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

Xuhong Qiu; Emilia Parada‑Cabaleiro

doi:10.5334/tismir.310

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

Volume 9 (2026): Issue 1

By: Xuhong Qiu and Emilia Parada‑Cabaleiro

Open Access

|Jul 2026

Aaen, M., Sadolin, C., and McGlashan, J. (2025). Toward a taxonomy for supraglottic structure vibrations in voice: A narrative literature review. Perspectives of the ASHA Special Interest Groups, 1–21. 10.1044/2024_PERSP-24-00140.
Open DOI Search in Google Scholar Back to article
Bekkar, M., Djemaa, H. K., and Alitouche, T. A. (2013). Evaluation measures for models assessment over imbalanced data sets. Journal of Information Engineering and Applications, 3, 27–38. 10.5121/ijdkp.2013.3402.
Open DOI Search in Google Scholar Back to article
Brackett, D. (2016). Categorizing Sound: Genre and Twentieth‑Century Popular Music. University of California Press. 10.1525/california/9780520248717.001.0001.
Open DOI Search in Google Scholar Back to article
Caffier, P. P., Ibrahim Nasr, A., and Ropero Rendon, M. D. M. (2018). Common vocal effects and partial glottal vibration in professional nonclassical singers. Journal of Voice, 32(3), 340–346. 10.1016/j.jvoice.2017.06.009.
Open DOI Search in Google Scholar Back to article
Eckers, C., Hütz, D., Kob, M., Murphy, P. J., Houben, D., and Lehnert, B. (2009). Voice production in death metal singers. In Proceedings of NAG/DAGA 2009, Rotterdam, The Netherlands, pp. 1747–1750.
Search in Google Scholar Back to article
Erbe, M. (2014). By demons be driven? Scanning “monstrous” voices. In In Hardcore, Punk, and Other Junk: Aggressive Sounds in Contemporary Music (pp. 51–71). 10.5771/9780739176061-51.
Open DOI Search in Google Scholar Back to article
Eyben, F., Wöllmer, M., and Schuller, B. (2010). OpenSMILE – The Munich versatile and fast open‑source audio feature extractor. In Proceedings of the ACM International Conference on Multimedia (MM 2010), Firenze, Italy, pp. 1459–1462. 10.1145/1873951.1874246.
Open DOI Search in Google Scholar Back to article
Fuks, L., Hammarberg, B., and Sundberg, J. (1998). A self‑sustained vocal ventricular phonation mode: Acoustical, aerodynamic and glottographic evidences. KTH TMH‑QPSR, 3, 49–59.
Search in Google Scholar Back to article
Gentilucci, M., Ardaillon, L., and Liuni, M. (2018). Vocal distortion and real‑time processing of roughness. In Proceedings of the International Computer Music Conference (ICMC 2018). Seoul, South Korea.
Search in Google Scholar Back to article
Green, O., Sturm, B., Born, G., and Wald‑Fuhrmann, M. (2024). A critical survey of research in music genre recognition. In Proceedings of the 25th International Society for Music Information Retrieval Conference (ISMIR), San Francisco, CA, USA, pp. 745–782.
Search in Google Scholar Back to article
Guyon, I., and Elisseeff, A. (2003). An introduction to variable and feature selection. The Journal of Machine Learning Research, 3, 1157–1182. 10.1162/153244303322753616.
Open DOI Search in Google Scholar Back to article
Guzman, M., Acevedo, K., Leiva, F., Ortiz, V., Hormazabal, N., and Quezada, C. (2018). Aerodynamic characteristics of growl voice and reinforced falsetto in metal singing. Journal of Voice, 32(6), 674–683. 10.1016/j.jvoice.2018.04.022.
Open DOI Search in Google Scholar Back to article
Ishi, C. T., Sakakibara, K.‑I., Ishiguro, H., and Hagita, N. (2007). A method for automatic detection of vocal fry. IEEE Transactions on Audio, Speech, and Language Processing, 15(1), 346–355. 10.1109/TASL.2007.910791.
Open DOI Search in Google Scholar Back to article
