Saved in:
Bibliographic Details
Main Authors: Suda, Hitoshi, Yoshida, Shunsuke, Nakamura, Tomohiko, Fukayama, Satoru, Ogata, Jun
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.12549
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917779808976896
author Suda, Hitoshi
Yoshida, Shunsuke
Nakamura, Tomohiko
Fukayama, Satoru
Ogata, Jun
author_facet Suda, Hitoshi
Yoshida, Shunsuke
Nakamura, Tomohiko
Fukayama, Satoru
Ogata, Jun
contents This study presents FruitsMusic, a metadata corpus of Japanese idol-group songs in the real world, precisely annotated with who sings what and when. Japanese idol-group songs, vital to Japanese pop culture, feature a unique vocal arrangement style, where songs are divided into several segments, and a specific individual or multiple singers are assigned to each segment. To enhance singer diarization methods for recognizing such structures, we constructed FruitsMusic as a resource using 40 music videos of Japanese idol groups from YouTube. The corpus includes detailed annotations, covering songs across various genres, division and assignment styles, and groups ranging from 4 to 9 members. FruitsMusic also facilitates the development of various music information retrieval techniques, such as lyrics transcription and singer identification, benefiting not only Japanese idol-group songs but also a wide range of songs featuring single or multiple singers from various cultures. This paper offers a comprehensive overview of FruitsMusic, including its creation methodology and unique characteristics compared to conversational speech. Additionally, this paper evaluates the efficacy of current methods for singer embedding extraction and diarization in challenging real-world conditions using FruitsMusic. Furthermore, this paper examines potential improvements in automatic diarization performance through evaluating human performance.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12549
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FruitsMusic: A Real-World Corpus of Japanese Idol-Group Songs
Suda, Hitoshi
Yoshida, Shunsuke
Nakamura, Tomohiko
Fukayama, Satoru
Ogata, Jun
Sound
Audio and Speech Processing
This study presents FruitsMusic, a metadata corpus of Japanese idol-group songs in the real world, precisely annotated with who sings what and when. Japanese idol-group songs, vital to Japanese pop culture, feature a unique vocal arrangement style, where songs are divided into several segments, and a specific individual or multiple singers are assigned to each segment. To enhance singer diarization methods for recognizing such structures, we constructed FruitsMusic as a resource using 40 music videos of Japanese idol groups from YouTube. The corpus includes detailed annotations, covering songs across various genres, division and assignment styles, and groups ranging from 4 to 9 members. FruitsMusic also facilitates the development of various music information retrieval techniques, such as lyrics transcription and singer identification, benefiting not only Japanese idol-group songs but also a wide range of songs featuring single or multiple singers from various cultures. This paper offers a comprehensive overview of FruitsMusic, including its creation methodology and unique characteristics compared to conversational speech. Additionally, this paper evaluates the efficacy of current methods for singer embedding extraction and diarization in challenging real-world conditions using FruitsMusic. Furthermore, this paper examines potential improvements in automatic diarization performance through evaluating human performance.
title FruitsMusic: A Real-World Corpus of Japanese Idol-Group Songs
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2409.12549