UTI (Ultrasound Tongue Imaging), EMA (Electromagnetic Articulography), MRI (Magnetic Resonance Imaging) are technologies which can be used to acquire articulatory data during speech production, e.g. https://sail.usc.edu/span/rtmri_ipa/index.html With these devices we can record high resolution images, and/or multichannel signals which can pose numerous challenges in terms of signal processing. The task of the student is to investigate deep learning (e.g. deep neural network, AutoEncoder, GAN) solutions, compare the various articulatory techniques, and apply this for the SSI (Silent Speech Interface) topic. Suggested programming languages: Python / Octave. The research will be conducted in collaboration with the MTA-ELTE Lingual Articulation Research Group (Momemtum grant, http://lingart.elte.hu/en).

UTI (Ultrasound Tongue Imaging), EMA (Electromagnetic Articulography), MRI (Magnetic Resonance Imaging) are technologies which can be used to acquire articulatory data during speech production, e.g. https://sail.usc.edu/span/rtmri_ipa/index.html With these devices we can record high resolution images, and/or multichannel signals which can pose numerous challenges in terms of signal processing. The task of the student is to investigate deep learning (e.g. deep neural network, AutoEncoder, GAN) solutions, compare the various articulatory techniques, and apply this for the SSI (Silent Speech Interface) topic. Suggested programming languages: Python / Octave. The research will be conducted in collaboration with the MTA-ELTE Lingual Articulation Research Group (Momemtum grant, http://lingart.elte.hu/en).