László Tóth

According to our database, László Tóth authored at least 97 papers between 1997 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2023

Adaptation of Tongue Ultrasound-Based Silent Speech Interfaces Using Spatial Transformer Networks.

László Tóth, Amin Honarmandi Shandiz, Gábor Gosztolya, Tamás Gábor Csapó

CoRR, 2023

2022

Optimizing the Ultrasound Tongue Image Representation for Residual Network-Based Articulatory-to-Acoustic Mapping.

Tamás Gábor Csapó, Gábor Gosztolya, László Tóth, Amin Honarmandi Shandiz, Alexandra Markó

Sensors, 2022

Automatic screening of mild cognitive impairment and Alzheimer's disease by means of posterior-thresholding hesitation representation.

José Vicente Egas López, Réka Balogh, Nóra Imre, Ildikó Hoffmann, Martina Katalin Szabó, László Tóth, Magdolna Pákáski, János Kálmán, Gábor Gosztolya

Comput. Speech Lang., 2022

Linguistic Parameters of Spontaneous Speech for Identifying Mild Cognitive Impairment and Alzheimer Disease.

Veronika Vincze, Martina Katalin Szabó, Ildikó Hoffmann, László Tóth, Magdolna Pákáski, János Kálmán, Gábor Gosztolya

Comput. Linguistics, 2022

Improved Processing of Ultrasound Tongue Videos by Combining ConvLSTM and 3D Convolutional Networks.

Amin Honarmandi Shandiz, László Tóth

Proceedings of the Advances and Trends in Artificial Intelligence. Theory and Practices in Artificial Intelligence, 2022

Using Spectral Sequence-to-Sequence Autoencoders to Assess Mild Cognitive Impairment.

Mercedes Vetráb, José Vicente Egas López, Réka Balogh, Nóra Imre, Ildikó Hoffmann, László Tóth, Magdolna Pákáski, János Kálmán, Gábor Gosztolya

Proceedings of the IEEE International Conference on Acoustics, 2022

Using Acoustic Deep Neural Network Embeddings to Detect Multiple Sclerosis From Speech.

Gábor Gosztolya, László Tóth, Veronika Svindt, Judit Bóna, Ildikó Hoffmann

Proceedings of the IEEE International Conference on Acoustics, 2022

Depthwise Convolutions using Physicochemical Features of DNA for Transcription Factor Binding Site Classification: Physicochemical Features for DNA-Protein Classification with Depthwise Convolutions.

Gergely Pap, Krisztian Adam, Zoltan Gyorgypal, László Tóth, Zoltan Hegedus

Proceedings of the 2022 The 6th International Conference on Advances in Artificial Intelligence, 2022

2021

Cross-lingual detection of mild cognitive impairment based on temporal parameters of spontaneous speech.

Gábor Gosztolya, Réka Balogh, Nóra Imre, José Vicente Egas López, Ildikó Hoffmann, Veronika Vincze, László Tóth, Davangere P. Devanand, Magdolna Pákáski, János Kálmán

Comput. Speech Lang., 2021

Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging.

Csaba Zainkó, László Tóth, Amin Honarmandi Shandiz, Gábor Gosztolya, Alexandra Markó, Géza Németh, Tamás Gábor Csapó

CoRR, 2021

Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input.

Tamás Gábor Csapó, László Tóth, Gábor Gosztolya, Alexandra Markó

CoRR, 2021

Voice Activity Detection for Ultrasound-Based Silent Speech Interfaces Using Convolutional Neural Networks.

Amin Honarmandi Shandiz, László Tóth

Proceedings of the Text, Speech, and Dialogue - 24th International Conference, 2021

Neural Speaker Embeddings for Ultrasound-Based Silent Speech Interfaces.

Amin Honarmandi Shandiz, László Tóth, Gábor Gosztolya, Alexandra Markó, Tamás Gábor Csapó

Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

Identifying Conflict Escalation and Primates by Using Ensemble X-Vectors and Fisher Vector Features.

José Vicente Egas López, Mercedes Vetráb, László Tóth, Gábor Gosztolya

Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

Reconstructing Speech from Real-Time Articulatory MRI Using Neural Vocoders.

