EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Distorted Realities: Classifying Extreme Vocals Between Harmony and Noise – A Machine–Human Evaluation of Vocal Confusion Patterns

Xuhong Qiu, Emilia Parada‑Cabaleiro

Transactions of the International Society for Music Information Retrieval · 16.07.2026 · 9 (1) · 309-328

DOI: 10.5334/tismir.310 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions of the International Society for Music Information Retrieval, online erschienen am 16.07.2026. Verfasst von Xuhong Qiu und 1 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Extreme vocal techniques like growling and shrieking are common in metal and related genres, giving the music a characteristic intensity. Although widely used, these techniques have received limited attention in Music Information Retrieval (MIR) and musicology, particularly in fine‑grained categorisation. Their niche status and marginalisation have led to limited representation in digital music libraries. Since current classification systems prioritise dominant subgenres due to a lack of detailed vocal categorisations, extreme vocal styles are often oversimplified or misrepresented, hindering tagging, retrieval, and analysis. Automation could enable consistent and nuanced vocal annotation, supporting the technical goals of MIR and analytical aims of musicology. Foregrounding vocal technique as a classification axis contributes to a richer understanding of vocal performance and genre formation. To assess machine learning as a reliable alternative to human judgment, this study developed a coarse frequency‑based qualitative taxonomy from interviews with 11 extreme vocal practitioners and compared human and machine performance using the Extreme Metal Vocals Dataset (EMVD), including a listening test with 158 expert participants. Perceptual results achieved 76.2% Unweighted Average Recall (UAR), while a Support Vector Machine (SVM) model trained on ComParE features achieved a UAR of 90% on average, using singer‑independent 3‑fold group cross‑validation. Feature group, ablation, and human prediction analyses suggest that the human‑machine gap reflects differences in cue prioritisation and classification performance. Results illustrate the feasibility of machine learning to annotate vocal styles, while showing that human confusion patterns remain informative for category boundaries. This highlights how MIR methods could facilitate analysis of underrepresented genres.

Zitieren

APA

Qiu, X., & Parada‑Cabaleiro, E. (2026). Distorted Realities: Classifying Extreme Vocals Between Harmony and Noise – A Machine–Human Evaluation of Vocal Confusion Patterns. Transactions of the International Society for Music Information Retrieval, 9(1), 309-328. https://doi.org/10.5334/tismir.310

Vancouver

Qiu X, Parada‑Cabaleiro E. Distorted Realities: Classifying Extreme Vocals Between Harmony and Noise – A Machine–Human Evaluation of Vocal Confusion Patterns. Transactions of the International Society for Music Information Retrieval. 2026;9(1):309-328. doi:10.5334/tismir.310

BibTeX
@article{Qiu2026,
  author = {Qiu, Xuhong and Parada‑Cabaleiro, Emilia},
  title = {Distorted Realities: Classifying Extreme Vocals Between Harmony and Noise – A Machine–Human Evaluation of Vocal Confusion Patterns},
  journal = {Transactions of the International Society for Music Information Retrieval},
  year = {2026},
  volume = {9},
  number = {1},
  pages = {309--328},
  doi = {10.5334/tismir.310}
}
Kostenlos starten →