Facial anonymization with Artificial Intelligence in Music Therapy: a pilot study with AKOOL Face Swap and Syntonym
DOI:
https://doi.org/10.55777/rea.v19i37.8603Keywords:
Music therapy, facial anonymization, artificial intelligence, facial expression, privacyAbstract
In music therapy, sharing clinical materials requires balancing privacy protection with the preservation of emotional information, as traditional methods such as blurring can hide facial expressions and reduce the clinical value of the material. This pilot study involved 20 music therapists who evaluated three video excerpts presented in four versions: original, blurred, and face substitution using two artificial intelligence applications (AKOOL Face Swap and Syntonym). Ratings were collected using Likert-type scales and analyzed with statistical procedures, together with estimates of reliability and inter-rater agreement. The results showed significant differences (χ²(2)=13.30; p=0.0013), with meaningful improvements in clinical utility and expressivity for the AI-based versions compared to blurring (≈0.8–0.9 points; p<0.01), and no differences between AKOOL and Syntonym. Reliability ranged from acceptable to excellent (α=0.61–0.88; ω=0.79–0.91), and inter-rater agreement was high when averaged across raters (ICC=0.86). AI-based face substitution better preserves expressive signals and provides a more favorable balance between privacy and utility than blurring, making it suitable for research and public dissemination under appropriate ethical and regulatory safeguards. However, original materials remain more appropriate for teaching and closed supervision settings with the required consent.
Downloads
References
Abdulaziz, S., & Bondarev, E. (2025). Unmasking performance gaps: A comparative study of human anonymization and its effects on video anomaly detection (arXiv:2507.14083). arXiv. https://doi.org/10.48550/arXiv.2507.14083
Agarwal, S., Peta, S., & Panyam, S. (2024). Deepfakes in healthcare: Reviewing the transformation potential and its challenges. International Journal of Intelligent Systems and Applications in Engineering, 12(4), 3965–3970.
Akool. (n.d.). Best face swap for photos & videos online with free trial. Akool. https://akool.com/apps/faceswap
Amorós-Sánchez, B., Gamella-González, D. J., Cisneros-Álvarez, P., & Gisbert-Caudeli, V. (2024). A systematic review of the technology available for data collection and assessment in music therapy. En A. L. Brooks (Ed.), ArtsIT 2023… Proceedings, Part I (pp. 41–54). Springer. https://doi.org/10.1007/978-3-031-55319-6_4
American Music Therapy Association. (n.d.). Code of ethics. https://www.musictherapy.org/about/ethics/
American Psychological Association (2024). Proposed Revision of Guidelines for the Practice of Telepsychology. Tomado de: https://www.apa.org/practice/guidelines/telepsychology-revisions.pdf
Baumgartner, R., Arora, P., Bath, C., Williams, R. (2023). Fair and equitable AI in biomedical research and healthcare: Social science perspectives. Artificial Intelligence in Medicine, 144, 102658. https://doi.org/10.1016/j.artmed.2023.102658
Behrens, G. A. (2020). Considerations when writing and presenting consent forms for clients. Music Therapy Perspectives, 38(1), 38–41. https://doi.org/10.1093/mtp/miz029
Braun, V., & Clarke, V. (2019). Reflecting on reflexive thematic analysis. Qualitative Research in Sport, Exercise and Health, 11(4), 589–597. https://doi.org/10.1080/2159676X.2019.1628806
Bruscia, K. E. (2014). Defining music therapy (4th ed.). Barcelona Publishers.
Bunt, L., & Stige, B. (2014). Music therapy: An art beyond words (2.ª ed.). Routledge.
Chesney, R., & Citron, D. (2019). Deepfakes: A looming challenge for privacy, democracy, and national security. California Law Review, 107, 1753–1819. https://doi.org/10.2139/ssrn.3213954
Clements-Cortés, A., Fuller, A., Kelly, L., Pranjić, M., Selvarajah, I., Mercadal-Brotons, M., & Bridi, N. (2025). Music therapists’ global perspectives on telehealth music therapy: A qualitative interview inquiry. Music Therapy Perspectives. Advance online publication. https://doi.org/10.1093/mtp/miae030
Conduah, A. K., Ofoe, S., & Siaw-Marfo, D. (2025). Data privacy in healthcare: Global challenges and solutions. Digital Health, 11, 20552076251343959. https://doi.org/10.1177/20552076251343959
Creswell, J. W., & Plano Clark, V. L. (2014). Designing and conducting mixed methods research (2.ª ed.). SAGE.
