Gábor Gosztolya

According to our database, Gábor Gosztolya authored at least 94 papers between 2003 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Investigating the Utility of wav2vec 2.0 Hidden Layers for Detecting Multiple Sclerosis.

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

Proceedings of the Speech and Computer - 26th International Conference, 2024

Automatic Assessment of Signs of Alcohol Dependency Syndrome from Spontaneous Speech.

Gábor Gosztolya, András Bence Lázár, Ildikó Hoffmann, Otília Bagi, Fruzsina Fanni Farkas, Janka Gajdics, László Tóth, János Kálmán

Proceedings of the Speech and Computer - 26th International Conference, 2024

2023

Using Hybrid HMM/DNN Embedding Extractor Models in Computational Paralinguistic Tasks.

Mercedes Vetráb, Gábor Gosztolya

Sensors, 2023

Identifying Subjects Wearing a Mask from the Speech by Means of Encoded Speech Representations.

José Vicente Egas López, Gábor Gosztolya

Proceedings of the Text, Speech, and Dialogue - 26th International Conference, 2023

Data Augmentation Methods on Ultrasound Tongue Images for Articulation-to-Speech Synthesis.

Ibrahim Ibrahimov, Gábor Gosztolya, Tamás Gábor Csapó

Proceedings of the 12th ISCA Speech Synthesis Workshop, 2023

Aggregation Strategies of Wav2vec 2.0 Embeddings for Computational Paralinguistic Tasks.

Mercedes Vetráb, Gábor Gosztolya

Proceedings of the Speech and Computer - 25th International Conference, 2023

Using Custom X-vectors for the Automatic Screening of COVID-19 Based on Coughing Audio Samples.

José Vicente Egas López, Gábor Gosztolya

Proceedings of the 17th IEEE International Symposium on Applied Computational Intelligence and Informatics, 2023

Automated Multiple Sclerosis Screening Based on Encoded Speech Representations.

José Vicente Egas López, Veronika Svindt, Judit Bóna, Ildikó Hoffmann, Gábor Gosztolya

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

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

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

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 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

Estimating the degree of conflict in speech by employing Bag-of-Audio-Words and Fisher Vectors.

Gábor Gosztolya

Expert Syst. Appl., 2022

Optimizing class priors to improve the detection of social signals in audio data.

Gábor Gosztolya

Eng. Appl. Artif. Intell., 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

On the Use of Ensemble X-Vector Embeddings for Improved Sleepiness Detection.

José Vicente Egas López, Róbert Busa-Fekete, Gábor Gosztolya

Proceedings of the Speech and Computer - 24th International Conference, 2022

Identification of Subjects Wearing a Surgical Mask from Their Speech by Means of X-vectors and Fisher Vectors.

José Vicente Egas López, Gábor Gosztolya

Proceedings of the Modeling Decisions for 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

Automatic Assessment of the Degree of Clinical Depression from Speech Using X-Vectors.

José Vicente Egas López, Gábor Kiss, Dávid Sztahó, 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

2021

Ensemble Bag-of-Audio-Words Representation Improves Paralinguistic Classification Accuracy.

Gábor Gosztolya, Róbert Busa-Fekete

IEEE ACM Trans. Audio Speech Lang. Process., 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

Using the Fisher Vector Approach for Cold Identification.

José Vicente Egas López, Gábor Gosztolya

Acta Cybern., 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

Proceedings of the 11th ISCA Speech Synthesis Workshop, 2021

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

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

Proceedings of the 11th ISCA Speech Synthesis Workshop, 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 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 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 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Deep Neural Network Embeddings for the Estimation of the Degree of Sleepiness.

José Vicente Egas López, Gábor Gosztolya

Proceedings of the IEEE International Conference on Acoustics, 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

Investigating the Corpus Independence of the Bag-of-Audio-Words Approach.

Mercedes Vetráb, Gábor Gosztolya

Proceedings of the Text, Speech, and Dialogue, 2020

Predicting a Cold from Speech Using Fisher Vectors; SVM and XGBoost as Classifiers.

José Vicente Egas López, Gábor Gosztolya

Proceedings of the Speech and Computer - 22nd International Conference, 2020

Making a Distinction Between Schizophrenia and Bipolar Disorder Based on Temporal Parameters in Spontaneous Speech.

Gábor Gosztolya, Anita Bagi, Szilvia Szalóki, István Szendi, Ildikó Hoffmann

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

Very Short-Term Conflict Intensity Estimation Using Fisher Vectors.

Gábor Gosztolya

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 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 21st Annual Conference of the International Speech Communication Association, 2020

2019

Calibrating AdaBoost for phoneme classification.

Gábor Gosztolya, Róbert Busa-Fekete

Soft Comput., 2019

Posterior-thresholding feature extraction for paralinguistic speech classification.

