143, Shandiz, A.H., Tóth, L.: Voice Activity Detection for Ultrasound-based Silent Speech Interfaces using Convolutional Neural Networks, Proc. TSD 2021.

142, Zainkó, Cs., Tóth, L., Shandiz, A.H., Gosztolya, G., Markó, A., Németh, G., Csapó, T.G.: Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging, Proc. Speech Synthesis Workshop, 2021.

141, Csapó, T.G., Tóth, L., Gosztolya, G., Markó, A.: Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input, Proc. Speech Synthsis Workshop, 2021.

140, Egas-Lopez, J.V., Vetráb, M., Tóth, L., Gosztolya, G.: Identifying Conflict Escalation and Primates by Using Ensemble X-Vectors and Fisher Vector Features, Proc. Interspeech 2021.

139, Shandiz, A.H, Tóth, L., Gosztolya, G., Markó, A., Csapó, T.G.: Neural Speaker Embedding for Ultrasound-based Silent Speech Interfaces, Proc. Interspeech 2021.

138, Yu Y., Shandiz, A.H., Tóth, L.: Reconstructing Speech from Real-Time Articulatory MRI Using Neural Vocoders, Proc. EUSIPCO, 2021.

137, Shandiz A.H., Tóth L., Gosztolya G., Markó A., Csapó T. G.: Improving Neural Silent Interface Speech Models by Adversarial Training, Proc. AICV 2021, pp. 430-440.

136, Tóth László, Amin Honarmandi Shandiz, Gosztolya Gábor, Zainkó Csaba, Markó Alexandra, Csapó Tamás Gábor, 3D konvolúciós neuronhálón és neurális vokóderen alapuló némabeszéd-interfész, Proc. MSZNY 2021, pp. 123-138.

135, László Tóth, Amin Honarmandi Shandiz: 3D Convolutional Neural Networks for Ultrasound-Based Silent Speech Interfaces, Proc. ICAISC, pp. 159-169, 2020.

134, Vincze, V., Szatlocki, G., Tóth, L., Gosztolya, G., Pakaski, M., Hoffmann, I., Kalman, J.: Telltale silence: temporal speech parameters discriminate between prodromal dementia and mild Alzheimer’s disease, Clinical Linguistics and Phonetics, 2020.

133, Gosztolya, G., Toth, L.: Applying Speech Tempo-Derived Features, BoAW and Fisher Vectors to Detect Elderly Emotion and Speech in Surgical Masks, Proc. Interspeech 2020

132, Gosztolya, G., Grosz, T., Toth, L., Marko, A., Csapo, T.: Applying DNN Adaptation to Reduce the Session Dependency of Ultrasound Tongue Imaging-based Silent Speech Interfaces, Acta Polytechnica Hungarica, Vo. 17, No. 7, 2020.

131, Imre, N., Balogh, R., Gosztolya, G., Tóth, L., Várkonyi, T., Lengyel, Cs., Pákáski, M., Kálmán, J.: Automatic recognition of temporal speech features in type 2 diabetes mellitus with mild cognitive impairment,Proc. CogInfoCom 2019.

130, Pap, G., Toth, L.: A Comparison of Supervised and Semi-supervised Training Algorithms of Restricted Boltzmann Machines on Biological Data, Proc. CINTI-MACRO 2019.

129, Toth, L., Gosztolya, G., Reducing the Inter-Speaker Variance of CNN Acoustic Models Using Unsupervised Adversarial Multi-Task Training, Proc. SPECOM 2019, pp. 481-490, 2019.

128, Lopez, H.V.E., Toth, L., Hoffmann, I., Kalman, J., Pakaski, M., Gosztolya, G., Assessing Alzheimer's Disease from Speech Using the i-Vector Approach, Proc. SPECOM 2019, pp. 289-298, 2019.

127, Kovacs, Gy., Toth, L., Van Compernolle, D., Liwicki, M.:Examining the combination of multi-band processing and channel dropout for robust speech recognition, Proc. Interspeech 2019.

126, Gosztolya, G., Toth, L.: Calibrating DNN Posterior Probability Estimates of HMM/DNN Models to Improve Social Signal Detection From Audio Data, Proc. Interspeech 2019.

