CURRICULUM VITAE. ALEXANDROS LAZARIDIS, PhD Electrical and Computer Engineer

Transcription

1 CURRICULUM VITAE ALEXANDROS LAZARIDIS, PhD Electrical and Computer Engineer Thessaloniki, Sept 2012

2 [THIS PAGE HAS INTENTIONALLY BEEN LEFT BLANK] 2

3 Contents Personal Details... 4 General Information... 4 Current Positions... 4 Academic Qualifications... 5 Special Knowledge in Computers... 5 Languages... 5 Teaching Experience... 6 Participation in Conferences... 6 Research Interests and Expertise... 6 R&D Project Experience... 7 PhD Dissertation... 7 Publications in Journals... 8 Publications in Book Chapters... 8 Publications in Conferences... 9 Technical Reports Citations Experience and Skills Related to the Position

4 Personal Details First Name ALEXANDROS Last Name LAZARIDIS Father s Name ANASTASIOS GEORGIOS Address 2A SOFOKLEOUS STR., P.C , THESSALONIKI, GREECE No Mobile No alaza@upatras.gr; alaza@live.com Webpage Nationality GREEK Date of birth 08/04/1981 General Information Alexandros Lazaridis was born in Thessaloniki, Macedonia, Greece, in He graduated in September of 2005 from the Department of Electrical & Computer Engineering at Aristotle University of Thessaloniki, in Greece. He was accepted as a PhD student at the Wire Communications Laboratory at the Department of Electrical and Computer Engineering at the University of Patras in October of 2005 and received his PhD in February of His fields of research include Speech Processing, Voice Conversion, Speech Synthesis and Speech Prosody. His published work consists of 22 papers: 5 journal papers, 4 book chapters, 10 conference papers and 3 technical reports. Nine confirmed third-party citations to the published work of Alexandros Lazaridis have been recorded. Currently he is post-doctoral researcher at the University of Patras and at the Aristotle University of Thessaloniki and non-tenured Lecturer at the University of Western Macedonia, at the Technological Educational Institute of Thessaloniki and at the Technological Educational Institute of Serres. Current Positions Lecturer (non-tenured) at the University of Western Macedonia, Greece Lecturer (non-tenured) at the Technological Educational Institute of Thessaloniki, Greece Lecturer (non-tenured) at the Technological Educational Institute of Serres, Greece Post-Doc Researcher at Informatics Department at Aristotle University of Thessaloniki, Greece. Post-Doc Researcher at Electrical Engineering and Technology Department at the University of Patras, Greece. 4

5 Academic Qualifications Nov Today Post-Doc Researcher at Informatics Department at Aristotle University of Thessaloniki, Greece. Feb Today Post-Doc Researcher at Electrical Engineering and Technology Department at the University of Patras, Greece. Nov Feb Accepted at the University of Patras in the Department of Electrical Engineering and Technology as a PhD student. - Title of the PhD Thesis: Prosody modelling using machine learning techniques for neutral and emotional speech synthesis. Oct Sept Diploma in Electrical and Computer Engineering, Department of Electrical and Computer Engineering, Faculty of Engineering, Aristotle University of Thessaloniki - Direction of Studies: Electronics and Computers - Grade: 6.62/10 Oct July 1999 High School Certificate, 2nd High School of Thessaloniki - Grade: 18.1/20 Special Knowledge in Computers Operating systems: MS Windows, MS DOS, Linux Programming Languages: Fortran, C, Matlab, Visual Basic Software: MS Office Specialized Software: CoolEdit (audio processing), SPSS (statistical analysis), WEKA (machine learning), Festival Speech Synthesis System, HTS (Speech Synthesis), Flite Speech Synthesis Engine, MARY Text-to- Speech System, MBROLA Speech Synthesis System Edinburgh Speech Tools Library (speech processing) Languages Greek (first language) English (Proficiency) 5

6 - Certificate of Proficiency in English awarded by the University of Cambridge (Dec 2001) Grade C Teaching Experience Feb Today Lecturer at the University of Western Macedonia, Greece - Digital Design I Sept Today Lecturer at the Technological Educational Institute of Thessaloniki, Greece - Informatics I Lecturer at the Technological Educational Institute of Serres, Greece - Digital Signal Processing - Informatics I - Informatics II Sept July 2010 Assisting in the course Speech Technology of the Department of Electrical Engineering and Technology at the University of Patras. Feb July 2008 Assisting in the course Introduction to Computers of the Department of Electrical Engineering and Technology at the University of Patras. Participation in Conferences 13th International Conference on Speech and Computer (SPECOM 2009), June 21st to 25th of 2009, Saint-Petersburg, Russia. 11th International Conference on Text, Speech and Dialogue (TSD 2008), Sept. 8th to 12th of 2008, Brno, Czech Republic. 18th European Conference on Artificial Intelligence (ECAI 2008), July 21st to 25th of 2008, Patras, Greece. 19th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2007), Oct. 29th to 31st of 2007, Patras, Greece. 12th International Conference on Speech and Computer (SPECOM 2007), Oct. 15th to 18th of 2007, Moscow, Russia. Research Interests and Expertise Human-computer Interaction Speech Processing, Voice Conversion, Speech Prosody, 6

