents the social, ethnic, and traditional livelihood of people belonging to a certain tribe or community and is important in keeping their culture and tradition alive. The Mizo people are a Tibeto-Burmese ethnic group, native to the Indian state of Mizoram and neighboring regions of Northeast India. Mizo folk culture is an amalgamation of festivity, celebration, liveliness, kinship, brotherhood, and merriment, and above all, preserves the ethnicity of this tribal community that is fundamentally entrenched. Unfortunately, the Mizos are fast giving up their old customs and adopting the new mode of life that is greatly influenced by the western culture. This makes it all the more crucial to preserve the intangible cultural heritage of this ethnic tribe whose folk cultures are vanishing day by day. To the best of our knowledge, this work is the first attempt at preservation and classification of Mizo folk songs. The first part of this paper presents a literature survey on preservation, analysis, and classification of folk songs. The second part presents the methodology for preliminary classification of Mizo folk songs. Three categories of Mizo folk songs—Hunting chants ( Hlado ), Children’s songs ( Pawnto hla ), and Elderly songs ( Pi pu zai )—are used in this study. A total of 29 acoustic features are used. A long short-term memory network using custom attention layer has been proposed for classification, whose results are compared with four supervised models (Support Vector Machines, K-Nearest Neighbor, Naive Baye’s, and Ensemble). Experimental results from the proposed model are promising, with an implication of scope for future research in acoustic analysis and classification of Mizo folk songs using recent unsupervised methods.
Zitieren
APA
Ramdinmawii, E., & Nath, S. (2025). Resource building and classification of Mizo folk songs. Natural Language Processing. https://doi.org/10.1017/nlp.2024.23
Vancouver
Ramdinmawii E, Nath S. Resource building and classification of Mizo folk songs. Natural Language Processing. 2025. doi:10.1017/nlp.2024.23
BibTeX
@article{Ramdinmawii2025,
author = {Ramdinmawii, Esther and Nath, Sanghamitra},
title = {Resource building and classification of Mizo folk songs},
journal = {Natural Language Processing},
year = {2025},
doi = {10.1017/nlp.2024.23}
}
EUVIMED