125, Csapo, T., Al-Radhi, M., Nemeth, G., Gosztolya, G., Grosz, T., Toth, L., Marko, A.: Ultrasound-based Silent Speech Interface Built on a Continuous Vocoder, Proc. Interspeech 2019.

124, Gosztolya, G., Pinter, A., Toth, L., Grosz, T., Marko, A., Csapo, T.: Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent Speech Interfaces, Proc. IJCNN, 2019.

123, Toth, L., Gosztolya, G.: Adversarial Multi-Task Learning of Speaker-Invariant Deep Neural Network Acoustic Models for Speech Recognition, Proc. ASPAI 2019, pp. 82-86.

122, Grosz, T., Toth, L.: Mely neuronhalos beszedfelismerok mukodesenek ertelmezo elemzese, Proc. MSZNY 2019, pp. 287-297

121, Pinter, A., Gosztolya, G., Toth, L., Grosz, T., Csapo, T., Marko, A.: Autoenkoderen alapulo jellemzoreprezentacio mely nauronhalos, ultrahang-alapu nemabeszed-interfeszekben, Proc. MSZNY 2019, pp. 13-22.

120, Toth, L., Gosztolya, G.: Beszeloinvarians akusztikus modellek letrehozasa mely neuronhalok ellenseges multi-taszk tanitasaval, Proc. MSZNY 2019, pp. 3-11.

119, Kov?s, Gy., T?h, L., Gosztolya, G.: Multi-Band Processing with Gabor Filters and Time-Delay Neural Nets for Noise Robust Speech Recognition, Proc. SLT 2018, pp.

118, T?h, L., Kov?s, Gy., Ivask? L., T?h, A., Jakab, K., V?sei, L.: Stroke-on ?esett dysarthir? betegek besz??ek g?i elemz?e - kezdeti eredm?yek, Proc. Neumann Kollokvium, 2018, pp. 43-49.

117, T?h, L., Kov?s, Gy., Van Compernolle, D.: A Perceptually Inspired Data Augmentation Method for Noise Robust CNN Acoustic Models, Proc. SPECOM 2018, pp. 697-706.

116, Gosztolya, G., Grosz, T., Toth, L.: General Utterance-Level Feature Extraction for Classifying Crying Sounds, Atypical & Self-Assessed Affect and Heart Beats, Proc. Interspeech, pp. 531-535, 2018.

115, Toth, L., Gosztolya, G., Grosz, T., Marko, A., Csapo, T.: Multi-Task Learning of Speech Recognition and Speech Synthesis Parameters for Ultrasound-based Silent Speech Interfaces, Proc. Interspeech, pp. 3172-3176, 2018.

114, Gosztolya, G., Grosz, T., Toth, L.: Social Signal Detection by Probabilistic Sampling DNN Training, IEEE Transactions on Affective Computing, Vol. 11, No. 1, pp. 164-177, 2020.

113, Gosztolya, G., Vincze, V., T?h, L., P??ki, M., K?m?, J., Hoffmann, I.:Identifying Mild Cognitive Impairment and Mild Alzheimer's Disease Based On Spontaneous Speech Using ASR and Linguistic Features, Computer Speech and language, 53: pp. 181-197. (2019)

112, Gr?z, T., Gosztolya, G., T?h, L., Csap? T., Mark? A.: F0 Estimation for DNN-Based Ultrasound Silent Speech Interfaces, Proc. ICASSP 2018, pp. 291-295.

111, Toth, L.: Deep Neural Network with Linearly Augmented Rectifier Layers for Speech Recognition, Proc. SAMI 2018, pp. 189-193, 2018.

110, Gosztolya, G., Hoffmann, I., T?h, L., Vincze, V., P??ki, M., K?m?, J.: Az enyhe kognit? zavar ? a korai Alzheimer-k? automatikus azonos??a spont? besz?b? akusztikus jellemz? seg?s??el, Proc. MSZNY, 2018.

109, Gr?z, T., T?h, L., Gosztolya, G., Csap? T., Mark? A.: K??letek az alapfrekvencia becsl??e m?y neuronh??, ultrahang alap? n?abesz?-interf?zekben, Proc. MSZNY, 2018.