7 Data Mining, Machine Learning, Emotional Speech Speech Synthesis - HMM-based Speech Synthesis System (HTS) - Festival Speech Synthesis System - Flite Speech Synthesis Engine - MARY Text-to-Speech System - MBROLA Speech Synthesis System R&D Project Experience Since November of 2005, Alexandros Lazaridis has participated as a researcher and occasionally as an administrative assistant in the following European and National research projects: MDD /98-06-NOR090: Electronic Dictionary of Pronunciation and Usage of the Grecanic Dialect of South Italy. GEMINI (FP ): Generic Environment for Multilingual Interactive Natural Interfaces. LE DGXIII-IDAS: Interactive, Telephone-based, Directory Assistance Services. INSPIRE (IST ): Infotainment Management with speech Interaction via Remote-Microphones and Telephone Interfaces. MOVEON (IST ): Multi-modal and multi-sensor zerodistraction interaction interface for two wheel vehicles ON the move. PLAYMANCER (FP ): PlayMancer: A European serious gaming 3D Environment. LOGOS: A general architecture for speech recognition and user friendly dialogue interaction for advanced commercial applications. PROMETHEUS (FP ): Prediction and Interpretation of human behaviour based on probabilistic models and heterogeneous sensors. ΑΜΙΒΙΟ (LIFE08 NAT/GR/000539): Automatic acoustic monitoring and inventory of biodiversity. PhD Dissertation Alexandros Lazaridis, "Prosody modelling using machine learning techniques for neutral and emotional speech synthesis",

8 Publications in Journals [1] Alexandros Lazaridis, Iosif Mporas, Todor Ganchev, "Phone Duration Modeling of Affective Speech using Support Vector Regression", International Journal of Intelligent Systems and Applications, 8, 1-9, [2] Alexandros Lazaridis, Todor Ganchev, Iosif Mporas, Evaggelos Dermatas, Nikos Fakotakis, "Two-stage phone duration modelling with feature construction and feature vector extension for the needs of speech synthesis", Computer Speech and Language, 26, , [3] Alexandros Lazaridis, Iosif Mporas, Todor Ganchev, George Kokkinakis, Nikos Fakotakis, "Improving Phone Duration Modeling using Support Vector Regression Fusion", Speech Communication, 53 (1), 85-97, [4] Alexandros Lazaridis, Todor Ganchev, Theodoros Kostoulas, Iosif Mporas, Nikos Fakotakis, "Phone Duration Modeling: Overview of Techniques and Performance Optimization via Feature Selection in the context of Emotional Speech", International Journal of Speech Technology, 13 (3), , [5] Alexandros Lazaridis, Basiliki Bourna and Nikos Fakotakis, "Comparative Evaluation of Phone Duration Models for Greek Emotional Speech", Journal of Computer Science, 6 (3), , Publications in Book Chapters [1] Theodoros Kostoulas, Todor Ganchev, Alexandros Lazaridis, Nikos Fakotakis, "Enhancing Emotion Recognition from Speech through Feature Selection", Text, Speech and Dialogue, TSD 2010, Lecture Notes in Computer Science, Springer Berlin / Heidelberg pp , [2] Alexandros Lazaridis, Todor Ganchev, Iosif Mporas, Theodoros Kostoulas and Nikos Fakotakis, "Feature Selection for Improved Phone Duration Modeling of Greek Emotional Speech", SETN 2010, Advances in Artificial Intelligence, Lecture Notes in Computer Science, Springer Berlin / Heidelberg, pp [3] Todor Ganchev, Alexandros Lazaridis, Iosif Mporas, Nikos Fakotakis, "Performance Evaluation for Voice Conversion Systems", Text, Speech and Dialogue, TSD 2008, Lecture Notes in Computer Science, Springer Berlin/ Heidelberg, pp [4] Theodoros Kostoulas, Iosif Mporas, Todor Ganchev, Nikos Katsaounos, Alexandros Lazaridis, Stavros Ntalampiras, Nikos Fakotakis, "LOGOS: A 8