Dileo, C. (2007). Ethical thinking in music therapy. Jeffrey Books.
Fattorini Vaca, A., & Gamella-González, D. J. (2022). Ética profesional en musicoterapia desde la perspectiva del musicoterapeuta. En S. Olivero Guidobono (Coord.), Artes y humanidades en el centro de los conocimientos: Miradas sobre el patrimonio, la cultura, la historia, la antropología y la demografía (pp. 637–670). Dykinson. https://www.dykinson.com/libros/artes-y-humanidades-en-el-centro-de-los-conocimientos-miradas-sobre-el-patrimonio-la-cultura-la-historia-la-antropologia-y-la-demografia/9788413779263/
Fernández-Company, J. F., Gamella-González, D. J., & García-Rodríguez, M. (2024). Autoevaluación de la práctica en musicoterapia para el crecimiento profesional. En M. del M. Simón Márquez, P. Molina Moreno, J. J. Gázquez Linares, & S. Fernández Gea (Coords.), Innovación en salud: Estrategias emergentes para la docencia y la investigación (pp. 27–33). ASUNIVEP. https://dialnet.unirioja.es/servlet/libro?codigo=974646
Fisher, C. B. (2021). Decoding the ethics code: A practical guide for psychologists (5th ed.). SAGE.
Flores Cruz, R. (2025). Uso de la realidad virtual para afrontar obstáculos didácticos, atendiendo los principales estilos de aprendizaje. Revista de Estilos de Aprendizaje, 18(35). Recuperado de https://revistaestilosdeaprendizaje.com/index
Franzreb, C., Das, A., Gieseler, H., Jahn, E. C., Polzehl, T., & Möller, S. (2024). Towards audiovisual anonymization for remote psychotherapy: A subjective evaluation. En Proceedings of SPSC 2024 (pp. 102–110). ISCA. https://doi.org/10.21437/SPSC.2024-17
Gamella-González, D. J. (2025). Proyecto MUTia: Inteligencia artificial aplicada al songwriting en musicoterapia. En D. De la Rosa & P. Renés (Eds.), Políticas educativas y nuevos modelos de enseñanza-aprendizaje en educación superior y formación profesional (pp. 229–252). Tirant lo Blanch.
Geretsegger, M., Elefant, C., Mössler, K. A., & Gold, C. (2014). Music therapy for people with autism spectrum disorder. Cochrane Database of Systematic Reviews, 2014(6), CD004381. https://doi.org/10.1002/14651858.CD004381.pub3
Gold, C. (2016). Abstracts of the 10th European Music Therapy Conference. Nordic Journal of Music Therapy, 25(sup1), 1–156. https://doi.org/10.1080/08098131.2016.11783620
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial networks. arXiv. https://doi.org/10.48550/arXiv.1406.2661
Gupta, A., Malik, P., Pathania, M., & Rathaur, V. K. (2019). Overview of artificial intelligence in medicine. Journal of Family Medicine and Primary Care, 8(7), 2328–2331. https://doi.org/10.4103/jfmpc.jfmpc_440_19
Hamilton, L. (2025). The future of music therapy: An exploration of music therapists’ perceptions of artificial intelligence and its ethical implications [Trabajo fin de grado, Edinburgh College of Art, Universidad de Edimburgo]. Edinburgh College of Art Graduate Show. https://www.2025.graduateshow.eca.ed.ac.uk/sites/default/files/2025-05/LH%20Dissertation%20ECA%20Graduate%20Show%202025.pdf
Hewson, T., Abraham, S., Randles, N., Akinola, A., Cliff, R., Byrne, P., & Ramkisson, R. (2022). The recording of mental health consultations by patients: Clinical, ethical and legal considerations. BJPsych Bulletin, 46(3), 133–137. https://doi.org/10.1192/bjb.2021.89