Gábor Gosztolya

Knowl. Based Syst., 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

Differentiating Laughter Types via HMM/DNN and Probabilistic Sampling.

Gábor Gosztolya, András Beke, Tilda Neuberger

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

Assessing Parkinson's Disease from Speech Using Fisher Vectors.

José Vicente Egas López, Juan Rafael Orozco-Arroyave, Gábor Gosztolya

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 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 20th Annual Conference of the International Speech Communication Association, 2019

Using the Bag-of-Audio-Word Feature Representation of ASR DNN Posteriors for Paralinguistic Classification.

Gábor Gosztolya

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Using Fisher Vector and Bag-of-Audio-Words Representations to Identify Styrian Dialects, Sleepiness, Baby & Orca Sounds.

Gábor Gosztolya

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 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 20th Annual Conference of the International Speech Communication Association, 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

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

Posterior Calibration for Multi-Class Paralinguistic Classification.

Gábor Gosztolya, Róbert Busa-Fekete

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

User-centric Evaluation of Automatic Punctuation in ASR Closed Captioning.

Máté Ákos Tündik, György Szaszák, Gábor Gosztolya, András Beke

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 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 19th Annual Conference of the International Speech Communication Association, 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 19th Annual Conference of the International Speech Communication Association, 2018

Identifying Schizophrenia Based on Temporal Parameters in Spontaneous Speech.

Gábor Gosztolya, Anita Bagi, Szilvia Szalóki, István Szendi, Ildikó Hoffmann

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 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

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

Tamás Grósz, Gábor Gosztolya, László Tóth

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Training Context-Dependent DNN Acoustic Models Using Probabilistic Sampling.

Tamás Grósz, Gábor Gosztolya, László Tóth

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 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 18th Annual Conference of the International Speech Communication Association, 2017

Optimized Time Series Filters for Detecting Laughter and Filler Events.

Gábor Gosztolya

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 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 18th Annual Conference of the International Speech Communication Association, 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 Laughter and Filler Events by Time Series Smoothing with Genetic Algorithms.

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 17th Annual Conference of the International Speech Communication Association, 2016

GMM-Free Flat Start Sequence-Discriminative DNN Training.

Gábor Gosztolya, Tamás Grósz, László Tóth

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 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 17th Annual Conference of the International Speech Communication Association, 2016

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

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

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 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

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 16th Annual Conference of the International Speech Communication Association, 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 16th Annual Conference of the International Speech Communication Association, 2015

On evaluation metrics for social signal detection.

Gábor Gosztolya

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Conflict intensity estimation from speech using Greedy forward-backward feature selection.

Gábor Gosztolya

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 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

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

Applying Representative Uninorms for Phonetic Classifier Combination.

Gábor Gosztolya, József Dombi

Proceedings of the Modeling Decisions for Artificial Intelligence, 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 15th Annual Conference of the International Speech Communication Association, 2014

On the Concept of Correct Hits in Spoken Term Detection.

Gábor Gosztolya

Proceedings of the Second International Workshop on Artificial Intelligence and Cognition (AIC 2014), 2014

2013

Using the Logarithmic Generator Function in the Spoken Term Detection Task.

Gábor Gosztolya

Proceedings of the Modeling Decisions for Artificial Intelligence, 2013

Detecting autism, emotions and social signals using adaboost.

Gábor Gosztolya, Róbert Busa-Fekete, László Tóth

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

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

2010

Improving speed and accuracy in automatic speech recognition

Gábor Gosztolya

PhD thesis, 2010

2009

Applying the Generalized Dombi Operator Family to the Speech Recognition Task.

Gábor Gosztolya, József Dombi, András Kocsor

J. Comput. Inf. Technol., 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 9th Annual Conference of the International Speech Communication Association, 2008

Detection of Phoneme Boundaries Using Spiking Neurons.

Gábor Gosztolya, László Tóth

Proceedings of the Artificial Intelligence and Soft Computing, 2008

2006

The use of speed-up techniques for a speech recognizer system.

András Kocsor, Gábor Gosztolya

Int. J. Speech Technol., 2006

A Hierarchical Evaluation Methodology in Speech Recognition.

Gábor Gosztolya, András Kocsor

Acta Cybern., 2006

2005

Speeding Up Dynamic Search Methods in Speech Recognition.

Gábor Gosztolya, András Kocsor

Proceedings of the Innovations in Applied Artificial Intelligence, 2005

2004

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

László Tóth, András Kocsor, Gábor Gosztolya

Acta Cybern., 2004

Aggregation Operators and Hypothesis Space Reductions in Speech Recognition.

Gábor Gosztolya, András Kocsor

Proceedings of the Text, Speech and Dialogue, 7th International Conference, 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

Improving the Multi-stack Decoding Algorithm in a Segment-Based Speech Recognizer.

Gábor Gosztolya, András Kocsor

Proceedings of the Developments in Applied Artificial Intelligence, 2003