9 Multimodal Dialogue System for Controlling Smart Appliances", KES IIMSS 2008, New Directions in Intelligent Interactive Multimedia, Studies in Computational Intelligence (142), pp Publications in Conferences [1] Alexandros Lazaridis, Iosif Mporas, Todor Ganchev and Nikos Fakotakis, "Support vector regression fusion scheme in phone duration modeling", in Proc. ICASSP 2011, pp , May [2] Alexandros Lazaridis, Iosif Mporas, Nikos Fakotakis, "Comparison of HSMM Training Approaches for Emotional Speech Synthesis", in Proc. ACOUSTICS [3] Alexandros Lazaridis, Theodoros Kostoulas, Todor Ganchev, Iosif Mporas, Nikos Fakotakis, "VERGINA: A modern Greek speech database for speech synthesis", in Proc. LREC 2010, Malta, May 19-21, 2010, pp [4] Dimitrios P. Lyras, George Kokkinakis, Alexandros Lazaridis, Kyriakos Sgarbas, Nikos Fakotakis, "A Large Greek-English Dictionary with Incorporated Speech and Language Processing Tools", in Proc. INTERSPEECH 2009, UK, September 6-10, 2009, pp [5] Iosif Mporas, Alexandros Lazaridis, Todor Ganchev, Nikos Fakotakis, "Using Hybrid HMM-based Speech Segmentation to improve Synthetic Speech Quality", in Proc. 13th Pan-Hellenic Conference on Informatics, PCI 2009, Corfu, Greece, September 10-12, 2009, pp [6] Vasiliki Bourna, Alexandros Lazaridis, Nikos Fakotakis, "Phone Duration Modeling for Greek Emotional Speech Synthesis", in Proc. 13th International Conference "SPEECH and COMPUTER", SPECOM 2009, Saint-Petersburg, Russia, June 21-25, 2009, pp [7] Todor Ganchev, Alexandros Lazaridis, Iosif Mporas, Nikos Fakotakis, "Average Performance Loss Measure for Assessment of Voice Conversion Systems", in Proc. 13th International Conference "SPEECH and COMPUTER", SPECOM 2009, Saint-Petersburg, Russia, June 21-25, 2009, pp [8] Todor Ganchev, Otilia Kocsis, Nikos Katsaounos, Iosif Mporas, Alexandros Lazaridis, Theodoros Kostoulas, Stavros Ntalampiras, Dimitrios Lyras, George Papadopoulos, Kyriakos Sgarbas, Nikos Fakotakis, "Natural Spoken Dialogue Interaction: Technology, Tools, Resources and Applications", System Demonstrations, in Proc. 18th European 9

10 Conference on Artificial Intelligence, ECAI 2008, July 21-25, 2008, pp [9] Alexandros Lazaridis, Theodoros Kostoulas, Iosif Mporas, Todor Ganchev, Nikos Katsaounos, Stavros Ntalampiras, Nikos Fakotakis, "Human Evaluation of the LOGOS Spoken Dialogue System", in Proc. 1st International International Conference on Pervasive Technologies Related to Assistive Environments, PETRA 2008, Athens, Greece, July 15-19, [10] Alexandros Lazaridis, Panagiotis Zervas, Nikos Fakotakis, George Kokkinakis, "A CART approach for Duration Modeling of Greek Phonemes", in Proc. 12th International Conference "SPEECH and COMPUTER", SPECOM 2007, Moscow, Russia, October 15-18, 2007, pp [11] Alexandros Lazaridis, Panagiotis Zervas, George Kokkinakis, "Segmental duration modeling for Greek Speech Synthesis", in Proc. 19th IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Patras, Greece, October 29-31, 2007, pp Technical Reports [1] Thomas Winkler, Todor Ganchev, Theodoros Kostoulas, Iosif Mporas, Alexandros Lazaridis, Stavros Ntalampiras, Atta Badii, Rick Adderley, Christian Bonkowski, "MoveOn Deliverable D.5: Report on Audio databases, Noise processing environment, ASR and TTS modules", December [2] Alexandros Lazaridis, Nikos Katsaunos, "MoveOn deliverable D5.10.2: Report on the MoveOn TTS component", October Citations [1] Alexandros Lazaridis, Iosif Mporas, Todor Ganchev, George Kokkinakis, Nikos Fakotakis, "Improving Phone Duration Modeling using Support Vector Regression Fusion", Speech Communication 53(1), 85-97, Cited in: o Siraj, F., Mustafa, N., Haris, M.F., Yusof, S.R.M., Salahuddin, M.A., Hasan, Md.R.: (2011). Pre-selection of recruitment candidates using case based reasoning, Proceedings - CIMSim 2011: 3rd International Conference on Computational Intelligence, Modelling and Simulation, art. no , pp o I. Sainz, D. Erro, E. Navas, J. Adell, A. Bonafonte (2011). BUCEADOR hybrid TTS for Blizzard Challenge 2011", The Blizzard Challenge

