László Tóth

ORCID

Publication Activity (10 Years)

Years Active: 1997-2023
Publications (10 Years): 68

Top Venues

Publications

László Tóth, Amin Honarmandi Shandiz, Gábor Gosztolya, Tamás Gábor Csapó
Adaptation of Tongue Ultrasound-Based Silent Speech Interfaces Using Spatial Transformer Networks. CoRR (2023)
László Tóth, Amin Honarmandi Shandiz, Gábor Gosztolya, Tamás Gábor Csapó
Adaptation of Tongue Ultrasound-Based Silent Speech Interfaces Using Spatial Transformer Networks. INTERSPEECH (2023)
Tamás Gábor Csapó, Gábor Gosztolya, László Tóth, Amin Honarmandi Shandiz, Alexandra Markó
Optimizing the Ultrasound Tongue Image Representation for Residual Network-Based Articulatory-to-Acoustic Mapping. Sensors 22 (22) (2022)
José Vicente Egas López, Réka Balogh, Nóra Imre, Ildikó Hoffmann, Martina Katalin Szabó, László Tóth, Magdolna Pákáski, János Kálmán, Gábor Gosztolya
Automatic screening of mild cognitive impairment and Alzheimer's disease by means of posterior-thresholding hesitation representation. Comput. Speech Lang. 75 (2022)
Amin Honarmandi Shandiz, László Tóth
Improved Processing of Ultrasound Tongue Videos by Combining ConvLSTM and 3D Convolutional Networks. IEA/AIE (2022)
Mercedes Vetráb, José Vicente Egas López, Réka Balogh, Nóra Imre, Ildikó Hoffmann, László Tóth, Magdolna Pákáski, János Kálmán, Gábor Gosztolya
Using Spectral Sequence-to-Sequence Autoencoders to Assess Mild Cognitive Impairment. ICASSP (2022)
Veronika Vincze, Martina Katalin Szabó, Ildikó Hoffmann, László Tóth, Magdolna Pákáski, János Kálmán, Gábor Gosztolya
Linguistic Parameters of Spontaneous Speech for Identifying Mild Cognitive Impairment and Alzheimer Disease. Comput. Linguistics 48 (1) (2022)
Gábor Gosztolya, László Tóth, Veronika Svindt, Judit Bóna, Ildikó Hoffmann
Using Acoustic Deep Neural Network Embeddings to Detect Multiple Sclerosis From Speech. ICASSP (2022)
Amin Honarmandi Shandiz, László Tóth
Improved Processing of Ultrasound Tongue Videos by Combining ConvLSTM and 3D Convolutional Networks. CoRR (2022)
Amin Honarmandi Shandiz, László Tóth, Gábor Gosztolya, Alexandra Markó, Tamás Gábor Csapó
Neural Speaker Embeddings for Ultrasound-Based Silent Speech Interfaces. Interspeech (2021)
Amin Honarmandi Shandiz, László Tóth, Gábor Gosztolya, Alexandra Markó, Tamás Gábor Csapó
Improving Neural Silent Speech Interface Models by Adversarial Training. AICV (2021)
Amin Honarmandi Shandiz, László Tóth
Voice Activity Detection for Ultrasound-based Silent Speech Interfaces using Convolutional Neural Networks. CoRR (2021)
Amin Honarmandi Shandiz, László Tóth
Voice Activity Detection for Ultrasound-Based Silent Speech Interfaces Using Convolutional Neural Networks. TDS (2021)
Gábor Gosztolya, Réka Balogh, Nóra Imre, José Vicente Egas López, Ildikó Hoffmann, Veronika Vincze, László Tóth, Davangere P. Devanand, Magdolna Pákáski, János Kálmán
Cross-lingual detection of mild cognitive impairment based on temporal parameters of spontaneous speech. Comput. Speech Lang. 69 (2021)
Csaba Zainkó, László Tóth, Amin Honarmandi Shandiz, Gábor Gosztolya, Alexandra Markó, Géza Németh, Tamás Gábor Csapó
Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging. CoRR (2021)
Amin Honarmandi Shandiz, László Tóth, Gábor Gosztolya, Alexandra Markó, Tamás Gábor Csapó