Jothimani, S., and Premalatha, K. (2022). MFF‑SAUG: Multi feature fusion with spectrogram augmentation of speech emotion recognition using convolution neural network. Chaos, Solitons & Fractals, 162, 112512. 10.1016/j.chaos.2022.112512.
Open DOI Search in Google Scholar Back to article
Juslin, P. N., and Västfjäll, D. (2008). Emotional responses to music: The need to consider underlying mechanisms. Behavioral and Brain Sciences, 31(5), 559–575. 10.1017/s0140525x08005293.
Open DOI Search in Google Scholar Back to article
Kalbag, V., and Lerch, A. (2022). Scream detection in heavy metal music. arXiv preprint arXiv:2205.05580
Search in Google Scholar Back to article
Kato, K., and Ito, A. (2013). Acoustic features and auditory impressions of death growl and screaming voice. In Proceedings of the 2013 Ninth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Beijing, China, pp. 460–463. 10.1109/IIH-MSP.2013.120.
Open DOI Search in Google Scholar Back to article
Kennedy, L. (2018). Functions of Genre in Metal and Hardcore Music [PhD thesis]. The University of Hull.
Search in Google Scholar Back to article
Kohavi, R., and John, G. H. (1997). Wrappers for feature subset selection. Artificial Intelligence, 97(1), 273–324. 10.1016/s0004-3702(97)00043-x.
Open DOI Search in Google Scholar Back to article
Krogh, M. (2025). Rampant abstraction as a strategy of singularization: Genre on Spotify. Cultural Sociology, 19(1), 89–107. 10.1177/17499755231172828.
Open DOI Search in Google Scholar Back to article
Li, H., Li, J., Liu, H., Liu, T., Chen, Q., and You, X. (2024). MelTrans: Mel‑spectrogram relationship learning for speech emotion recognition via transformers. Sensors, 24(17). 10.3390/s24175506.
Open DOI Search in Google Scholar Back to article
Lindestad, P. A., Södersten, M., Merker, B., and Granqvist, S. (2001). Voice source characteristics in Mongolian “throat singing” studied with high‑speed imaging technique, acoustic spectra, and inverse filtering. Journal of Voice, 15(1), 78–85. 10.1016/s0892-1997(01)00008-x.
Open DOI Search in Google Scholar Back to article
Lã, F. M. (2012). Teaching singing and technology. In K. S. Basa (Ed.), Aspects of Singing II: Unity in Understanding – Diversity in Aesthetics (pp. 88–109). BDG e.V.
Search in Google Scholar Back to article
Martin, K. D. (1999). Sound‑Source Recognition: A Theory and Computational Model. [PhD thesis]. Massachusetts Institute of Technology.
Search in Google Scholar Back to article
McCoy, S. (2014). Singing pedagogy in the twenty‑first century: A look toward the future. In S. D. Harrison and J. O’Bryan (Eds.), Teaching Singing in the 21st Century (pp. 13–20). Springer. 10.1007/978-94-017-8851-9_2.
Open DOI Search in Google Scholar Back to article
McFee, B., Raffel, C., Liang, D., Ellis, D. P., McVicar, M., Battenberg, E., and Nieto, O. (2015). librosa: Audio and music signal analysis in Python. SciPy, 18–24. 10.25080/Majora-7b98e3ed-003.
Open DOI Search in Google Scholar Back to article
Nandwana, M. K., Ziaei, A., and Hansen, J. H. L. (2015). Robust unsupervised detection of human screams in noisy acoustic environments. In Proceedings of the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, QLD, Australia, pp. 161–165. 10.1109/ICASSP.2015.7177952.
Open DOI Search in Google Scholar Back to article
Nieto, O. (2008). Voice transformations for extreme vocal effects. Master’s thesis. Pompeu Fabra University.
Search in Google Scholar Back to article
Nieto, O. (2013). Unsupervised clustering of extreme vocal effects. In Proceedings of the 10th International Conference on Advances in Quantitative Laryngology, Voice and Speech Research, New York, NY, USA.
Search in Google Scholar Back to article
