1. Tamás Gábor Csapó, Tamás Grósz, Gábor Gosztolya, László Tóth, Alexandra Markó, ,,DNN-based Ultrasound-to-Speech Conversion for a Silent Speech Interface'', Interspeech 2017, Stockholm, Svédország, (elfogadva) cikk

  2. Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh ,,Time-domain envelope modulating the noise component of excitation in a continuous residual-based vocoder for statistical parametric speech synthesis'', Interspeech 2017, Stockholm, Svédország, (elfogadva) cikk

  3. Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh ,,Deep Recurrent Neural Networks in Speech Synthesis Using a Continuous Vocoder'', SPECOM 2017, Hatfield, Hertfordshire, UK, (elfogadva) cikk

  4. Sajtóközlemény a projekt elindításáról.

  5. Milan Gnjatović, Branislav Borovac (2016) “Toward Conscious-Like Conversational Agents”, In: Toward Robotic Socially Believable Behaving Systems, Volume II - Modeling Social Signals, A. Esposito, L.C. Jain (eds.), volume 106 of the series Intelligent Systems Reference Library, Springer, pp. 23-45, DOI: 10.1007/978-3-319-31053-4_4, Invited chapter [M13]

  6. Milan Sečujski, Tijana Delić (2016) “A research into the linguistic aspects of the atom decomposition prosody modelling paradigm”, a chapter in Specific Applications of Information Technology and Signal Processing in Speech Disorder Diagnosis and Therapy, LAAC & IEPSP, Belgrade, ISBN 978–86–89431-14-8, Ed. S. T. Jovičić, Z. Šarić, M. Subotić, pp. 323-345 [M14]

  7. Lidija Krstanović, Nebojša M. Ralević, Vladimir Zlokolica, Ratko Obradović, Dragiša Mišković, Marko Janev, Branislav Popović (2016) “GMMs Similarity Measure Based on LPP-like Projection of the Parameter Space”, Expert Systems with Applications, Elsevier, ISSN: 0957-4174, Vol. 66, pp. 136-148, DOI: 10.1016/j.eswa.2016.09.014 (IF 2015: 2.981) [M21]

  8. Dragiša Mišković, Milan Gnjatović, Perica Štrbac, Branislav Trenkić, Nikša Jakovljević, Vlado Delić (2016) “Hybrid methodological approach to context-dependent speech recognition”, International Journal of Advanced Robotic Systems, ISBN: 1729-8806. [M23] (not published yet)

  9. Vlado Delić (2016) “From the Central Audio Library of the University of Novi Sad toward the Network of Audio Libraries at the Universities in the Western Balkan”, XII Međunarodni simpozij iz IKT - INTSIKT 2016 „Challenges for Education in ICT Engineering“, Tuzla, 6-7.6.2016. [M32]

  10. Milan Sečujski, Branislav Gerazov, Tamás Gábor Csapó, Vlado Delić, Philip Garner, Aleksandar Gjoreski, David Guennec, Zoran Ivanovski, Aleksandar Melov, Géza Németh, Ana Stojković and György Szaszák (2016) “Design of a Speech Corpus for Research on Cross-Lingual Prosody Transfer”, Proc. of the 18th SPECOM, Speech and Computer, Budapest, Hungary: Budapest University Of Technology And Economics (BME-TMIT), Budapest, Hungary, Moscow State Linguistic University, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, ITMO University, St. Petersburg, Russia, 23-27 August 2016, Andrey Ronzhin, Rodmonga Potapova, Géza Németh (Eds.), Lecture Notes in Computer Science (LNCS), Springer, LNAI 9811, pp. 199-206, DOI: 10.1007/978-3-319-43958-7_23, Series ISSN: 0302-9743, Print ISBN: 978-3-319-43957-0, Online ISBN: 978-3-319-43958-7. [M33]

  11. Edvin Pakoci, Branislav Popović, Nikša Jakovljević, Darko Pekar, Fathy Yassa (2016) “A Phonetic Segmentation Procedure Based on Hidden Markov Models”, Proc. of the 18th SPECOM, Speech and Computer, Budapest, Hungary: Budapest University Of Technology And Economics (BME-TMIT), Budapest, Hungary, Moscow State Linguistic University, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, ITMO University, St. Petersburg, Russia, 23-27 August 2016, Andrey Ronzhin, Rodmonga Potapova, Géza Németh (Eds.), Lecture Notes in Computer Science (LNCS), Springer, LNAI 9811, pp. 67-74, DOI: 10.1007/978-3-319-43958-7_7, Series ISSN: 0302-9743, Print ISBN: 978-3-319-43957-0, Online ISBN: 978-3-319-43958-7. [M33]