11 o Sainz, I., Erro, D., Navas, E., Hernaez, I. (2011) A Hybrid TTS Approach for Prosody and Acoustic Modules, Proc. of the Interspeech, 2011, pp [2] Theodoros Kostoulas, Todor Ganchev, Alexandros Lazaridis, Nikos Fakotakis, "Enhancing Emotion Recognition from Speech through Feature Selection", TSD 2010, Lecture Notes in Computer Science, Springer Berlin / Heidelberg, pp , Cited in: o Planet Santiago, Iriondo Ignasi, "Improving Spontaneous Children s Emotion Recognition by Acoustic Feature Selection and Feature-Level Fusion of Acoustic and Linguistic Parameters Book Title: Advances in Nonlinear Speech Processing", Advances in Nonlinear Speech Processing 5th International Conference on Nonlinear Speech Processing, NOLISP 2011, Las Palmas de Gran Canaria, Spain, November 7-9, [3] Theodoros Kostoulas, Iosif Mporas, Todor Ganchev, Nikos Katsaounos, Alexandros Lazaridis, Stavros Ntalampiras, Nikos Fakotakis, "LOGOS: A Multimodal Dialogue System for Controlling Smart Appliances", KES IIMSS 2008, New Directions in Intelligent Interactive Multimedia, Studies in Computational Intelligence (142), pp Cited in: o Spyros Lalis, Jaroslaw Domaszewicz, Aleksander Pruszkowski, Tomasz Paczesny, Mikko Ala-Louko, Markus Taumberger, Giorgis Georgakoudis, Kostas Lekkas, "Tangible Applications for Regular Objects: An End-User Model for Pervasive Computing at Home", in UBICOMM 2010 : The Fourth International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies, pp , [4] Alexandros Lazaridis, Theodoros Kostoulas, Iosif Mporas, Todor Ganchev, Nikos Katsaounos, Stavros Ntalampiras, Nikos Fakotakis, "Human Evaluation of the LOGOS Spoken Dialogue System", In Proceedings of the 1st International International Conference on Pervasive Technologies Related to Assistive Environments, PETRA 2008, Athens, Greece, July, Cited in: o Hannig Hannes, Einsatz von sprach- und gerauschsensitiven Systemen in Smart Home Umgebungen, HASE'10 - HCI Aspects of Smart Environments, pp , [5] Alexandros Lazaridis, Panagiotis Zervas, George Kokkinakis, "Segmental duration modeling for Greek Speech Synthesis", In Proceedings of the 19th 11

12 IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Patras, Greece, 2007, pp Cited in: o Mporas, I., Automatic segmentation of digital speech signals and application to speech synthesis, speech recognition and language recognition. Ph.D. Dissertation. o Bourna, V., 2008, Segmentation of speech in for recognition and synthesis of emotional speech. Diploma Thesis, University of Patras. [6] Alexandros Lazaridis, Panagiotis Zervas, Nikos Fakotakis, George Kokkinakis, "A CART approach for Duration Modeling of Greek Phonemes", In Proceedings of the 12th International Conference "Speech and Computer", Moscow, Russia, October 2007, pp Cited in: o Milan Secujski Darko Pekar, Dragan Knezevic, Vladimir Svrkota, Prosody prediction in speech synthesis based on regression trees, in Proc of. SinFonljA 3, o Sovilj-Nikić, S., 2008, Modeling of segmental duration in speech synthesis, In Proceedings of the 16th TELFOR, Beograd, Serbia, November 2008, pp Experience and Skills Related to the Position Speech Synthesis o Designing and building speech database for speech synthesis o Festival Speech Synthesis Framework Diphone and Unit-selection Voices (Greek and English languages) Prosodically Rich Voices Emotional Unit-selection Voices o Flite Speech Synthesis Engine o HMM-based Speech Synthesis (HTS) Greek and English Voices Emotional Voices (Adaptation Techniques) o MARY Text-to-speech Synthesis System o MBROLA Speech Synthesis System Prosody Modelling o Phone Duration Modelling (Machine Learning) Voice Conversion o Speaker Conversion o Emotion Conversion o Objective Voice Conversion evaluation through Speaker Identification. 12