Hoek S, Metselaar S, Ploem C. & Bak, C. (2025). Promising for patients or deeply disturbing? The ethical and legal aspects of deepfake therapy. Journal of Medical Ethics 51:481-486. https://doi.org/10.1136/jme-2024-109985
Johnson, J., Alahi, A., & Fei-Fei, L. (2016). Perceptual losses for real-time style transfer and super-resolution. En ECCV 2016 (pp. 694–711). Springer. https://doi.org/10.1007/978-3-319-46475-6_43
Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. En CVPR 2019 (pp. 4401–4410). IEEE. https://doi.org/10.1109/CVPR.2019.00453
Kern, P. (2025). Artificial intelligence in music therapy: A new era of personalized care and scalable impacts. MiSOSTENiDO, 5(9), 8–16. https://doi.org/10.59028/misostenido.2025.02
Khalid, H., Kim, M., Tariq, S., & Woo, S. S. (2021). Evaluation of an audio-video multimodal deepfake dataset using unimodal and multimodal detectors. En ADGD ’21, ACM MM Workshops (pp. 7–15). ACM. https://doi.org/10.1145/3476099.3484315
Khalid, N., Qayyum, A., Bilal, M., Al-Fuqaha, A., & Qadir, J. (2023). Privacy-preserving artificial intelligence in healthcare: Techniques and applications. Computers in Biology and Medicine, 158, 106848. https://doi.org/10.1016/j.compbiomed.2023.106848
Kim, J., & Lee, S. (2018). Music therapy for depression: A meta-analysis. The Arts in Psychotherapy, 59, 103–112. https://doi.org/10.1016/j.aip.2018.03.004
Lavanchy, J. L., Vardazaryan, A., Mascagni, P., et al. (2023). Preserving privacy in surgical video analysis using a deep learning classifier to identify out-of-body scenes in endoscopic videos. Scientific Reports, 13, 9235. https://doi.org/10.1038/s41598-023-36453-1
Liu, Z., Luo, P., Wang, X., & Tang, X. (2015). Deep learning face attributes in the wild. En ICCV 2015 (pp. 3730–3738). IEEE. https://doi.org/10.1109/ICCV.2015.425
Navarro Martínez, O., Fernández-García, D., Cuartero Monteagudo, N., & Forero-Rincón, O. (2024). Possible health benefits and risks of deepfake videos: A qualitative study in nursing students. Nursing Reports, 14(4), 2746–2757. https://doi.org/10.3390/nursrep14040203
NHS Lothian. (2023). Audio and video recordings of psychological therapy sessions policy. https://policyonline.nhslothian.scot/wp-content/uploads/2023/03/Audio-and-Video-Recordings-of-Psychological-Therapy-Sessions-Policy.pdf
Paris, B., & Donovan, J. (2019). Deepfakes and cheap fakes: The manipulation of audio and visual evidence. Data & Society. https://datasociety.net/library/deepfakes-and-cheap-fakes/
Parlamento Europeo & Consejo de la Unión Europea. (2016). Regulation (EU) 2016/679 (GDPR). Official Journal of the European Union, L119, 1–88. https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:32016R0679
Pérez, M., & García, J. (2025). Adaptación y validación de la escala TPACK en la formación de profesores para la educación a distancia. Revista de Estilos de Aprendizaje, 18(35). Recuperado de https://revistaestilosdeaprendizaje.com/index
Pink, S., Horst, H., Postill, J., Hjorth, L., Lewis, T., & Tacchi, J. (2016). Digital ethnography: Principles and practice. SAGE.