Yide Yu, Amin Honarmandi Shandiz, László Tóth

Proceedings of the 29th European Signal Processing Conference, 2021

Improving Neural Silent Speech Interface Models by Adversarial Training.

Amin Honarmandi Shandiz, László Tóth, Gábor Gosztolya, Alexandra Markó, Tamás Gábor Csapó

Proceedings of the International Conference on Artificial Intelligence and Computer Vision, 2021

2020

Social Signal Detection by Probabilistic Sampling DNN Training.

Gábor Gosztolya, Tamás Grósz, László Tóth

IEEE Trans. Affect. Comput., 2020

Applying Speech Tempo-Derived Features, BoAW and Fisher Vectors to Detect Elderly Emotion and Speech in Surgical Masks.

Gábor Gosztolya, László Tóth

CoRR, 2020

Ultrasound-Based Articulatory-to-Acoustic Mapping with WaveGlow Speech Synthesis.

Tamás Gábor Csapó, Csaba Zainkó, László Tóth, Gábor Gosztolya, Alexandra Markó

Proceedings of the Interspeech 2020, 2020

Mining Hypernyms Semantic Relations from Stack Overflow.

László Tóth, Balázs Nagy, Tibor Gyimóthy, László Vidács

Proceedings of the ICSE '20: 42nd International Conference on Software Engineering, Workshops, Seoul, Republic of Korea, 27 June, 2020

3D Convolutional Neural Networks for Ultrasound-Based Silent Speech Interfaces.

László Tóth, Amin Honarmandi Shandiz

Proceedings of the Artificial Intelligence and Soft Computing, 2020

2019

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

Comput. Speech Lang., 2019

Reducing the Inter-speaker Variance of CNN Acoustic Models Using Unsupervised Adversarial Multi-task Training.

László Tóth, Gábor Gosztolya

Proceedings of the Speech and Computer - 21st International Conference, 2019

Assessing Alzheimer's Disease from Speech Using the i-vector Approach.

José Vicente Egas López, László Tóth, Ildikó Hoffmann, János Kálmán, Magdolna Pákáski, Gábor Gosztolya

Proceedings of the Speech and Computer - 21st International Conference, 2019

Examining the Combination of Multi-Band Processing and Channel Dropout for Robust Speech Recognition.

György Kovács, László Tóth, Dirk Van Compernolle, Marcus Liwicki

Proceedings of the Interspeech 2019, 2019

Calibrating DNN Posterior Probability Estimates of HMM/DNN Models to Improve Social Signal Detection from Audio Data.

Gábor Gosztolya, László Tóth

Proceedings of the Interspeech 2019, 2019

Ultrasound-Based Silent Speech Interface Built on a Continuous Vocoder.

Tamás Gábor Csapó, Mohammed Salah Al-Radhi, Géza Németh, Gábor Gosztolya, Tamás Grósz, László Tóth, Alexandra Markó

Proceedings of the Interspeech 2019, 2019

Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent Speech Interfaces.

Gábor Gosztolya, Ádám Pintér, László Tóth, Tamás Grósz, Alexandra Markó, Tamás Gábor Csapó

Proceedings of the International Joint Conference on Neural Networks, 2019

Automatic recognition of temporal speech features in type 2 diabetes mellitus with mild cognitive impairment.

Nóra Imre, Réka Balogh, Gábor Gosztolya, László Tóth, Tamás Várkonyi, Csaba Lengyel, Magdolna Pákáski, János Kálmán

Proceedings of the 10th IEEE International Conference on Cognitive Infocommunications, 2019

2018

A feature selection-based speaker clustering method for paralinguistic tasks.

Gábor Gosztolya, László Tóth

Pattern Anal. Appl., 2018

Efficient visual code localization with neural networks.

Péter Bodnár, Tamás Grósz, László Tóth, László G. Nyúl

Pattern Anal. Appl., 2018

A Perceptually Inspired Data Augmentation Method for Noise Robust CNN Acoustic Models.

László Tóth, György Kovács, Dirk Van Compernolle

Proceedings of the Speech and Computer - 20th International Conference, 2018

Multi-Band Processing With Gabor Filters and Time Delay Neural Nets for Noise Robust Speech Recognition.

György Kovács, László Tóth, Gábor Gosztolya

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

Multi-Task Learning of Speech Recognition and Speech Synthesis Parameters for Ultrasound-based Silent Speech Interfaces.