  12. Tijana Delić, Branislav Gerazov, Branislav Popović, Milan Sečujski (2016) “A Linguistic Interpretation of the Atom Decomposition of Fundamental Frequency Contour for American English”, Proc. of the 18th SPECOM, Speech and Computer, Budapest, Hungary: Budapest University Of Technology And Economics (BME-TMIT), Budapest, Hungary, Moscow State Linguistic University, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, ITMO University, St. Petersburg, Russia, 23-27 August 2016, Andrey Ronzhin, Rodmonga Potapova, Géza Németh (Eds.), Lecture Notes in Computer Science (LNCS), Springer, LNAI 9811, pp. 59-66, DOI: 10.1007/978-3-319-43958-7_6, Series ISSN: 0302-9743, Print ISBN: 978-3-319-43957-0, Online ISBN: 978-3-319-43958-7. [M33]

  13. Darko Pekar, Siniša Suzić, Robert Mak, Meir Friedlander, Milan Sečujski (2016) “An Algorithm for Phase Manipulation in a Speech Signal”, Proc. of the 18th SPECOM, Speech and Computer, Budapest, Hungary: Budapest University Of Technology And Economics (BME-TMIT), Budapest, Hungary, Moscow State Linguistic University, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, ITMO University, St. Petersburg, Russia, 23-27 August 2016, Andrey Ronzhin, Rodmonga Potapova, Géza Németh (Eds.), Lecture Notes in Computer Science (LNCS), Springer, LNAI 9811, pp. 92-99, DOI: 10.1007/978-3-319-43958-7_10, Series ISSN: 0302-9743, Print ISBN: 978-3-319-43957-0, Online ISBN: 978-3-319-43958-7. [M33]

  14. Ivan Jokić, Stevan Jokić, Vlado Delić, Zoran Perić (2016) “One Solution for Mobile Phone Screen Unlocking by Voice”, In Proceedings of 3rd International Conference on Electrical, Electronic and Computing Engineering - IcETRAN 2016, Zlatibor, Serbia, June 13-16, 2016, ISBN 978-86-7466-618-0, pp. VII1.4.1-4. [M33]

  15. Ivan Jokić, Stevan Jokić, Vlado Delić, Zoran Perić (2016) “Application for Comparison Similarities Between Speakers by Using Algorithm for Automatic Speaker Recognition”, XIII International Conference of Society for Electronics, Telecom., Automation and Informatics, ETAI-2016, Struga, Macedonia, 22-24.09.2016, Zbornik apstrakta: ISBN 978-9989-630-82-8, p. 46; CD: pp. DP-1.1-4. [M33]

  16. Branislav Popović, Edvin Pakoci, Darko Pekar (2016) “Advanced Voice Activity Detection on Mobile Phones by Using Microphone Array and Phoneme-Specific Gaussian Mixture Models”, Proc. of the SISY 2016, IEEE 14th International Symposium on Intelligent Systems and Informatics, Subotica, Serbia: Óbuda University, Budapest, Hungary, Subotica Tech, Serbia, IEEE SMC Technical Committee on Computational Cybernetics, 29-31 August 2016, pp. 45-48, ISBN: 978-1-5090-2866-5. [M33]

  17. Stevan Ostrogonac, Branislav Popović, Milan Sečujski (2016) “The Use of Semantic Word Classes in Document Classification”, Proc. of the JT-DH 2016, Language Technologies & Digital Humanities, Ljubljana, Slovenia: Slovenian Language Technologies Society, Centre for Language Resources and Technologies at the University of Ljubljana, research infrastructures CLARIN.SI and DARIAH-SI, 29 September - 1 October 2016, pp. 216-217, ISBN: 978-961-237-862-2, COBISS.SI-ID=286548224. [M34]