Qureshi, J., & Khan, S. (2025). Artificial intelligence deepfakes in healthcare systems: A double-edged sword? International Journal of Data Science and Big Data Analytics, 5(1), 84–93. https://doi.org/10.51483/IJDSBDA.5.1.2025.84-93
Reid, A., & Miño, P. (2021). When therapy goes public: Copyright gatekeepers and sharing therapeutic artifacts on social media. International Journal of Communication, 15, 950–969. https://ijoc.org/index.php/ijoc/article/view/1652
Sæle, R. G., & Gilbertson, S. (2024). Ethical reflections on social media use within music therapy: A conversational focus group study. Nordic Journal of Music Therapy, 33(5), 409–425. https://doi.org/10.1080/08098131.2024.2350939
Shuvi, M., Fish, N., Aberman, K., Shamir, A., & Cohen-Or, D. (2020). Neural alignment for face de-pixelization (arXiv:2009.13856). arXiv. https://doi.org/10.48550/arXiv.2009.13856
Sun, J., Yang, J., Zhou, G., Jin, Y., & Gong, J. (2024). Understanding human-AI collaboration in music therapy through co-design with therapists. En CHI 2024 Proceedings (Art. 704, pp. 1–21). ACM. https://doi.org/10.1145/3613904.3642764
Syntonym. (n.d.). Generative AI for privacy! Hyper realistic face anonymization for videos & images. Syntonym. https://www.Syntonym.com/
Tariq, S., Woo, S. S., Singh, P., Irmalasari, I., Gupta, S., & Gupta, D. (2025). From prediction to explanation: Multimodal, explainable, and interactive deepfake detection framework for non-expert users (arXiv:2508.07596) https://arxiv.org/abs/2508.07596
Tiribelli, S., Monnot, A., Shah, S. F. H., Arora, A., Toong, P. J., & Kong, S. (2023). Ethics Principles for Artificial Intelligence-Based Telemedicine for Public Health. American journal of public health, 113(5), 577–584. https://doi.org/10.2105/AJPH.2023.307225
Todt, J., Hanisch, S., & Strufe, T. (2024). Fantômas: Understanding face anonymization reversibility. Proceedings on Privacy Enhancing Technologies, 2024(4), 24–43. https://doi.org/10.56553/POPETS-2024-0105
Warrier, U., Warrier, A., & Khandelwal, K. (2023). Ethical considerations in the use of artificial intelligence in mental health. The Egyptian Journal of Neurology, Psychiatry and Neurosurgery, 59, 139. https://doi.org/10.1186/s41983-023-00735-2
Westerlund, M. (2019). The emergence of deepfake technology: A review. Technology Innovation Management Review, 9(11), 39–52. https://doi.org/10.22215/timreview/1282
Yim, D., Khuntia, J., Parameswaran, V., & Meyers, A. (2024). Preliminary evidence of the use of generative AI in health care clinical services: Systematic narrative review. JMIR Medical Informatics, 12, e52073. https://doi.org/10.2196/52073
Zhu, Y., Imoussaïne-Aïkous, M., Côté-Lussier, C., and H. Falk, T. (2024). On the Impact of Voice Anonymization on Speech Diagnostic Applications: A Case Study on COVID-19 Detection. Trans. Info. For. Sec. 19 5151–5165. https://doi.org/10.1109/TIFS.2024.3390990
Downloads
Published
How to Cite
Issue
Section
License
By submitting the original, the author(s) declare that they are aware of and accept, in full, the privacy policy as well as the copyright of the Learning Styles Magazine.
The Learning Styles Magazine offers free and open access to its content, completely free of charge, in order to bring scientific research to its readers and society in general. All digital contents are free and open access and are published under a Creative Commons license:
Rights are granted under the Creative Commons Reconocimiento-NoComercial-SinObraDerivada 4.0 Internacional (CC-BY-NC-ND 4.0)
The Learning Styles Magazine is an open access journal. Publication of articles or reviews in the Journal does not entitle you to any remuneration. For authors as well as readers, the journal is free Creative Commons Reconocimiento-NoComercial-SinObraDerivada 4.0 Internacional (CC-BY-NC-ND 4.0).
With this licence, the reproduction and dissemination of the contents of the magazine for educational, social and knowledge transmission purposes is permitted, without any profit motive in mind, provided that the source and authorship are not modified. The licence granted to Learning Styles Magazine allows the copying and distribution of the magazine's contents, as long as the authorship of the work is recognised, correctly specifying the author and the publishing entity. The work may not be used for commercial purposes, nor may it be altered, transformed or generated from this work.
The publication of articles or reviews in the Journal does not give the right to any remuneration.
The Learning Styles Journal invites the author/authors to increase the visibility and scope of their articles published by re-disseminating them in:
- Web spaces and personal networks, as well as in scientific meetings and forums
- Open institutional archives in Universities, educational repositories and Research Centres.
- Academic and scientific networks (Researchgate, Academia.edu, Plubons, etc.)
All these spaces and publications must include all the bibliographic data of the publication.