László Tóth, Gábor Gosztolya, Tamás Grósz, Alexandra Markó, Tamás Gábor Csapó

Proceedings of the Interspeech 2018, 2018

General Utterance-Level Feature Extraction for Classifying Crying Sounds, Atypical & Self-Assessed Affect and Heart Beats.

Gábor Gosztolya, Tamás Grósz, László Tóth

Proceedings of the Interspeech 2018, 2018

F0 Estimation for DNN-Based Ultrasound Silent Speech Interfaces.

Tamás Grósz, Gábor Gosztolya, László Tóth, Tamás Gábor Csapó, Alexandra Markó

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

DNN-Based Feature Extraction for Conflict Intensity Estimation From Speech.

Gábor Gosztolya, László Tóth

IEEE Signal Process. Lett., 2017

Increasing the robustness of CNN acoustic models using autoregressive moving average spectrogram features and channel dropout.

György Kovács, László Tóth, Dirk Van Compernolle, Sriram Ganapathy

Pattern Recognit. Lett., 2017

Multi-resolution spectral input for convolutional neural network-based speech recognition.

László Tóth

Proceedings of the International Conference on Speech Technology and Human-Computer Dialogue, 2017

A Comparative Evaluation of GMM-Free State Tying Methods for ASR.

Tamás Grósz, Gábor Gosztolya, László Tóth

Proceedings of the Interspeech 2017, 2017

Training Context-Dependent DNN Acoustic Models Using Probabilistic Sampling.

Tamás Grósz, Gábor Gosztolya, László Tóth

Proceedings of the Interspeech 2017, 2017

DNN-Based Feature Extraction and Classifier Combination for Child-Directed Speech, Cold and Snoring Identification.

Gábor Gosztolya, Róbert Busa-Fekete, Tamás Grósz, László Tóth

Proceedings of the Interspeech 2017, 2017

DNN-Based Ultrasound-to-Speech Conversion for a Silent Speech Interface.

Tamás Gábor Csapó, Tamás Grósz, Gábor Gosztolya, László Tóth, Alexandra Markó

Proceedings of the Interspeech 2017, 2017

2016

Adaptation of DNN Acoustic Models Using KL-divergence Regularization and Multi-task Training.

László Tóth, Gábor Gosztolya

Proceedings of the Speech and Computer - 18th International Conference, 2016

Detecting Mild Cognitive Impairment from Spontaneous Speech by Correlation-Based Phonetic Feature Selection.

Gábor Gosztolya, László Tóth, Tamás Grósz, Veronika Vincze, Ildikó Hoffmann, Gréta Szatlóczki, Magdolna Pákáski, János Kálmán

Proceedings of the Interspeech 2016, 2016

GMM-Free Flat Start Sequence-Discriminative DNN Training.

Gábor Gosztolya, Tamás Grósz, László Tóth

Proceedings of the Interspeech 2016, 2016

Estimating the Sincerity of Apologies in Speech by DNN Rank Learning and Prosodic Analysis.

Gábor Gosztolya, Tamás Grósz, György Szaszák, László Tóth

Proceedings of the Interspeech 2016, 2016

Determining Native Language and Deception Using Phonetic Features and Classifier Combination.

Gábor Gosztolya, Tamás Grósz, Róbert Busa-Fekete, László Tóth

Proceedings of the Interspeech 2016, 2016

Detecting Mild Cognitive Impairment by Exploiting Linguistic Information from Transcripts.

Veronika Vincze, Gábor Gosztolya, László Tóth, Ildikó Hoffmann, Gréta Szatlóczki, Zoltán Bánréti, Magdolna Pákáski, János Kálmán

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016

2015

Selection and enhancement of Gabor filters for automatic speech recognition.

György Kovács, László Tóth, Dirk Van Compernolle

Int. J. Speech Technol., 2015

Phone recognition with hierarchical convolutional deep maxout networks.

László Tóth

EURASIP J. Audio Speech Music. Process., 2015

Joint Optimization of Spectro-Temporal Features and Deep Neural Nets for Robust Automatic Speech Recognition.

György Kovács, László Tóth

Acta Cybern., 2015

Automatic detection of mild cognitive impairment from spontaneous speech using ASR.

