Publications

Export 9 results:
Author Title Type [ Year(Asc)]
Filters: Author is J. Melechovsky  [Clear All Filters]
2026
Melechovsky J., Novotny M., Tykalova T., Klempir J., Herremans D..  2026.  Development of Interpretable Deep Learning-based Segmentation Algorithm for Automated Assessment of Oral Diadochokinesis in Progressive Neurological Diseases. Journal of Speech, Language, and Hearing Research.
Lu T., Geist C-M, Melechovsky J., Roy A., Herremans D..  2026.  MelodySim: Measuring Melody-aware Music Similarity for Plagiarism Detection. IEEE Tencon.
Melechovsky J., Mehrish A., Roy A., Herremans D..  2026.  SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering. Proceedings of ICML. PDF icon 2508.03448v2.pdf (3.31 MB)
2025
Melechovsky J..  2025.  Analysis and Synthesis of Audio with AI: from Neurological Disease to Accented Speech and Music. PDF icon thesis_Jan.pdf (26.4 MB)
2024
Melechovsky J., Mehrish A., Sisman B., Herremans D..  2024.  Accent Conversion in Text-To-Speech Using Multi-Level VAE and Adversarial Training. Proc. of IEEE Tencon, Singapore.
Melechovsky J., Mehrish A., Sisman B., Herremans D..  2024.  Accented Text-to-Speech Synthesis with a Conditional Variational Autoencoder. Proc. of IEEE Tencon, Singapore.
Melechovsky J., Mehrish A., Sisman B., Herremans D..  2024.  DART: Disentanglement of Accent and Speaker Representation in Multispeaker Text-to-Speech. Audio Imagination: NeurIPS 2024 Workshop.
Melechovsky J., Roy A., Herremans D..  2024.  MidiCaps — A large-scale MIDI dataset with text captions. ISMIR. PDF icon 2406.02255v1.pdf (699.83 KB)
2023
Melechovsky J., Mehrish A., Herremans D., Sisman B..  2023.  Learning accent representation with multi-level VAE towards controllable speech synthesis. IEEE Spoken Language Technology (SLT) Workshop.