108, T?h, L., Gr?z, T., GOsztolya, G.: Besz?felismer? m?y neuronh?? ?lapotkapcsol?i algoritmusainak k??leti ?szehasonl??a, Proc. MSZNY. 2018.

107, Toth, L., Hoffmann, I., Gosztolya, G., Vincze, V., Szatloczki, G., Banreti, Z., Pakaski, M., Kalman, J.: A Speech Recognition-based Solution for the Automatic Detection of Mild Cognitive Impairment from Spontaneous Speech, Current Alzheimer Research, Vol. 15, No. 2, pp. 130-138, 2018.

106, Hoffmann, I., T?h, L., Gosztolya, G., Szatl?zki, G., Vincze, V., K?p?i, E., P??ki, K?m?, J.: Besz?felismer? alap?elj?? az enyhe kognit? zavar automatikus felismer??e spont? besz? alapj?, ?ltal?os Nyelv?zeti Tanulm?yok XXIX. Szerk.: Kenesei I.-B?r?i Z., Akad?iai Kiad? Budapest, pp. 385-405

105, Kovacs, Gy., T?h, L.,Van COmpernolle, D., Ganapathy, S.: Increasing the robustness of CNN acoustic models using ARMA spectrogram features and channel dropout, Pattern Recognition Letters, Vo. 100, pp. 44-50, 2017.

104, Gosztolya, G., Busa-Fekete, R., Gr?z, T., T?h, L.: DNN-based Feature Extraction and Classifier Combination for Child-Directed Speech, Cold and Snoring Identification, Proc. Interspeech 2017.

103, Csap? T.G., Gr?z, T., Gosztolya, G., T?h, L., Mark?A.: DNN-based Ultrasound-to-Speech Conversion for a Silent Speech Interface, Proc. Interspeech 2017.

102, Gr?z, T., Gosztolya, G., T?h, L.: A Comparative Evaluation of GMM-Free State Tying Methods for ASR, Proc. Interspeech 2017.

101, Gr?z, T., Gosztolya, G., T?h, L.: Training Context-Dependent DNN Acoustic Models using Probabilistic Sampling, Proc. Interspeech 2017.

100, Gosztolya, G., T?h, L.: DNN-based Feature Extraction for Conflict Intensity Estimation from Speech, IEEE Signal Processing Letters, Vol. 24, Issue 12, pp. 1837-1841, 2017.

99, T?h, L.: Multi-Resolution Spectral Input for Convolutional Neural Network-based Speech Recognition, Proc. SpeD 2017, pp. 1-6.

98, Bodn?, P., Gr?z, T., T?h, L., Ny?, L.G.: Efficient visual code localization with neural networks, Pattern Analysis and Applications, Vo. 21, No. 1, pp. 249-260, 2018.

97, Gosztolya, G., T?h, L.: A feature selection-based speaker clustering method for paralinguistic tasks, Pattern Analysis and Applications, Vol. 21, No.1, pp. 193-204, 2018.

96, Csap? T.G., Gr?z, T., T?h, L., Mark? A.: Besz?szint?is ultrahangos artikul?i? felv?elekb? m?y neuronh?? seg?s??el, Proc. MSZNY, pp. 181-192, 2017.

95, Gr?z, T., Gosztolya, G., T?h, L.: M?y neuronh?? besz?felismer? GMM-mentes tan??a, Proc. MSZNY, pp. 170-180, 2017.

94, Kov?s, Gy., T?h, L.: M?y neuronh??a integr?t spektro-tempor?is jellemz?inyer?i m?szer optimaliz??a, Proc. MSZNY, pp. 158-169, 2017.

93, Gosztolya, G., Gr?z, T., T?h, L., Beke, A., Neuberger, T.: Neur?is h?? tan??a val?z???i mintav?elez?sel nevet?ek felismer??e, Proc. MSZNY, pp. 136-145, 2017.

92, Gosztolya, G., Beke, A., Neuberger, T., T?h. L.: Laughter Classification using Deep Rectifier Neural Networks with a Minimal Feature Subset, Archives of Acoustics, Vol. 41, No. 4, pp. 669-682, 2016.

91, Gosztolya, G., Gr?z, T., T?h. L.: GMM-Free Flat Start Sequence-Discriminative DNN Training, Interspeech 2016, pp. 3409-3413.

