The O-COCOSDA 2017 Organizing committee is pleased to announce the following distinguished keynote speakers to give plenary talks at the conference:

  • Dr. Joseph Mariani (LIMSI-CNRS, France), Rediscovering 50 Years of Discoveries in Speech and Language Processing:A Survey.
  • Prof. Nick Campbell(Trinity College Dublin, Ireland), Corpora of Spoken Interaction; Watching People Talk
  • Dr. Young-Jik Lee( ETRI, Korea), Recent Speech and Language Researches in ETRI



Rediscovering 50 Years of Discoveries in Speech and Language Processing:A Survey.
(Joseph Mariani)


Dr. Joseph Mariani
Gil FRANCOPOULO, Tagmatica


Joseph Mariani conducted his first research activities on Speech Recognition at LIMSI, a laboratory of CNRS, the French National Center for Scientific Research, in 1973 before taking the responsibility of its “Speech Communication” group. He then joined Fred Jelinek’s team at the IBM T.J. Watson Research Center as a World Trade Visiting Scientist in 1985. When he returned LIMSI, he became in 1987 head of its "Human-Machine Communication” department, covering various modalities (spoken, written and signed language processing, computer vision, computer graphics, gestural communication, Virtual and Augmented Reality) with various approaches (Computer Science, Signal Processing, Linguistics, Cognitive Science, Human Factors and Social Sciences). He was appointed general director of LIMSI from 1989 to 2000.

He then became Director of the "Information and Communication Technologies" department at the French Ministry for Research from 2001 to 2006. In this framework, he managed several national programs, and he launched in particular the Techno-Langue and Techno-Vision actions, addressing technology development and assessment in the domains of Language Technology and Computer Vision.

He was then nominated director of the Institute for Multilingual and Multimedia Information (IMMI), a French-German joint International Laboratory involving LIMSI, the Karlsruhe Institute of Technology (KIT) and RWTH Aachen, settled in 2007 in the framework of the Quaero national French program.

Joseph Mariani was president of the CNRS “Information Science and Technology” Committee and a member of the CNRS Scientific Advisory Council and Ethics Committee (COMETS), where he coordinated a report on the ethics of ICT which resulted in the creation of the French National Ethics Committee for Information Science and Technology (CERNA).

On the international scene, he launched and coordinated FRANCIL, the Language Technology Network of the Francophone Universities Association (AUF), initiated and chaired in 1988 the “European Speech Communication Association”, now “International Speech Communication Association” (ISCA), where he launched in 1989 the Eurospeech conference, now Interspeech. He also initiated in 1995 the “European Language Resources Association” (ELRA), where he is now Honorary President, and in 1998 the “Language Resources and Evaluation Conference” (LREC). He was the first general convenor of Cocosda (the Coordinating Committee on Speech Databases and Speech input/output systems Assessment) at its creation in 1991. He seated in the Board of the “European Language & Speech Network of Excellence” (ELSNET), in the Steering Committee of FLaReNet (the “Fostering Language Resources Network”) and in the Management Board and Council of META-NET (the “Multilingual Europe Technology Alliance”).

He was or still is in the Editorial Committees of the “Speech Communication”, “Speech Technology” and “Language Resources and Evaluation” Journals. An author of more than 500 publications, he co-edited the "Survey of the State-of-the-Art in Human Language Technology" and edited the “Spoken Language Processing” monograph.

Joseph Mariani is now Research Director Emeritus at CNRS. His research activities concern Spoken Language Processing, Human-Machine Communication and Human Language Resources and Technologies.


We have created the NLP4NLP corpus to study the content of scientific publications in the field of speech and natural language processing. It contains articles published in 34 major conferences and journals in that field over a period of 50 years (1965-2015), comprising 65,000 documents, gathering 50,000 authors, including 325,000 references and representing approximately 270 million words. Most of these publications are in English, some are in French, German or Russian. Some are open access, others have been provided by the publishers.

