To KTH's start page To KTH's start page

Speech, Music and Hearing (TMH)

Research at the Division of Speech, Music and Hearing (TMH) is truly multi-disciplinary including linguistics, phonetics, auditory perception, vision and experimental psychology. Rooted in an engineering modelling approach, our research forms a solid base for developing multimodal human-computer interaction systems in which speech, music, sound and gestures combine to create human-like communication.

Research Area

Latest Publications

[1]
Malmberg, F., Klezovich, A., Mesch, J., Beskow, J. (2024). Exploring Latent Sign Language Representations with Isolated Signs, Sentences and In-the-Wild Data. In 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources, sign-lang@LREC-COLING 2024. (pp. 219-224). Association for Computational Linguistics (ACL).
[2]
Mehta, S., Tu, R., Beskow, J., Székely, É., Henter, G. E. (2024). MATCHA-TTS: A FAST TTS ARCHITECTURE WITH CONDITIONAL FLOW MATCHING. In 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings. (pp. 11341-11345). Institute of Electrical and Electronics Engineers (IEEE).
[3]
Amerotti, M., Sturm, B., Benford, S., Maruri-Aguilar, H., Vear, C. (2024). Evaluation of an Interactive Music Performance System in the Context of Irish Traditional Dance Music. In Proceedings New Interfaces for Musical Expression NIME’24..
[4]
Jonason, N., Wang, X., Cooper, E., Juvela, L., Sturm, B., Yamagishi, J. (2024). DDSP-based Neural Waveform Synthesis of Polyphonic Guitar Performance from String-wise MIDI Input. In Proceedings of the 27th International Conference on Digital Audio Effects (DAFx24)..
[5]
Tånnander, C., O'Regan, J., House, D., Edlund, J., Beskow, J. (2024). Prosodic characteristics of English-accented Swedish neural TTS. In Proceedings of Speech Prosody 2024. (pp. 1035-1039). Leiden, The Netherlands: International Speech Communication Association.
Full list in the KTH publications portal

News