Neural Speaker Embeddings for Ultrasound-based Silent Speech Interfaces. CoRR (2021)
Csaba Zainkó, László Tóth, Amin Honarmandi Shandiz, Gábor Gosztolya, Alexandra Markó, Géza Németh, Tamás Gábor Csapó
Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging. SSW (2021)
Yide Yu, Amin Honarmandi Shandiz, László Tóth
Reconstructing Speech from Real-Time Articulatory MRI Using Neural Vocoders. CoRR (2021)
Tamás Gábor Csapó, László Tóth, Gábor Gosztolya, Alexandra Markó
Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input. SSW (2021)
Tamás Gábor Csapó, László Tóth, Gábor Gosztolya, Alexandra Markó
Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input. CoRR (2021)
Yide Yu, Amin Honarmandi Shandiz, László Tóth
Reconstructing Speech from Real-Time Articulatory MRI Using Neural Vocoders. EUSIPCO (2021)
Amin Honarmandi Shandiz, László Tóth, Gábor Gosztolya, Alexandra Markó, Tamás Gábor Csapó
Improving Neural Silent Speech Interface Models by Adversarial Training. CoRR (2021)
José Vicente Egas López, Mercedes Vetráb, László Tóth, Gábor Gosztolya
Identifying Conflict Escalation and Primates by Using Ensemble X-Vectors and Fisher Vector Features. Interspeech (2021)
László Tóth, Amin Honarmandi Shandiz
3D Convolutional Neural Networks for Ultrasound-Based Silent Speech Interfaces. CoRR (2021)
László Tóth, Balázs Nagy, Tibor Gyimóthy, László Vidács
Mining Hypernyms Semantic Relations from Stack Overflow. ICSE (Workshops) (2020)
Tamás Gábor Csapó, Csaba Zainkó, László Tóth, Gábor Gosztolya, Alexandra Markó
Ultrasound-Based Articulatory-to-Acoustic Mapping with WaveGlow Speech Synthesis. INTERSPEECH (2020)
Gábor Gosztolya, László Tóth
Applying Speech Tempo-Derived Features, BoAW and Fisher Vectors to Detect Elderly Emotion and Speech in Surgical Masks. CoRR (2020)
László Tóth, Amin Honarmandi Shandiz
3D Convolutional Neural Networks for Ultrasound-Based Silent Speech Interfaces. ICAISC (1) (2020)
Tamás Gábor Csapó, Csaba Zainkó, László Tóth, Gábor Gosztolya, Alexandra Markó
Ultrasound-based Articulatory-to-Acoustic Mapping with WaveGlow Speech Synthesis. CoRR (2020)
Gábor Gosztolya, Tamás Grósz, László Tóth
Social Signal Detection by Probabilistic Sampling DNN Training. IEEE Trans. Affect. Comput. 11 (1) (2020)
Gábor Gosztolya, Ádám Pintér, László Tóth, Tamás Grósz, Alexandra Markó, Tamás Gábor Csapó
Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent Speech Interfaces. IJCNN (2019)
Tamás Gábor Csapó, Mohammed Salah Al-Radhi, Géza Németh, Gábor Gosztolya, Tamás Grósz, László Tóth, Alexandra Markó
Ultrasound-based Silent Speech Interface Built on a Continuous Vocoder. CoRR (2019)
Gábor Gosztolya, Veronika Vincze, László Tóth, Magdolna Pákáski, János Kálmán, Ildikó Hoffmann
Identifying Mild Cognitive Impairment and mild Alzheimer's disease based on spontaneous speech using ASR and linguistic features. Comput. Speech Lang. 53 (2019)
Gábor Gosztolya, László Tóth
Calibrating DNN Posterior Probability Estimates of HMM/DNN Models to Improve Social Signal Detection from Audio Data. INTERSPEECH (2019)
György Kovács, László Tóth, Dirk Van Compernolle, Marcus Liwicki
Examining the Combination of Multi-Band Processing and Channel Dropout for Robust Speech Recognition. INTERSPEECH (2019)
László Tóth, Gábor Gosztolya