László Tóth, Gábor Gosztolya, Veronika Vincze, Ildikó Hoffmann, Gréta Szatlóczki, Edit Biró, Fruzsina Zsura, Magdolna Pákáski, János Kálmán

Proceedings of the INTERSPEECH 2015, 2015

Assessing the degree of nativeness and parkinson's condition using Gaussian processes and deep rectifier neural networks.

Tamás Grósz, Róbert Busa-Fekete, Gábor Gosztolya, László Tóth

Proceedings of the INTERSPEECH 2015, 2015

Modeling long temporal contexts in convolutional neural network-based phone recognition.

László Tóth

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Building context-dependent DNN acoustic models using Kullback-Leibler divergence-based state tying.

Gábor Gosztolya, Tamás Grósz, László Tóth, David Imseng

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2014

Robust Multi-Band ASR Using Deep Neural Nets and Spectro-temporal Features.

György Kovács, László Tóth, Tamás Grósz

Proceedings of the Speech and Computer - 16th International Conference, 2014

A Sequence Training Method for Deep Rectifier Neural Networks in Speech Recognition.

Tamás Grósz, Gábor Gosztolya, László Tóth

Proceedings of the Speech and Computer - 16th International Conference, 2014

QR code localization using deep neural networks.

Tamás Grósz, Péter Bodnár, László Tóth, László G. Nyúl

Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing, 2014

Convolutional deep maxout networks for phone recognition.

László Tóth

Proceedings of the INTERSPEECH 2014, 2014

Detecting the intensity of cognitive and physical load using AdaBoost and deep rectifier neural networks.

Gábor Gosztolya, Tamás Grósz, Róbert Busa-Fekete, László Tóth

Proceedings of the INTERSPEECH 2014, 2014

Combining time- and frequency-domain convolution in convolutional neural network-based phone recognition.

László Tóth

Proceedings of the IEEE International Conference on Acoustics, 2014

Localization of Visual Codes in the DCT Domain Using Deep Rectifier Neural Networks.

Péter Bodnár, Tamás Grósz, László Tóth, László G. Nyúl

Proceedings of the International Workshop on Artificial Neural Networks and Intelligent Information Processing, 2014

2013

A Comparison of Deep Neural Network Training Methods for Large Vocabulary Speech Recognition.

László Tóth, Tamás Grósz

Proceedings of the Text, Speech, and Dialogue - 16th International Conference, 2013

The Joint Optimization of Spectro-Temporal Features and Neural Net Classifiers.

György Kovács, László Tóth

Proceedings of the Text, Speech, and Dialogue - 16th International Conference, 2013

Convolutional deep rectifier neural nets for phone recognition.

László Tóth

Proceedings of the INTERSPEECH 2013, 2013

Detecting autism, emotions and social signals using adaboost.

Gábor Gosztolya, Róbert Busa-Fekete, László Tóth

Proceedings of the INTERSPEECH 2013, 2013

Phone recognition with deep sparse rectifier neural networks.

László Tóth

Proceedings of the IEEE International Conference on Acoustics, 2013

2011

Phone recognition experiments with 2D-DCT spectro-temporal features.

György Kovács, László Tóth

Proceedings of the 6th IEEE International Symposium on Applied Computational Intelligence and Informatics, 2011

Spoken term detection from noisy input.

Gábor Gosztolya, György Kovács, László Tóth

Proceedings of the 6th IEEE International Symposium on Applied Computational Intelligence and Informatics, 2011

A hierarchical, context-dependent neural network architecture for improved phone recognition.

László Tóth

Proceedings of the IEEE International Conference on Acoustics, 2011

2010

Speech Recognition Experiments with Audiobooks.

László Tóth, Balázs Tarján, Gellért Sárosi, Péter Mihajlik

Acta Cybern., 2010

2009

Using One-Class Classification Techniques in the Anti-phoneme Problem.

Gábor Gosztolya, András Bánhalmi, László Tóth

Proceedings of the Pattern Recognition and Image Analysis, 4th Iberian Conference, 2009

2008

Cross-lingual portability of MLP-based tandem features - a case study for English and Hungarian.

László Tóth, Joe Frankel, Gábor Gosztolya, Simon King

Proceedings of the INTERSPEECH 2008, 2008

Detection of Phoneme Boundaries Using Spiking Neurons.

