SongEval: A Benchmark Dataset for Song Aesthetics Evaluation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yao, Jixun, Ma, Guobin, Xue, Huixin, Chen, Huakang, Hao, Chunbo, Jiang, Yuepeng, Liu, Haohe, Yuan, Ruibin, Xu, Jin, Xue, Wei, Liu, Hao, Xie, Lei
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916739372023808
author Yao, Jixun
Ma, Guobin
Xue, Huixin
Chen, Huakang
Hao, Chunbo
Jiang, Yuepeng
Liu, Haohe
Yuan, Ruibin
Xu, Jin
Xue, Wei
Liu, Hao
Xie, Lei
author_facet Yao, Jixun
Ma, Guobin
Xue, Huixin
Chen, Huakang
Hao, Chunbo
Jiang, Yuepeng
Liu, Haohe
Yuan, Ruibin
Xu, Jin
Xue, Wei
Liu, Hao
Xie, Lei
contents Aesthetics serve as an implicit and important criterion in song generation tasks that reflect human perception beyond objective metrics. However, evaluating the aesthetics of generated songs remains a fundamental challenge, as the appreciation of music is highly subjective. Existing evaluation metrics, such as embedding-based distances, are limited in reflecting the subjective and perceptual aspects that define musical appeal. To address this issue, we introduce SongEval, the first open-source, large-scale benchmark dataset for evaluating the aesthetics of full-length songs. SongEval includes over 2,399 songs in full length, summing up to more than 140 hours, with aesthetic ratings from 16 professional annotators with musical backgrounds. Each song is evaluated across five key dimensions: overall coherence, memorability, naturalness of vocal breathing and phrasing, clarity of song structure, and overall musicality. The dataset covers both English and Chinese songs, spanning nine mainstream genres. Moreover, to assess the effectiveness of song aesthetic evaluation, we conduct experiments using SongEval to predict aesthetic scores and demonstrate better performance than existing objective evaluation metrics in predicting human-perceived musical quality.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10793
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SongEval: A Benchmark Dataset for Song Aesthetics Evaluation
Yao, Jixun
Ma, Guobin
Xue, Huixin
Chen, Huakang
Hao, Chunbo
Jiang, Yuepeng
Liu, Haohe
Yuan, Ruibin
Xu, Jin
Xue, Wei
Liu, Hao
Xie, Lei
Audio and Speech Processing
Aesthetics serve as an implicit and important criterion in song generation tasks that reflect human perception beyond objective metrics. However, evaluating the aesthetics of generated songs remains a fundamental challenge, as the appreciation of music is highly subjective. Existing evaluation metrics, such as embedding-based distances, are limited in reflecting the subjective and perceptual aspects that define musical appeal. To address this issue, we introduce SongEval, the first open-source, large-scale benchmark dataset for evaluating the aesthetics of full-length songs. SongEval includes over 2,399 songs in full length, summing up to more than 140 hours, with aesthetic ratings from 16 professional annotators with musical backgrounds. Each song is evaluated across five key dimensions: overall coherence, memorability, naturalness of vocal breathing and phrasing, clarity of song structure, and overall musicality. The dataset covers both English and Chinese songs, spanning nine mainstream genres. Moreover, to assess the effectiveness of song aesthetic evaluation, we conduct experiments using SongEval to predict aesthetic scores and demonstrate better performance than existing objective evaluation metrics in predicting human-perceived musical quality.
title SongEval: A Benchmark Dataset for Song Aesthetics Evaluation
topic Audio and Speech Processing
url https://arxiv.org/abs/2505.10793