  18. Tijana Delić, Milan Sečujski (2016) “Sinteza govora na srpskom jeziku zasnovana na veštačkim neuralnim mrežama”, 24. Telekomunikacioni forum, TELFOR 2016, 22-23.11.2016. u Beogradu, ISBN: 978-1-5090-4085-8, pp. 403-406 [M33]

  19. Nikša Jakovljević, Dragiša Mišković, Željen Trpovski (2016) “Evaluation of Noise Estimation Algorithms Based on Minimum Statistics and Signal to Noise Ratio”, 24. Telekomunikacioni forum, TELFOR 2016, 22-23.11.2016. u Beogradu, ISBN: 978-1-5090-4085-8, pp. 419-422 [M33]

  20. Vlado Delić, Milan Sečujski, Dragiša Mišković, Dušan Nikolić (2016) “Govorne tehnologije u visokom obrazovanju”, XXII Skup Trendovi razvoja, TREND-2016, “Nove tehnologije u nastavi”, Zlatibor, 16-19.02.2016. ISBN: 978-86-7392-795-9, pp. 45-48 [M63]

  21. Vlado Delić (2016) “Dostignuća u razvoju govornih tehnologija i perspektive njihove primene u pametnim kućama”, VI ciklus serije stručnih predavanja, unapređenje projektovanja telekomunikacionih mreža i sistema; Tema: „Sistemi upravljanja pametnim zgradama i gradovima“, Privredna komora Srbije, Beograd, 21.06.2016. [M64]

  22. Branislav Popović, Edvin Pakoci, Darko Pekar, Vlado Delić (2016) „Napredna detekcija govornih segmenata na mobilnom telefonu primenom mikrofonskog niza i dekodera“, Tehničko rešenje, FTN i AlfaNum d.o.o., Novi Sad, verifikovano na FTN 30.11.2016. [M82]

  23. Darko Pekar, Branislav Popović, Edvin Pakoci, Dragiša Mišković, Vlado Delić, Milan Sečujski (2016) „Duboke neuronske mreže na serveru u kombinaciji sa lokalnim dekoderom za prepoznavanje govora“ (Cloud-Based Deep Neural Networks Combined with Local Speech Recognition Decoder), AlfaNum d.o.o., Novi Sad, 21 June 2016, Patent application number P-2016/0452. [M87]

  24. Tijana Delić (2016) “Speech synthesis in Serbian language based on artificial neural networks”, master thesis on FTS, menthor prof. dr Milan Sečujski, 06.10.2016.

  25. Dragiša Mišković, Milan Gnjatović, PericaŠtrbac, Branislav Trenkić, Nikša Jakovljević, Vlado Delić (2017) “Hybrid methodological approach to context-dependent speech recognition”, International Journal of Advanced Robotic Systems, ISSN: 1729-8814, SAGE Publications, Vol. 14, No. 1, Feb. 1st, 2017, pp. 1-12, DOI: 10.1177/1729881416687131 [M23] http://journals.sagepub.com/home/arx

  26. Vlado Delić, Milan Sečujski, Nikša Jakovljević, Dragiša Mišković (2017) “Assistive character of voice technology”, Proceedings VI International Conference on Fundamental and Applied Aspects of Speech and Language (SPEECH & LANGUAGE), October 27-29, 2017, Belgrade, Serbia, IEPSP & LAAC, ISBN: 978-86-89431-24-7, pp. 18-26 [M31] (invited)

  27. Nikša Jakovljević, Dragiša Mišković, Željen Trpovski (2017) „Poređenjekarakteristikanekolikometodazadetekcijugovorneaktivnosti“ (A Comparison of Several Voice Activity Detection Methods), 16th International Scientific - Professional Symposium (INFOTEH-JAHORINA), 22-24.03.2017, Jahorina, ISBN: 978-99976-710-0-4, pp. 211-216 [M33]

  28. Milan Gnjatović, Dragiša Mišković, SrđanSavić, Branislav Borovac, Nemanja Maček, BranimirTrenkić (2017) “A Novel Modular Architecture for Conversational Robotic Agents”, In: Proc. of the 4th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN), Kladovo, Serbia, 05 08.06.2017. ISBN: 978-86-7466-692-0, Society for ETRAN, pp. ROI2.4.1-4 [M33]