Gábor Gosztolya, László Tóth

Proceedings of the Artificial Intelligence and Soft Computing, 2008

2007

Development of a Hungarian Medical Dictation System.

András Bánhalmi, Dénes Paczolay, László Tóth, András Kocsor

Informatica (Slovenia), 2007

A segment-based interpretation of HMM/ANN hybrids.

László Tóth, András Kocsor

Comput. Speech Lang., 2007

Benchmarking human performance on the acoustic and linguistic subtasks of ASR systems.

László Tóth

Proceedings of the INTERSPEECH 2007, 2007

2006

Investigating the robustness of a Hungarian medical dictation system under various conditions.

András Bánhalmi, Dénes Paczolay, László Tóth, András Kocsor

Int. J. Speech Technol., 2006

2005

Explicit Duration Modelling in HMM/ANN Hybrids.

László Tóth, András Kocsor

Proceedings of the Text, Speech and Dialogue, 8th International Conference, 2005

Fundamental frequency estimation by least-squares harmonic model fitting.

András Bánhalmi, Kornél Kovács, András Kocsor, László Tóth

Proceedings of the INTERSPEECH 2005, 2005

Training HMM/ANN Hybrid Speech Recognizers by Probabilistic Sampling.

László Tóth, András Kocsor

Proceedings of the Artificial Neural Networks: Biological Inspirations, 2005

2004

Kernel-based feature extraction with a speech technology application.

András Kocsor, László Tóth

IEEE Trans. Signal Process., 2004

Application of Kernel-Based Feature Space Transformations and Learning Methods to Phoneme Classification.

András Kocsor, László Tóth

Appl. Intell., 2004

Phonetic Level Annotation and Segmentation of Hungarian Speech Databases.

Gyula Zsigri, András Kocsor, László Tóth, Györgyi Sejtes

Acta Cybern., 2004

Telephone Speech Recognition via the Combination of Knowledge Sources in a Segmental Speech Model.

László Tóth, András Kocsor, Gábor Gosztolya

Acta Cybern., 2004

Replicator Neural Networks for Outlier Modeling in Segmental Speech Recognition.

László Tóth, Gábor Gosztolya

Proceedings of the Advances in Neural Networks, 2004

2003

Various Robust Search Methods in a Hungarian Speech Recognition System.

Gábor Gosztolya, András Kocsor, László Tóth

Acta Cybern., 2003

Real-Time Vocal Tract Length Normalization.

Dénes Paczolay, András Kocsor, László Tóth

Proceedings of the Text, Speech and Dialogue, 6th International Conference, 2003

Harmonic alternatives to sine-wave speech.

László Tóth, András Kocsor

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

2002

Hungarian Speech Synthesis Using a Phase Exact HNM Approach.

Kornél Kovács, András Kocsor, László Tóth

Proceedings of the SOFSEM 2002: Theory and Practice of Informatics, 2002

2001

A Nonlinearized Discriminant Analysis and Its Application to Speech Impediment Therapy.

András Kocsor, László Tóth, Dénes Paczolay

Proceedings of the Text, Speech and Dialogue, 4th International Conference, 2001

Application of Feature Transformation and Learning Methods in Phoneme Classification.

András Kocsor, László Tóth, László Felföldi

Proceedings of the Engineering of Intelligent Systems, 2001

2000

A Comparative Study of Several Feature Transformation and Learning Methods for Phoneme Classification.

András Kocsor, László Tóth, András Kuba, Kornél Kovács, Márk Jelasity, Tibor Gyimóthy, János Csirik

Int. J. Speech Technol., 2000

A Discriminative Segmental Speech Model and Its Application to Hungarian Number Recognition.

László Tóth, András Kocsor, Kornél Kovács

Proceedings of the Text, Speech and Dialogue - Third International Workshop, 2000

1999

Optimal Parameters of a Sinusoidal Representation of Signals.

András Kocsor, László Tóth, I. Bálint

Acta Cybern., 1999

1997

Learning Phonetic Rules in a Speech Recognition System.

Zoltán Alexin, János Csirik, Tibor Gyimóthy, Márk Jelasity, László Tóth

Proceedings of the Inductive Logic Programming, 7th International Workshop, 1997