Reducing the Inter-speaker Variance of CNN Acoustic Models Using Unsupervised Adversarial Multi-task Training. SPECOM (2019)
Tamás Gábor Csapó, Mohammed Salah Al-Radhi, Géza Németh, Gábor Gosztolya, Tamás Grósz, László Tóth, Alexandra Markó
Ultrasound-Based Silent Speech Interface Built on a Continuous Vocoder. INTERSPEECH (2019)
Gábor Gosztolya, Ádám Pintér, László Tóth, Tamás Grósz, Alexandra Markó, Tamás Gábor Csapó
Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent Speech Interfaces. CoRR (2019)
Nóra Imre, Réka Balogh, Gábor Gosztolya, László Tóth, Tamás Várkonyi, Csaba Lengyel, Magdolna Pákáski, János Kálmán
Automatic recognition of temporal speech features in type 2 diabetes mellitus with mild cognitive impairment. CogInfoCom (2019)
José Vicente Egas López, László Tóth, Ildikó Hoffmann, János Kálmán, Magdolna Pákáski, Gábor Gosztolya
Assessing Alzheimer's Disease from Speech Using the i-vector Approach. SPECOM (2019)
László Tóth, Gábor Gosztolya, Tamás Grósz, Alexandra Markó, Tamás Gábor Csapó
Multi-Task Learning of Speech Recognition and Speech Synthesis Parameters for Ultrasound-based Silent Speech Interfaces. INTERSPEECH (2018)
Tamás Grósz, Gábor Gosztolya, László Tóth, Tamás Gábor Csapó, Alexandra Markó
F0 Estimation for DNN-Based Ultrasound Silent Speech Interfaces. ICASSP (2018)
György Kovács, László Tóth, Gábor Gosztolya
Multi-Band Processing With Gabor Filters and Time Delay Neural Nets for Noise Robust Speech Recognition. SLT (2018)
Gábor Gosztolya, László Tóth
A feature selection-based speaker clustering method for paralinguistic tasks. Pattern Anal. Appl. 21 (1) (2018)
Péter Bodnár, Tamás Grósz, László Tóth, László G. Nyúl
Efficient visual code localization with neural networks. Pattern Anal. Appl. 21 (1) (2018)
László Tóth, György Kovács, Dirk Van Compernolle
A Perceptually Inspired Data Augmentation Method for Noise Robust CNN Acoustic Models. SPECOM (2018)
Gábor Gosztolya, Tamás Grósz, László Tóth
General Utterance-Level Feature Extraction for Classifying Crying Sounds, Atypical & Self-Assessed Affect and Heart Beats. INTERSPEECH (2018)
Tamás Grósz, Gábor Gosztolya, László Tóth
Training Context-Dependent DNN Acoustic Models Using Probabilistic Sampling. INTERSPEECH (2017)
Gábor Gosztolya, Róbert Busa-Fekete, Tamás Grósz, László Tóth
DNN-Based Feature Extraction and Classifier Combination for Child-Directed Speech, Cold and Snoring Identification. INTERSPEECH (2017)
László Tóth
Multi-resolution spectral input for convolutional neural network-based speech recognition. SpeD (2017)
Tamás Gábor Csapó, Tamás Grósz, Gábor Gosztolya, László Tóth, Alexandra Markó
DNN-Based Ultrasound-to-Speech Conversion for a Silent Speech Interface. INTERSPEECH (2017)
Tamás Grósz, Gábor Gosztolya, László Tóth
A Comparative Evaluation of GMM-Free State Tying Methods for ASR. INTERSPEECH (2017)
György Kovács, László Tóth, Dirk Van Compernolle, Sriram Ganapathy
Increasing the robustness of CNN acoustic models using autoregressive moving average spectrogram features and channel dropout. Pattern Recognit. Lett. 100 (2017)
Gábor Gosztolya, László Tóth
DNN-Based Feature Extraction for Conflict Intensity Estimation From Speech. IEEE Signal Process. Lett. 24 (12) (2017)
László Tóth, Gábor Gosztolya