  29. Ivan Jokić, Stevan Jokić, Vlado Delić, Zoran Perić (2017) “About Applicability of Automatic Speaker Recognition Algorithm for Automatic Recognition of Sounds in Nature”, In: Proc. of the 4th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN), Kladovo, Serbia, 05 08.06.2017. ISBN: 978-86-7466-692-0, Society for ETRAN, pp. AKI2.7.1-4 [M33]

  30. Nikša Jakovljević, Ivan Jokić, Slobodan Jošić, Vlado Delić (2017) “A Comparison of Covariance Matrix and i-Vector Based Speaker Recognition”, Proc. of the 19th Int. Conf. Speech and Computer (SPECOM), Alexey Karpov, RodmongaPotapova, Iosif Mporas (Eds.), Lecture Notes in Computer Science (LNCS), Series ISSN: 0302-9743, Print ISBN: 978-3-319-66428-6, Online ISBN: 978-3-319-66429-3, Hatfield, Hertfordshire, UK: University of Hertfordshire, Hatfield, UK, Moscow State Linguistic University, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, ITMO University, St. Petersburg, Russia, 12-16.09.2017, Springer, LNAI 10458, pp. 37-45, DOI: 10.1007/978-3-319-66429-3_3 [M33]

  31. Edvin Pakoci, Branislav Popović, Darko Pekar (2017) “Language Model Optimization for a Deep Neural Network Based Speech Recognition System for Serbian”, Proc. of the 19th Int. Conf. Speech and Computer (SPECOM), Alexey Karpov, RodmongaPotapova, Iosif Mporas (Eds.), Lecture Notes in Computer Science (LNCS), Series ISSN: 0302-9743, Print ISBN: 978-3-319-66428-6, Online ISBN: 978-3-319-66429-3, Hatfield, Hertfordshire, UK: University of Hertfordshire, Hatfield, UK, Moscow State Linguistic University, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, ITMO University, St. Petersburg, Russia, 12-16.09.2017, Springer, LNAI 10458, pp. 483-492, DOI: 10.1007/978-3-319-66429-3_48 [M33]

  32. Branislav Popović, Edvin Pakoci, Darko Pekar (2017) “End-to-End Large Vocabulary Speech Recognition for the Serbian Language”, Proc. of the 19th Int. Conf. Speech and Computer (SPECOM), Alexey Karpov, RodmongaPotapova, Iosif Mporas (Eds.), Lecture Notes in Computer Science (LNCS), Series ISSN: 0302-9743, Print ISBN: 978-3-319-66428-6, Online ISBN: 978-3-319-66429-3, Hatfield, Hertfordshire, UK: University of Hertfordshire, Hatfield, UK, Moscow State Linguistic University, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, ITMO University, St. Petersburg, Russia,12-16.09.2017, Springer, LNAI 10458, pp. 343-352, DOI: 10.1007/978-3-319-66429-3_33 [M33]

  33. Milan Gnjatović, JovicaTasevski, Dragiša Mišković, SrđanSavić, Branislav Borovac, Aleksandra Mikov, Rastislava Krasnik (2017) “Pilot Corpus of Child-Robot Interaction in Therapeutic Settings”, in Proc. of the 8th IEEE International Conference on Cognitive Infocommunications (CogInfoCom), Debrecen, Hungary, 11-14.09.2017, pp. 253-257. ISBN: 978-1-5386-1264-4/17 [M33]

  34. SrđanSavić, Milan Gnjatović, Dragiša Mišković, JovicaTasevski, Nemanja Maček (2017) „Cognitively-Inspired Symbolic Framework for Knowledge Representation“, in Proc. of the 8th IEEE International Conference on Cognitive Infocommunications (CogInfoCom), Debrecen, Hungary, 11-14.09.2017, pp. 315-320. ISBN: 978-1-5386-1264-4/17[M33]

  35. Siniša Suzić, Tijana Delić, Darko Pekar, Vladimir Ostojić (2017) “Novel alignment method for DNN TTS training using HMM synthesis models”, IEEE International Symposium on Intelligent Systems and Informatics (SISY), Subotica, 14-16.09.2017., ISBN: 978-1-5386-3855-2/17, pp. 271-276, DOI: 10.1109/SISY.2017.8080585 [M33]

  36. Milan Gnjatović, Nemanja Maček, ZlatogorMinchev (2017) “Methodological Pitfalls of Automatic Speech Recognition”, in Proc. of the 9th International Conference on Business Information Security (BISEC), Belgrade, October 2017, pp. 54-57 [M33]