In order to constitute and analyze this corpus several tools have been used or developed. Some of them use natural language processing methods that have been published in the corpus, hence its name. Numerous manual corrections were necessary, which demonstrated the importance of establishing standards for uniquely identifying authors, publications or resources.

We have conducted various studies: evolution over time of the number of articles and authors, collaborations between authors, citations between papers and authors, evolution of research themes and identification of the authors who introduced them, detection of innovations and epistemological ruptures, use of language resources, reuse of articles and plagiarism in the context of a global or comparative analysis between sources.

Corpora of Spoken Interaction; Watching People Talk
(Nick Campbell)


Prof. Nick Campbell
Trinity College Dublin


Nick Campbell ( is a Professor and Fellow Emeritus, Director of the Speech Communication Lab at Trinity College Dublin (The University of Dublin) in Ireland. He received his Ph.D. degree in Experimental Psychology from the University of Sussex in the U.K. He was invited to TCD in 2008 as Professor of Phonetics and Speech Communication, and was an SFI Stokes Professor until 2015 when he suffered mandatory age-related retirement and was appointed to the School of Computer Science and Statistics as Adjunct Professor. Until 2008 he was a Senior Scientist at the Japanese National Institute of Information and Communications Technology, (as and Chief Researcher in the Department of Acoustics and Speech Research, Advanced Telecommunications Research Institute International (as, Kyoto, Japan, where he also served as Research Director for the JST/CREST Expressive Speech Processing and the SCOPE “Robot’s Ears” projects. He was first invited as a Research Fellow at the IBM U.K. Scientific Centre, where he developed algorithms for speech synthesis, and later at the AT&T Bell Laboratories, where he worked on the synthesis of Japanese. He served as Senior Linguist at the Edinburgh University Centre for Speech Technology Research before joining ATR in 1990. His research interests are based on large speech databases, and include nonverbal speech processing, concatenative speech synthesis, and prosodic information modeling. He was Visiting Professor at the School of Information Science, Nara Institute of Science and Technology (NAIST), Nara, Japan, and was also Visiting Professor at Kobe University, Kobe, Japan for 10 years. [h-index 37(23), i10 131(63) May ’17]


This talk will describe recent work at the Speech Communication Lab in the University of Dublin, Ireland, where our focus is on non-verbal aspects of spoken and social interaction. We are developing autonomous conversational agents for language learning and call-centre applications and have discovered that much information regarding the cognitive states of interlocutors can be gained by processing of synchronous aspects of low-level audio and video input. The talk will be illustrated with samples of our research and recordings of people interacting spontaneously and naturally with computer-based dialogue interfaces. This work comes under the umbrella of Interactive Speech Synthesis.

Recent Speech and Language Researches in ETRI
(Young-Jik Lee)


Dr. Young-Jik Lee
ETRI, Korea


Youngjik Lee received the B.S. degree in electronics engineering from Seoul National University, Seoul, Korea in 1979, the M.S. degree in electrical engineering from Korea Advanced Institute of Science and Technology, Seoul, Korea in 1981 and the Ph.D. degree in electrical engineering from the Polytechnic University, Brooklyn, New York, USA.

From 1981 to 1985 he was with Samsung Electronics Company, where he had developed video display terminals. From 1985 to 1988 he had worked on sensor array signal processing. Since 1989, he has been with Electronics and Telecommunications Research Institute pursuing researches in language and speech including speech recognition, speech synthesis, automatic speech translation, machine translation, question and answering, and neural networks.


This Keynote describes recent research activities in speech and language areas in Electronics and Telecommunications Research Institute (ETRI).

Speech and language research has been a major theme for more than twenty years in ETRI. The goal of the research starts with spoken language translation. During the twenty years, ETRI has added more goals in speech and languages researches such as voice commands for interactive game, 450K word recognition for POI(point of interest) selection, Korean-to-English patent translation, Exo-Brain question answering, GenieTutor computer assisted language learning.(CALL), and GenieTalk 9-language speech translation.

Among them, the speaker will present the last three goals, which are the most recent researches.