90, Gosztolya, G., T?h, L., Gr?z, T., Vincze, V., Hoffmann, I., Szatl?zki, G., P??ki, M., K?m?, J.: Detecting Mild Cognitive Impairment from Spontaneous Speech by Correlation-Based Phonetic Feature Selection, Interspeech 2016, pp. 107-111.

89, Gosztolya, G., Gr?z, T., Busa-Fekete, R., T?h. L.: Determining Native Language and Deception Using Phonetic Features and Classifier Combination, Interspeech 2016, pp. 2418-2422.

88, Gosztolya, G., Gr?z, T., Szasz?, Gy., T?h. L.: Estimating the Sincerity of Apologies in Speech by DNN Rank Learning and Prosodic Analysis, Interspeech 2016, pp. 2026-2030.

87, T?h, L., Gosztolya, G.: Adaptation of DNN Acoustic Models using KL-divergence Regularization and Multi-task Training, SPECOM 2016, pp. 108-115.

86, Vincze, V., Gosztolya, G., T?h, L., Hoffmann, I., Szatl?zki, G., B?r?i, Z., P??ki, J., K?m?, J.: Detecting Mild Cognitive Impairment by Exploiting Linguistic Information from Transcripts, Proc. ACL 2016, pp. 181-187.

85, Kov?s, Gy., T?h, L.: T?bs?os, zajt??besz?felismer? m?y neuronh??al, Proc. MSZNY 2016, pp. 287-294.

84, T?h, L., Gosztolya, G.: M?y neuronh?? akusztikus modellek gyors adapt?i?a multi-taszk tan??sal, Proc. MSZNY 2016, pp. 154-162.

83, Gosztolya, G., Vincze, V., Gr?z, T., T?h, L.: Egy magyar nyelv?besz?felismer?rendszer sz?zint?hib?nak elemz?e, Proc. MSZNY 2016, pp. 100-110.

82, T?h, L., Gosztolya, G., Vincze, V., Hoffmann, I., Szatl?zki, G., Bir? E., Zsura, F., P??ki, M., K?m?, J.: Az enyhe kognit? zavar automatikus azonos??a besz?felismer?i technik? haszn?at?al, Proc. XVIII. Neumann Kollokvium 2015, pp. 112-117

81, Toth, L.: Phone Recognition with Hierarchical Convolutional Deep Maxout Networks, , EURASIP Journal on Audio, Speech, and Music Processing, 2015:25, 2015.

80, Kov?s Gy., T?h L., : Joint Optimization of Spectro-Temporal Features and Deep Neural Nets for Robust Automatic Speech Recognition, Acta Cybernetica, Volume 22, Number 1 , Page 117-134, 2015.

79, Gr?z, T., Busa-Fekete, R., Gosztolya, G., T?h, L.: Assessing the Degree of Nativeness and Parkinson's Condition Using Gaussian Processes and Deep Rectifier Neural Networks, Proc. Interspeech 2015, pp. 919-923

78, T?h, L., Gosztolya, G., Vincze, V., Hoffmann, I., Szatl?zki, G., Bir? E., Zsura, F., P??ki, M., K?m?, J.: Automatic Detection of Mild Cognitive Impairment from Spontaneous Speech using ASR, Proc. Interspeech 2015, pp. 2694-2698

77, Gosztolya, G., Gr?z, T., T?h, L., Imseng, D.: Building Context-Dependent DNN Acoustic Models using Kullback-Leibler Divergence-Based State Tying, Proc. ICASSP 2015, pp. 4570-4574

76, Toth, L.: Modeling Long Temporal Contexts in Convolutional Neural Network-Based Phone Recognition, Proc. ICASSP 2015, pp. 4575-4579

75, Vincze, V., Hoffmann, I., Szatl?zki, G., B?? E., Gosztolya, G., T?h, L., P??ki, M., K?m?, J.: Az enyhe kognit? zavar automatikus azonos??a besz??iratok alapj?, Proc. MSZNY 2015, pp. 249-256.

74, Gr?z, T., Gosztolya, G., T?h, L.: K?nyezetf?g?akusztikai modellek l?rehoz?a Kullback-Leibler-divergencia alap?klaszterez?sel, Proc. MSZNY 2015, pp. 174-181.

