L
László Tóth
Researcher at University of Szeged
Publications - 140
Citations - 2042
László Tóth is an academic researcher from University of Szeged. The author has contributed to research in topics: Artificial neural network & Hidden Markov model. The author has an hindex of 22, co-authored 131 publications receiving 1654 citations. Previous affiliations of László Tóth include Hungarian Academy of Sciences.
Papers
More filters
Journal ArticleDOI
A Speech Recognition-based Solution for the Automatic Detection of Mild Cognitive Impairment from Spontaneous Speech.
László Tóth,Ildikó Hoffmann,Gábor Gosztolya,Veronika Vincze,Gréta Szatlóczki,Zoltán Bánréti,Magdolna Pákáski,János Kálmán +7 more
TL;DR: The temporal analysis of spontaneous speech can be exploited in implementing a new, auto-matic detection-based tool for screening MCI for the community.
Journal ArticleDOI
Identifying Mild Cognitive Impairment and mild Alzheimer’s disease based on spontaneous speech using ASR and linguistic features
Gábor Gosztolya,Veronika Vincze,László Tóth,Magdolna Pákáski,János Kálmán,Ildikó Hoffmann,Ildikó Hoffmann +6 more
TL;DR: An automatic speech recognition based procedure for the extraction of a special set of acoustic features and a linguistic feature set that is extracted from the transcripts of the same speech signals to tell apart Alzheimer’s patients from those with mild cognitive impairment.
Journal ArticleDOI
Effect of pH on stability and plasmonic properties of cysteine-functionalized silver nanoparticle dispersion
Edit Csapó,Rita Patakfalvi,Viktória Hornok,László Tóth,Áron Sipos,Anikó Szalai,Mária Csete,Imre Dékány,Imre Dékány +8 more
TL;DR: Electrostatic interaction arose between the deprotonated carboxylate (COO(-)) and protonated amino groups (NH(3)(+)) of the amino acid resulting in cross-linking network of the Ag NPs between pH ~3 and 7.
Proceedings ArticleDOI
Combining time- and frequency-domain convolution in convolutional neural network-based phone recognition
TL;DR: The two network architectures, convolution along the frequency axis and time-domain convolution, can be readily combined and report an error rate of 16.7% on the TIMIT phone recognition task, a new record on this dataset.
Journal ArticleDOI
Phone recognition with hierarchical convolutional deep maxout networks
TL;DR: It is shown that with the hierarchical modelling approach, the CNN can reduce the error rate of the network on an expanded context of input, and it is found that all the proposed modelling improvements give consistently better results for this larger database as well.