Adaptation of DNN Acoustic Models Using KL-divergence Regularization and Multi-task Training. SPECOM (2016)
Gábor Gosztolya, László Tóth, Tamás Grósz, Veronika Vincze, Ildikó Hoffmann, Gréta Szatlóczki, Magdolna Pákáski, János Kálmán
Detecting Mild Cognitive Impairment from Spontaneous Speech by Correlation-Based Phonetic Feature Selection. INTERSPEECH (2016)
Gábor Gosztolya, Tamás Grósz, György Szaszák, László Tóth
Estimating the Sincerity of Apologies in Speech by DNN Rank Learning and Prosodic Analysis. INTERSPEECH (2016)
Gábor Gosztolya, Tamás Grósz, Róbert Busa-Fekete, László Tóth
Determining Native Language and Deception Using Phonetic Features and Classifier Combination. INTERSPEECH (2016)
Gábor Gosztolya, Tamás Grósz, László Tóth
GMM-Free Flat Start Sequence-Discriminative DNN Training. INTERSPEECH (2016)
Gábor Gosztolya, Tamás Grósz, László Tóth
GMM-Free Flat Start Sequence-Discriminative DNN Training. CoRR (2016)
Veronika Vincze, Gábor Gosztolya, László Tóth, Ildikó Hoffmann, Gréta Szatlóczki, Zoltán Bánréti, Magdolna Pákáski, János Kálmán
Detecting Mild Cognitive Impairment by Exploiting Linguistic Information from Transcripts. ACL (2) (2016)
Tamás Grósz, Róbert Busa-Fekete, Gábor Gosztolya, László Tóth
Assessing the degree of nativeness and parkinson's condition using Gaussian processes and deep rectifier neural networks. INTERSPEECH (2015)
György Kovács, László Tóth, Dirk Van Compernolle
Selection and enhancement of Gabor filters for automatic speech recognition. Int. J. Speech Technol. 18 (1) (2015)
László Tóth
Phone recognition with hierarchical convolutional deep maxout networks. EURASIP J. Audio Speech Music. Process. 2015 (2015)
György Kovács, László Tóth
Joint Optimization of Spectro-Temporal Features and Deep Neural Nets for Robust Automatic Speech Recognition. Acta Cybern. 22 (1) (2015)
László Tóth, Gábor Gosztolya, Veronika Vincze, Ildikó Hoffmann, Gréta Szatlóczki, Edit Biró, Fruzsina Zsura, Magdolna Pákáski, János Kálmán
Automatic detection of mild cognitive impairment from spontaneous speech using ASR. INTERSPEECH (2015)
Gábor Gosztolya, Tamás Grósz, László Tóth, David Imseng
Building context-dependent DNN acoustic models using Kullback-Leibler divergence-based state tying. ICASSP (2015)
László Tóth
Modeling long temporal contexts in convolutional neural network-based phone recognition. ICASSP (2015)
Tamás Grósz, Gábor Gosztolya, László Tóth
A Sequence Training Method for Deep Rectifier Neural Networks in Speech Recognition. SPECOM (2014)
Gábor Gosztolya, Tamás Grósz, Róbert Busa-Fekete, László Tóth
Detecting the intensity of cognitive and physical load using AdaBoost and deep rectifier neural networks. INTERSPEECH (2014)
György Kovács, László Tóth, Tamás Grósz
Robust Multi-Band ASR Using Deep Neural Nets and Spectro-temporal Features. SPECOM (2014)
László Tóth
Convolutional deep maxout networks for phone recognition. INTERSPEECH (2014)
László Tóth
Combining time- and frequency-domain convolution in convolutional neural network-based phone recognition. ICASSP (2014)
Péter Bodnár, Tamás Grósz, László Tóth, László G. Nyúl
Localization of Visual Codes in the DCT Domain Using Deep Rectifier Neural Networks. ANNIIP (2014)
Tamás Grósz, Péter Bodnár, László Tóth, László G. Nyúl
QR code localization using deep neural networks. MLSP (2014)
