Automatic Classification of Strain in the Singing Voice Using Machine Learning
This study demonstrates that machine learning models utilizing selected acoustic features can classify perceptual strain of singing voices automatically with high accuracy. These preliminary findings highlight the potential for larger studies involving more diverse singer groups across different genres.
Authors
- Okko Räsänen (ORCID: https://orcid.org/0000-0002-0537-0946)
- Tua Hakanpää (ORCID: https://orcid.org/0000-0001-8573-5855)
- Paavo Alku (ORCID: https://orcid.org/0000-0002-8173-9418)
- M. Kiran Reddy (ORCID: https://orcid.org/0000-0002-7987-1735)
- Tero Ikävalko (ORCID: https://orcid.org/0000-0003-1785-3707)
- Yuanyuan Liu (ORCID: https://orcid.org/0000-0002-1839-4728)
- Anne-Maria Laukkanen
- Madhu Keerthana Yagnavajjula
- Aleksi Öyry
Institutions
- Indian Institute of Management Raipur (IN)
- Indian Institute of Technology Kharagpur (IN)
- Tampere University of Applied Sciences (FI)
- University of Turku (FI)
- Tampere University (FI)
- University of Agricultural Sciences Raichur (IN)
- Aalto University (FI)
Publication Details
- Journal
- Journal of Voice
- Published
- 2025-04-01
- DOI
- https://doi.org/10.1016/j.jvoice.2025.03.040
- Citations
- 2
- Primary Topic
- Voice and Speech Disorders
- Type
- article
- Field-Weighted Citation Impact
- 2.33