To KTH's start page

Department for Speech, Music and Hearing (TMH)

The Department of Speech, Music and Hearing (TMH) is one of the leading research environments in speech and music technology. Since 1951, TMH has conducted research in spoken interaction – both to understand human perception and production, and to explore how these can be modelled by machines. TMH currently runs a large number of research projects in generative methods for speech, gesture, text, sign language and music. The department also works with social robotics and human–robot interaction, with applications in education and assistive technology.

Research Area

Latest Publications

[1]
Thomé, C., Sturm, B., Pertoft, J., Jonason, N. (2026). Applying Textual Inversion to Control and Personalize Text-to-Music Models. In Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2024, Revised Selected Papers. (pp. 395-401). Springer Nature.
[2]
Sundberg, J. (2026). Ugly and Beautiful Voices : A Rebuttal of Saruhan’s Critical Comments. Journal of Voice.
[3]
Moëll, B. & Sand Aronsson, F. (2026). High-accuracy prediction of mental health scores from English BERT embeddings trained on LLM-generated synthetic self-reports: a synthetic-only method development study. Frontiers in Digital Health, 7.
[4]
Rugayan, J., Salvi, G., Svendsen, T. (2026). Optimizing ASR Models with Semantic Information. In TEXT, SPEECH, AND DIALOGUE, TSD 2025, PT I. (pp. 25-35). Springer Nature.
[5]
Axelsson, A., Vaddadi, B., Bogdan, C. M., Tobin, D. & Skantze, G. (2026). Robots as Hosts in Autonomous Buses : A Field Trial. ACM Transactions on Human-Robot Interaction, 15(1).
Full list in the KTH publications portal

News