László Tóth is an associate professor at the Department of Algorithms and Artificial Intelligence, Institute of Informatics. He obtained the MSc and PhD degrees from the University of Szeged, after which he joined the Research Group on Artificial Intelligence of the Hungarian Academy of Sciences and the University of Szeged University of Szeged. His main research interests are speech recognition, machine learning and signal processing. Currently, he is focusing on the application of the latest deep neural networks (DNNs) to speech technology, including the most recent DNN technologies such as adversarial learning, or transformers.

Selected publications

  • L Tóth, I Hoffmann, G Gosztolya, V Vincze, G Szatlóczki, Z Bánréti et al: A speech recognition-based solution for the automatic detection of mild cognitive impairment from spontaneous speech, Current Alzheimer Research 15 (2), 130-138, 2018.
  • L Tóth: Phone recognition with hierarchical convolutional deep maxout networks, EURASIP Journal on Audio, Speech, and Music Processing (1), 1-13, 2015.
  • L Tóth: Phone recognition with deep sparse rectifier neural networks, IEEE International Conference on Acoustics, Speech and Signal Procesing, pp. 6985-6989, 2013.