László Tóth
Phone recognition with deep sparse rectifier neural networks. ICASSP (2013)
László Tóth, Tamás Grósz
A Comparison of Deep Neural Network Training Methods for Large Vocabulary Speech Recognition. TSD (2013)
György Kovács, László Tóth
The Joint Optimization of Spectro-Temporal Features and Neural Net Classifiers. TSD (2013)
Gábor Gosztolya, Róbert Busa-Fekete, László Tóth
Detecting autism, emotions and social signals using adaboost. INTERSPEECH (2013)
László Tóth
Convolutional deep rectifier neural nets for phone recognition. INTERSPEECH (2013)
György Kovács, László Tóth
Phone recognition experiments with 2D-DCT spectro-temporal features. SACI (2011)
Gábor Gosztolya, György Kovács, László Tóth
Spoken term detection from noisy input. SACI (2011)
László Tóth
A hierarchical, context-dependent neural network architecture for improved phone recognition. ICASSP (2011)
László Tóth, Balázs Tarján, Gellért Sárosi, Péter Mihajlik
Speech Recognition Experiments with Audiobooks. Acta Cybern. 19 (4) (2010)
Gábor Gosztolya, András Bánhalmi, László Tóth
Using One-Class Classification Techniques in the Anti-phoneme Problem. IbPRIA (2009)
László Tóth, Joe Frankel, Gábor Gosztolya, Simon King
Cross-lingual portability of MLP-based tandem features - a case study for English and Hungarian. INTERSPEECH (2008)
Gábor Gosztolya, László Tóth
Detection of Phoneme Boundaries Using Spiking Neurons. ICAISC (2008)
László Tóth, András Kocsor
A segment-based interpretation of HMM/ANN hybrids. Comput. Speech Lang. 21 (3) (2007)
András Bánhalmi, Dénes Paczolay, László Tóth, András Kocsor
Development of a Hungarian Medical Dictation System. Informatica (Slovenia) 31 (2) (2007)
László Tóth
Benchmarking human performance on the acoustic and linguistic subtasks of ASR systems. INTERSPEECH (2007)
András Bánhalmi, Dénes Paczolay, László Tóth, András Kocsor
Investigating the robustness of a Hungarian medical dictation system under various conditions. Int. J. Speech Technol. 9 (3-4) (2006)
András Bánhalmi, Kornél Kovács, András Kocsor, László Tóth
Fundamental frequency estimation by least-squares harmonic model fitting. INTERSPEECH (2005)
László Tóth, András Kocsor
Training HMM/ANN Hybrid Speech Recognizers by Probabilistic Sampling. ICANN (1) (2005)
László Tóth, András Kocsor
Explicit Duration Modelling in HMM/ANN Hybrids. TSD (2005)
Gyula Zsigri, András Kocsor, László Tóth, Györgyi Sejtes
Phonetic Level Annotation and Segmentation of Hungarian Speech Databases. Acta Cybern. 16 (4) (2004)
László Tóth, András Kocsor, Gábor Gosztolya
Telephone Speech Recognition via the Combination of Knowledge Sources in a Segmental Speech Model. Acta Cybern. 16 (4) (2004)
László Tóth, Gábor Gosztolya
Replicator Neural Networks for Outlier Modeling in Segmental Speech Recognition. ISNN (1) (2004)
András Kocsor, László Tóth
Kernel-based feature extraction with a speech technology application. IEEE Trans. Signal Process. 52 (8) (2004)
András Kocsor, László Tóth
Application of Kernel-Based Feature Space Transformations and Learning Methods to Phoneme Classification. Appl. Intell. 21 (2) (2004)
László Tóth, András Kocsor
Harmonic alternatives to sine-wave speech. INTERSPEECH (2003)

László Tóth.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

László Tóth