  37. Ivan Jokić, Stevan Jokić, Vlado Delić, Zoran Perić (2017) “Towards Enabling Measurement of Similarity of Acoustical Environments Using Mobile Devices”, Proceedings of the 13th International Conference on Advanced Technologies, Systems and Services in Telecommunications (TELSIKS), Serbia, Niš, 18-20.10.2017, ISBN: 978-1-5386-1798-4 (IEEE) 978-86-6125-189-4 (FEE), pp. 195-198 [M33]

  38. Ivan Jokić, Stevan Jokić, Vlado Delić, Zoran Perić (2017) “Application of algorithm for automatic speaker recognition based on use of Mel-frequency cepstral coefficients in music”, The 4th International Acoustics and Audio Engineering Conference (TAKTONS), N. Sad, Serbia, 22-25.11.2017., ISBN: 978-86-7892-994-6, pp. 9-11 [M33]

  39. Tijana Delić, Milan Sečujski, Siniša Suzić (2017)“A review of Serbian parametric speech synthesis based on deep neural networks”, Telfor Journal, Telecommunications Society and Academic Mind, Belgrade, ISSN: 1821-3251, Vol. 9, No. 1, pp. 32-37, DOI: 10.5937/telfor1701032D [M52] http://journal.telfor.rs/

  40. Tijana Delić, Siniša Suzić, Stevan Ostrogonac, Simona Đurić, Darko Pekar (2017) „Multi-style statistical parametric TTS“, 11th DOGS, Digital Speech and Image Processing, Novi Sad, Serbia, 22-25.11.2017., ISBN: 978-86-7892-993-9, pp. 5-8 [M63]

  41. Milan Sečujski, Stevan Ostrogonac, Siniša Suzić, Darko Pekar (2017) „Reprodukcijarečeničnognaglaska u sintezigovoranaameričkomengleskomjeziku“ (Reproduction of emphasis at sentence level in American English speech synthesis), 11th DOGS, Digital Speech and Image Processing, Novi Sad, Serbia, 22-25.11.2017., ISBN: 978-86-7892-993-9, pp. 9-12 [M63]

  42. Edvin Pakoci, Branislav Popović, Darko Pekar (2017) „Fast sequence-trained deep neural network models for Serbian speech recognition“, 11th DOGS, Digital Speech and Image Processing, Novi Sad, Serbia, 22-25.11.2017., ISBN: 978-86-7892-993-9, pp. 25-28 [M63]

  43. Ivan Jokić, Stevan Jokić, Vlado Delić, Zoran Perić (2017) „Proširenjepostupkazaautomatskoprepoznavanjegovornikanaostalezvukove u prirodi“ (Extension of procedure for automatic speaker recognition to other sounds in nature), 11th DOGS, Digital Speech and Image Processing, Novi Sad, Serbia, 22-25.11.2017., ISBN: 978-86-7892-993-9, pp. 33-36 [M63]

  44. Nikša Jakovljević, Robert Černjanski, Dragiša Mišković, Vlado Delić (2017) „AplikacijazaunostekstapomoćuglasanatelefonusaoperativnimsistemomAndroid“ (A text input mechanism based on voice recognition for Android smartphones), 11th DOGS, Digital Speech and Image Processing, Novi Sad, Serbia, 22-25.11.2017., ISBN: 978-86-7892-993-9, pp. 41-44 [M63]

  45. Zoran Perić, Siniša Suzić, Tijana Delić (2017) „Optimizacijamaksimalne amplitude i izborkonstante A semilogaritamskogkvantizerazauzakdinamičkiopseg“ (Optimization of maximal amplitude and selection of constant A for semilogaritmicquantizer for narrow dynamic range), 11th DOGS, Digital Speech and Image Processing, Novi Sad, Serbia, 22-25.11.2017., ISBN: 978-86-7892-993-9, pp. 49-52 [M63]

  46. Dragiša Mišković, Milan Gnjatović, Nikša Jakovljević, Vlado Delić (2017) „Realizacija audio-bibliotekeUniverziteta u NovomSadu“ (Development of the audio library of the University of Novi Sad), 11th DOGS, Digital Speech and Image Processing, Novi Sad, Serbia, 22-25.11.2017., ISBN: 978-86-7892-993-9, pp. 53-56 [M63]