73, Kov?s Gy., T?h L., Van Compernolle, D.: Selection and enhancement of Gabor filters for automatic speech recognition, International Journal of Speech Technology, Volume 18, Issue 1 , Page 1-16, 2015.

72, Bodn? P., Gr?z T., T?h L., Ny? L.: Localization of Visual Codes in the DCT Domain Using Deep Rectifier Neural Networks, Proc. ANNIIP 2014, pp. 37-44.

71, Gr?z T., Bodn? P., T?h L., Ny? L.: QR Code Localization Using Deep Neural Networks, Proc. MLSP 2014, pp. 1-6.

70, Kov?s Gy., T?h L., Gr?z T.: Robust Multi-Band ASR Using Deep Neural Nets and Spectro-temporal Features, Proc. SPECOM 2014, pp. 386-393.

69, Gr?z T., Gosztolya G, T?h L.: A Sequence Training Method for Deep Rectifier Neural Networks in Speech Recognition, Proc. SPECOM 2014, pp. 81-88.

68, Gr?z, T., Gosztolya, G., Busa-Fekete, R., T?h, L.: Detecting the Intensity of Cognitive and Physical Load Using AdaBoost and Deep Rectifier Neural Networks, Proc. Interspeech 2014, pp. 452-456.

67, Toth, L.: Convolutional Deep Maxout Networks for Phone Recognition Proc. Interspeech 2014, pp. 1078-1082.

66, Toth, L.: Combining Time- and Frequency-Domain Convolution in Convolutional Neural Network-Based Phone Recognition Proc. ICASSP 2014, pp. 190-194.

65. Grosz, T., Kovacs, Gy., Toth. L.: Uj eredmenyek a mely neuronhalos magyar nyelvu beszedfelismeresben, Proc. MSZNY, pp. 3-13, 2014.

64. Grosz, T., Toth, L.: A Comparison of Deep Neural Network Training Methods for Large Vocabulary Speech Recognition, Proc. TSD2013, pp. 36-43, 2013.

63. Kovacs, Gy., Toth, L.: The Joint Optimization of Spectro-Temporal Features and Neural Net Classifiers, Proc. TSD2013, pp. 552-559, 2013.

62. Gosztolya, G., Busa-Fekete, R., Toth, L.: Detecting Autism, Emotions and Social Signals Using AdaBoost, Proc. Interspeech 2013, pp. 220-224.

61, Toth, L.: Convolutional Deep Rectifier Neural Nets for Phone Recognition, Proc. Interspeech 2013, pp. 1722-1726.

60, Toth, L.: Phone Recognition with Deep Sparse Rectifier Neural Networks, Proc. ICASSP 2013, pp. 6985-6989.

59, Grosz, T., Toth, L.: Mely neuronhalok az akusztikus modellezesben, Proc. MSZNY 2013, pp. 3-12.

58, Toth, L.: K??letek beszedfelismerok akusztikus modelljenek nyelvek kozotti atvitelere, Altalanos Nyelveszeti Tanulmanyok XXIV, pp. 311-327, 2012.

57, Gosztolya, G., Toth, L.: Improving the Sound Recording Quality of Wireless Sensors Using Automatic Gain Control Methods, Scientific Bulletin of Politechnica University of Timisoara, Vol. 56(70), No. 2, pp. 47-56, June 2011,

56, Toth, L.:A Hierarchical, Context-Dependent Neural Network Architecture for Improved Phone Recognition, Proc. ICASSP 2011, pp. 5040-5043.

55, Kovacs, Gy., Toth, L.: Phone Recognition Experiments with 2D-DCT Spectro-Temporal Features, Proc. SACI 2011, pp. 143-146.

54, Gosztolya, G., Toth, L., Kovacs, Gy.: Spoken Term Detection from Noisy Input, Proc. SACI 2011, pp. 91-96.

53, Gosztolya, G., Toth, L.: Spoken Term Detection Based on the Most Probable Phoneme Sequence, Proc. SAMI 2011, pp. 101-106.

52, Gosztolya, G., Toth, L.:Kulcsszokeresesi kiserletek hangzo hiranyagokon beszedhang alapu felismeresi technologiakkal, Proc. MSZNY 2010, pp. 224-235.

