DAFT-Net: Dual Attention and Fast Tongue Contour Extraction Using Enhanced U-Net Architecture

X Wang, W Lu, H Liu, W Zhang, Q Li - Entropy, 2024 - mdpi.com
In most silent speech research, continuously observing tongue movements is crucial, thus
requiring the use of ultrasound to extract tongue contours. Precisely and in real-time …

A Neural Network Based Approach for Combining Ultrasound and MRI Data of 2-D Dynamic Records of Human Speech

R Trencsényi, L Czap - 2022 13th IEEE International …, 2022 - ieeexplore.ieee.org
We aim at exploring the geometrical information that can be extracted from dynamic two-
dimensional audiovisual records created by magnetic resonance imaging (MRI) and …

Extension to the Serial Vector Format Specification Supporting Testing of Analog Units of Safety-Critical Embedded Systems

J Kohut, Z Molnár - 2023 IEEE 6th International Conference and …, 2023 - ieeexplore.ieee.org
In safety-critical embedded systems, the built-in self-test is an important tool to increase
reliability. Embedded self-test solutions for digital circuits are much more sophisticated than …

Machine Learning Applied in Speech Science

R Trencsényi, L Czap - 2022 23rd International Carpathian …, 2022 - ieeexplore.ieee.org
We study the qualitative and quantitative information acquired from two-dimensional
dynamic audiovisual sources storing synchronized image and sound signals recorded …

Articulatory Data of Audiovisual Records of Speech Connected by Machine Learning

R Trencsényi, L Czap - 2022 IEEE 2nd Conference on …, 2022 - ieeexplore.ieee.org
The center of attraction of the present study is the application of neural networks for
combining data arising from dynamic audiovisual sources made by ultrasound and magnetic …