  47. Dragiša Mišković(2017) “Kontekstnozavisnoprepoznavanjegovora u interakcijiizmeđučoveka i mašine” (Context-Dependent Speech Recognition in human-machine interaction), Doctoral Dissertation, Faculty of Technical Sciences, Novi Sad, 02.06.2017, mentor Vlado Delić [M71]

  48. Branislav Popović, Edvin Pakoci, Darko Pekar, Vlado Delić (2017) „Poboljšanjeperformansisistemazaglasovnopozivanje (VoiceDial) primenom Chain dekodera“ (Improving the Performance of the Voice Calling System (VoiceDial) by Using the Chain Decoder), Significantly improved technical solution applied on the national level, FTS andAlfaNumd.o.o., Novi Sad, verified on FTS on 27.12.2017. (submitted for verification to MESTD) [M84] http://ftn.uns.ac.rs/n1109667516/tehnicka-resenja

  49. Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh, „Continuous vocoder in feed-forward deep neural network based speech synthesis”, In: Digital speech and image processing (DOGS2017). Konferencia helye, ideje: Novi Sad, Szerbia, 2017.11.22-2017.11.25.pp. 1-4.

  50. Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh, „Deep recurrent neural networks in speech synthesis using a continuous vocoder” LECTURE NOTES IN COMPUTER SCIENCE 10458: pp. 282-291. (2017), Speech and Computer: 19th International Conference. Hatfield, Egyesült Királyság / Anglia: 2017.09.12 -2017.09.15.

  51. Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh, „Time-domain envelope modulating the noise component of excitation in a continuous residual-based vocoder for statistical parametric speech synthesis”, In: Lacerda F, Strombergsson S, Wlodarczak M, Heldner M, Gustafson J, House D (szerk.), Interspeech 2017. Konferencia helye, ideje: Stockholm, Svédország, 2017.08.20-2017.08.24. (2017)pp. 434-438. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; 2017-August. )

  52. Darko Pekar, Branislav Popović, Edvin Pakoci, Dragiša Mišković, Vlado Delić, Milan Sečujski (2018) „Dubokeneuronskemreženaserveru u kombinacijisalokalnimdekoderomzaprepoznavanjegovora“ (Cloud-Based Deep Neural Networks Combined with Local Speech Recognition Decoder), AlfaNumLtd, Novi Sad, 21.06.2016, application number P-2016/0452. ([M87 u 2016]; Published in the intellectual property bulletin, number 1/2018, 31.01.2018.Published patent at the national level [M94 in 2018]

  53. Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh ,,A Continuous Vocoder using Sinusoidal Model for Statistical Parametric Speech Synthesis'', SPECOM 2018, Lipcse, Németország, pp. 11-20, 2018.

  54. Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh, ,,RNN-based speech synthesis using a continuous sinusoidal model'', IJCNN 2019, (International Joint Conference on Neural Networks), Budapest, Magyarország, 2019, elfogadva.

  55. Sevinj Yolchuyeva, Géza Németh, Bálint Gyires-Tóth, "Grapheme-to-Phoneme Conversion with Convolutional Neural Networks", Applied Sciences 2019, 9(6), 1143,

  56. Sevinj Yolchuyeva, Géza Németh, Bálint Gyires-Tóth, "End-to-end Convolutional Neural Networks for Intent Detection", XV. Magyar Számítógépes Nyelvészeti Konferencia, Szeged, 2019. január 24–25. pp. 123-134.

  57. Tarján Balázs, Fegyó Tibor, Mihajlik Péter, „Ügyfélszolgálati beszélgetések nyelvmodellezése rekurrens neurális hálózatokkal” In: Berend, Gábor; Gosztolya, Gábor; Vincze, Veronika (szerk.) XV. Magyar Számítógépes Nyelvészeti Konferencia, Szeged, Magyarország : Szegedi Tudományegyetem, Informatikai Intézet, (2019) pp. 23-33.