51, Toth L., Tarjan B., Sarosi G., Mihajlik P.: Speech Recognition Experiments with Audiobooks, Acta Cybernetica 19 (2010). pp. 695-713.

50, Gosztolya, G., Paczolay, D., Toth, L.: Low-Complexity Audio Compression Methods For Wireless Sensors,Proc. SISY 2010, pp. 77-81.

49, Gosztolya, G., Paczolay, D., Toth, L.: Automatic Gain Control Algorithms for Wireless Sensors, Proc. ICCC-CONTI 2010, pp. 401-406.

48, Kovacs, Gy., Toth, L.: Localized Spectro-Temporal Features for Noise-Robust Speech Recognition, Proc. ICCC-CONTI 2010, pp. 481-485.

47, Toth, L.: Beszedfelismeresi kiserletek hangoskonyvekkel, Proc. MSZNY, pp. 206-216, 2009.

46, Gosztolya, G., Banhalmi, A., Toth, L.: Using One-Class Classification Techniques in the Anti-Phoneme Problem, Proceedings of IbPRIA 2009 (2009), pp. 433-440.

45, Banhalmi, A., Paczolay, D., Toth, L., Kocsor, A.: Investigating the robustness of a Hungarian medical dictationsystem under various conditions, International Journal of Speech Technology, VOLUME 9, ISSUE 3-4 (2008), PAGE 121-131.

44, Toth, L., Frankel, J., Gosztolya, G., King, S.: Cross-lingual Portability of MLP-Based Tandem Features - A Case Study for English and Hungarian, Proceedings of Interspeech 2008, pp. 2695-2698, 2008.

43, Gosztolya, G., Toth, L.: Detection of Phoneme Boundaries Using Spiking Neurons, Proceedings of ICAISC 2008, pp. 782-793, 2008.

42, Banhalmi, A., Paczolay, D., Toth, L.: Dikt??endszer pontoss??ak ? hat?onys??ak vizsg?ata a keres?i t?en alkalmazott v??i technik? f?gv?y?en, Proc. MSZNY 2007, pp. 56-68.

41, Toth, L.: Benchmarking Human Performance on the Acoustic and Linguistic Subtasks of ASR System, Proceedings of Eurospeech 2007, pp. 382-385, 2007.

40, Banhalmi, A., Paczolay, D., Toth, L. and Kocsor, A.: Development of a Hungarian Medical Dictation System, Informatica, Vol. 31, No. 2, pp. 241-246, 2007.

39, Toth, L., Kocsor, A.: A segment-based interpretation of HMM/ANN hybrids, Computer Speech And Language, Vol. 21, pp. 562-578, 2007.

38, Banhalmi, A., Kocsor, A., Kovacs, K., Toth, L.: Fundamental Frequency Estimation by Combinations of Various Methods, Proc. 7th Nordic Signal Processing Symposium NORSIG 2006.

37, Toth, L.: Posterior-Based Speech Models and their Application to Hungarian Speech Recognition, Ph.D. Dissertation, University of Szeged, 2006.

36, Banhalmi, A., Paczolay, D., Toth, L., Kocsor, A.: First Results of a Hungarian Medical Dictation Project, Proc. of IS-LTC 2006, pp. 23-26.

35, Vicsi, K., Kocsor, A., Toth, L., Velkei, Sz., Szaszak, Gy., Teleki, Cs., Banhalmi, A., Paczolay, D.: A Magyar Referencia Beszedadatb?is ? alkalmaz?a orvosi dikt??rendszerek kifejleszt??ez, Proc. MSZNY 2005, pp. 435-438.

34, Rovo, L., Smehak, Gy., Toth, L., Szamoskozi, A., Toth, F., Kiss, J. G., Czigner, J., Jori, J.: A ketoldali hangszalagbenulas "korai" szakaban vegzett hangrestagito mutet kovetkezteben letrejovo elvaltozasok reverzibilitasanak vizsgalata laryngostroboszkopiaval es obejktiv hangelemzessel, Ful-, orr-, gegegyogyaszat, Vol. 51, No. 2., pp. 85-92, 2005.