Olsen, K. N., Thompson, W. F., and Giblin, I. (2018). Listener expertise enhances intelligibility of vocalizations in death metal music. Music Perception, 35(5), 527–539. 10.1525/mp.2018.35.5.527.
Open DOI Search in Google Scholar Back to article
Parada‑Cabaleiro, E., Batliner, A., Schmitt, M., Schedl, M., Costantini, G., and Schuller, B. W. (2023). Perception and classification of emotions in nonsense speech: Humans versus machines. PLOS ONE, 18, 1–26. 10.1371/journal.pone.0281079.
Open DOI Search in Google Scholar Back to article
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit‑learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830. http://jmlr.org/papers/v12/pedregosa11a.html, 10.48550/arXiv.1201.0490.
Open DOI Search in Google Scholar Back to article
Pohjalainen, J., Alku, P., and Kinnunen, T. (2011). Shout detection in noise. In Proceedings of the 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Prague, Czech Republic, pp. 4960–4963. 10.1109/ICASSP.2011.5947471.
Open DOI Search in Google Scholar Back to article
Purwins, H., Li, B., Virtanen, T., Schlüter, J., Chang, S., and Sainath, T. N. (2019). Deep learning for audio signal processing. IEEE Journal of Selected Topics in Signal Processing, 13(2), 206–219. 10.1109/jstsp.2019.2908700.
Open DOI Search in Google Scholar Back to article
Sadolin, C. (2012). Complete Vocal Technique. CVI Publications.
Search in Google Scholar Back to article
Sakakibara, K.‑I., Fuks, L., Imagawa, H., and Tayama, N. (2004). Growl voice in ethnic and pop styles. In Proceedings of the International Symposium on Musical Acoustics (ISMA 2004), Nara, Japan.
Search in Google Scholar Back to article
Smialek, E., Depalle, P., and Brackett, D. (2012). A spectrographic analysis of vocal techniques in extreme metal for musicological analysis. In Proceedings of the ICMC 2012 – International Computer Music Conference, Montréal, QC, Canada, pp. 88–92.
Search in Google Scholar Back to article
Stadler, A., Parada‑Cabaleiro, E., and Schedl, M. (2023). Towards potential applications of machine learning in computer‑assisted vocal training. In Proceedings of the International Symposium on Computer Music Multidisciplinary Research (CMMR), Tokyo, Japan, pp. 430–441.
Search in Google Scholar Back to article
Tailleur, M., Pinquier, J., Millot, L., Vogel, C., and Lagrange, M. (2024). EMVD dataset: A dataset of extreme vocal distortion techniques used in heavy metal. In Proceedings of the International Conference on Content‑Based Multimedia Indexing (CBMI), Reykjavik, Iceland, pp. 1–5. 10.1109/CBMI62980.2024.10859205.
Open DOI Search in Google Scholar Back to article
Titze, I. (2008). Nonlinear source‑filter coupling in phonation: Theory. The Journal of the Acoustical Society of America, 123, 2733–2749. 10.1121/1.2832337.
Open DOI Search in Google Scholar Back to article
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., and Bright, J. (2020). SciPy 1.0: Fundamental algorithms for scientific computing in Python. Nature Methods, 17(3), 261–272. 10.1038/s41592-020-0772-5.
Open DOI Search in Google Scholar Back to article
Wallmark, Z. (2018). The sound of evil: Timbre, body, and sacred violence in death metal. In R. Fink, M. Latour, and Z. Wallmark (Eds.), The Relentless Pursuit of Tone: Timbre in Popular Music (pp. 65–87). Oxford University Press. 10.1093/oso/9780199985227.003.0004.
Open DOI Search in Google Scholar Back to article
Xu, Y., Wang, W., Cui, H., Xu, M., and Li, M. (2022). Paralinguistic singing attribute recognition using supervised machine learning for describing the classical tenor solo singing voice in vocal pedagogy. EURASIP Journal on Audio, Speech, and Music Processing, 2022(1), 8. 10.1186/s13636-022-00240-z.
Open DOI Search in Google Scholar Back to article