  58. Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik, N-gram Approximation of LSTM Recurrent Language Models for Single-pass Recognition of Hungarian Call Center Conversations, benyújtva: CogInfoCom’2019 konferencia

  59. Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik , Investigation on n-gram approximated RNNLMs for recognition of morphologically rich speech, benyújtva: SLSP’2019 konferencia

  60. Előadások, disszemináció:

  61. Vlado Delić, Milan Sečujski, Nikša Jakovljević, Tijana Delić (2017) „Govornakomunikacijačovek-mašinapomoćuveštačkihneuronskihmreža“ (Human-Machine Speech Communication Using Artificial Neural Networks), invited presentation, AI & ML community of Serbia, 26 December 2017, Belgrade, https://www.meetup.com/AI-Serbia-Meetup/events/past/

  62. Milan Sečujski (2017) „Sintezagovoranaosnovuteksta“ (Text-To-Speech Synthesis), a lecture at thePetnica Science Centre, May 2017

  63. Tijana Delić (2017) „Govornakomunikacijačovek-mašina“ (Human-Machine Speech Communication), lectures in one secondary and one elementary school in Belgrade within the framework of the “O group” project, supported by the Centre for the Promotion of Science

  64. Vlado Delić (2017) „Dostignuća u razvojugovornihtehnologija i perspektivenjihoveprimene u pametnimkućama“ (Achievements in the development of speech technologies and the prospects of their application in smart homes). Section of designers of the Chamber of Commerce and Industry of Serbia, 7th series of professional lectures, design improvement of telecommunication networks and systems; Lecture program: „Sistemiupravljanjapametnimzgradama i gradovima“ (Management systems for smart buildings and cities), Chamber of Commerce and Industry of Serbia, Belgrade, 20 July 2017.

  65. Tijana Delić (2017) “Speech synthesis based on Deep Neural Networks – our solutions for English and Serbian”, invited lecture for teaching and research staff and students of doctoral studies at the Faculty of Applied Sciences, University of West Bohemia, and the associates of the research centre NTIS - New Technologies for the Information Society, organized within the ERASMUS+ Staff Mobility Programme.

  66. Nikša Jakovljević (2017) “A Review of Speaker Recognition Algorithms Used at the Faculty of Technical Sciences”, invited lecture for teaching and research staff and students of doctoral studies at the Faculty of Applied Sciences, University of West Bohemia, and the associates of the research centre NTIS - New Technologies for the Information Society, organized within the ERASMUS+ Staff Mobility Programme.

  67. Branislav Popović (2017) “Speech Recognition for the Serbian Language”, invited lecture for teaching and research staff and students of doctoral studies at the Faculty of Applied Sciences, University of West Bohemia, and the associates of the research centre NTIS - New Technologies for the Information Society, organized within the ERASMUS+ Staff Mobility Programme.

  68. Németh Géza (2017) „Kempelentől a WaveNet-ig:a gépi beszédkeltés tudományának fejlődése”, Meghívott előadás a Magyar Tudomány Ünnepe alkalmából szervezett „A humán tudományok és a gépi intelligencia” konferencián az MTA Nyelvtudományok osztálya szervezésében, 2017.11.20.

  69. Németh Géza (2017) „A gépi beszédkeltés kihívásai AAK- alkalmazásokban”, Meghívott előadás a Bliss Alapítvány 30 éves évfordulóján, az „Egy emberöltő Az Akadályozott Kommunikációval élők szolgálatában” konferencián, 2017. október 6. http://www.blissalapitvany.hu/wp-content/uploads/2017/09/bliss30-plakat-es-program.pdf

  70. Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh (2018) ,,Improving continuous F0 estimator with adaptive time-warping for high-quality speech synthesis'', Beszédkutatás 2018, Budapest, Magyarország, 2018. október 18-19.

  71. Európa első interaktív mesterséges intelligencia kiállítása (2019) Magyarországi Mesterséges Intelligencia Koalíció által szervezett interaktív kiállításon többek között a pályázat eredményeit is bemutattuk az érdeklődő közönségnek

  72. Sajtóközlemény a projekt zárásáról.

  73. Egyszerű bemutató a beszédfelismerő program működéséről.

A projekt résztvevői:


ftn alfanum Budapest University of technology and economics

Slovac academy of sciences speechtex hsminformatika

Kapcsolat:

A DANSPLAT projekt nemzetközi konzorcimának vezetője: Faculty of Technical Sciences, University of Novi Sad, Serbia. A projekt koordinátor dr Vlado Delić.
A hazai konzorcium vezetője a SpeechTex Kft.