33, Banhalmi, A., Kovacs, K., Kocsor, A., Toth, L.: Fundamental Frequency Estimation by Least-Squares Harmonic Model Fitting, Proceedings of EuroSpeech 2005, pp. 305-308.

32, Toth, L., Kocsor, A.: Explicit Duration Modelling in HMM/ANN Hybrids, Matousek et al. (eds.): Proceedings of TSD 2005, LNAI 3658, pp. 310-317, Springer, 2005.

31, Toth, L., Kocsor, A.: Training HMM/ANN Hybrid Speech Recognizers by Probabilistic Sampling,Duch et al. (eds): Proceedings of ICANN 2005, LNCS 3696, pp. 597-603, 2005.

30, Toth, L., Kocsor, A., Csirik, J.: On Naive Bayes in Speech Recognition, Int. J. Applied Mathematics and Computer Science, Vol. 15, No. 2, pp. 287-294, 2005.

29, Zsigri, Gy., Kocsor, A., Toth, L., Sejtes, Gy.: Phonetic Level Annotation and Segmentation of Hungarian Speech Databases, Acta Cybernetica, Vol. 16, pp. 659-673, 2004.

28, Toth, L., Kocsor, L., Gosztolya, G.: Telephone Speech Recognition via the Combination of Knowledge Sources in a Segmental Speech Model, Acta Cybernetica, Vol 16, pp. 643-657, 2004.

27, Zsigri, Gy., Toth, L., Kocsor, A. Sejtes, Gy.: Az automata es kezi szegmentalas ejtesvariaciok okozta problemai, Proc. MSZNY 2004.

26, Vicsi, K., Kocsor, A., Teleki, Cs., Toth, L.: Beszedadatbazis irodai szamitogep-felhasznaloi kornyezetben, Proc. MSZNY 2004.

25, Faddi, G., Kocsor, A, Toth, L.: Initializing Directions in Projection Pursuit Learning, Proc. IJCNN'2004, Paper No. 1429

24, Toth, L., Gosztolya, G.: Replicator Neural Networks for Outlier Modeling in Segmental Speech Recognition, In: Yin, Fuliang; Wang, Jun; Guo, Chengan (Eds.): Advances in Neural Networks - ISNN 2004,Proceedings of International Symposium on Neural Networks, Dalian, China, August 19-21, 2004, Part I, Springer LNCS Vol. 3173, pp. 996-1001.

23, Kocsor, A., Toth, L., Kernel-Based Feature Extraction with a Speech Technology Application, IEEE Trans. Signal Processing, Vol. 52, No. 8, pp. 2250-2263, Aug. 2004.

22, Kocsor, A. and Toth, L.: Application of Kernel-Based Feature Space Transformations and Learning Methods to Phoneme Classification, Applied Intelligence, Vol. 21., No. 2., pp. 129-142, 2004.

21, Toth, L., Kocsor, A., Kovacs, K., Felfoldi, L.: Nyelveszeti tudasforrasok integralasi lehetosegei diszkriminativ szegmens-alapu beszedfelismero rendszerekbe, Proc. MSZNY 2003, pp. 169-174.

20, Toth, L., Kocsor, A., Az MTBA magyar telefonbeszed-adatbazis kezi feldolgozasanak tapasztalatai, A Beszedkutatas 2003 kotetben (szerk. Gosy Maria), pp. 134-146, 2003.

19, Toth, L., Kocsor, A., Harmonic Alternatives to Sine-Wave Speech, Proc. Eurospeech, Geneva, 2003, pp. 2073-2076.

18, Felfoldi, L., Kocsor, A., Toth, L.: Classifier Combination in Speech Recognition, Periodica Polytechnica Ser. El. Eng., Vol. 47, No. 1-2., pp. 125-140, 2003.

17, Gosztolya, G., Kocsor, A., Toth, L., Felfoldi, L.: Various Robust Search Methods in a Hungarian Speech Recognition System, Acta Cybernetica, Vol. 16, No. 2., pp. 229-240, 2003.

16, Paczolay. D., Kocsor, A., Toth, L.: Real-Time Vocal Tract Length Normalization in a Phonological Awareness Teaching System, Matousek, V., Mautner, . (eds.): Proc. of TSD'2003, pp. 309-314.

15, Paczolay, D., Toth, L., Kocsor, A., Kerekes, J.: Gepi tanulas alkalmazasa egy fonologiai tudatossag-fejleszto rendszerben, Alkalmazott Nyelvtudomany, II. evf. 2. szam, 2002, pp. 55-67

14, Kovacs, K., Kocsor, A., Toth, L.: Hungarian Speech Synthesis Using a Phase Exact HNM Approach, in: Grosky, W. I., Plasil, F. (eds.):Proc. of SOFSEM 2002: Theory and Practice of Informatics, Milovy, CzechRepublic, Nov. 2002, pp. 181-185

13, Vicsi, K., Toth, L., Kocsor, A., Gordos, G., Csirik, J.: MTBA -magyar nyelvu telefonbeszed-adatbazis, Hiradastechnika, Vol. LVII, NO.8,pp. 35-43, 2002

12, Kocsor, a., Toth, L., Paczolay, D.: A Nonlinearized DiscriminantAnalysis and its Application to Speech Impediment Therapy, in:V. Matousek, P. Mautner, R. Moucek, K. Tauser (eds): Proceedings of the4th Int. Conf. on Text, Speech and Dialogue, LNAI 2166, pp. 249-257,Springer Verlag, 2001

11, Kocsor, A., Toth, L., Felfoldi, L.: Application of FeatureTransformation and Learning Methods in Phoneme Classification, in:L. Monostori, J. Vancza and M. Ali (Eds.): Proc. 14th Int. Conf. onIndustrial and Engineering Applications of Artificial Intelligenceand Expert Systems, IEA/AIE 2001, LNAI 2070, pp. 502-512, 2001,Springer Verlag

10, Kocsor, A., Kuba, A. Jr., Toth, L.: Phoneme Classification UsingKernel Principal Component Analysis, Periodica Polytechnica, Vol. 44, No.1, pp. 77-90, 2000

09, Toth, L., Kocsor, A., Kovacs, K.: A Discriminative Segmental SpeechModel and its Application to Hungarian Number Recognition,in: P. Sojka, I kopecek, K. Pala (eds.): TSD'2000, LNAI 1902,pp. 307-313, Springer Verlag, 2000

08, Kocsor, A., Toth, L., Kuba, A. Jr., Kovacs, K., Jelasity, M.,Gyimothy, T., Csirik, J.: A Comparative Study of Several Feature SpaceTransformation and Learning Methods for Phoneme Classification,International Journal of Speech Technology, Vol. 3, Number 3/4,2000, pp. 263-276

07, Kocsor, A., Kuba A. Jr., Toth L.: An Overview of the OASIS speech recognition project, Proceedings of the 4th International Conference on Applied Informatics, Aug. 30-Sept. 3, Eger-Noszvaj, Hungary, 1999, pp. 94-102

06, Kocsor, A., Kuba A. Jr., Toth L., Jelasity M., Felfoldi L., Gyimothy T., Csirik J.,: A Segment-Based Statistical Speech Recognition System for Isolated/Continuous Number Recognition, Proceedings of the FUSST'99, Aug. 19-21, Sagadi,Estonia, pp. 201-211

05, Kocsor, A., T?h, L., B?int I.,: On the Optimal Parameters of a Sinusoidal Representation of Signals, Acta Cybernetica 14, pp. 315-330, 1999

04, T?h, L.: Automatic Speech Recognition, (a chapter in the book "Artificial Intelligence", edited by: Fut?Iv?), 1999, Aula, pp. 815-872 (in Hungarian)

03, T?h, L.: Computer, Can You Hear Me?; ? Alaplap magazin, Vol. XVI. No. 6., p. 5-7. , June, 1998 (in Hungarian)

02, T?h, L.: Speech Recognition Based On Phonetic Features, Proceedings of the High Speed Networking International Workshop (Speech Processing Section), 1997, Balatonf?ed, Hungary, pp. 37-40

01, Alexin, Z., Csirik, J., Gyim?hy, T., Jelasity, M., T?h, L.: Learning Phonetic Rules in a Speech Recognition System, Proceedings of ILP'97, Seventh International Workshop on Inductive Logic Programming, 1997, Prag, Czech Republic, LNAI Vol 1297, pp. 37-44 (1997), Springer Verlag