People

Faculty

Maxine Eskenazi

Maxine S. Eskenazi received her Bachelor of Arts degree in Modern Languages from Carnegie-Mellon University in 1973. She received her DEA (Diplome d’Etudes Approfondies - equiv. Masters) in Linguistics from the University of Paris VII in 1981 and her Doctorat de Troisieme Cycle in Computer Science from the University of Paris XI in 1984. Her thesis was on “Caracterisation acoustique des voyelles francaises en vue de leur reconnaissance automatique” and her thesis advisor was Jean-Sylvain Lienard.

She founded the Carnegie SpeechTM company in 2001 and is Chief Technical Officer and Vice President. Carnegie SpeechTM is a CMU spinoff. She is presently Principal Systems Scientist in the Language Technologies Institute of the School of Computer Science of Carnegie Mellon University. She also holds a tenured research position at LIMSI-CNRS in Orsay, France.

Alan W. Black

Prof. Alan W Black is a world leader in the area of speech synthesis. He is a principal author of the Festival Speech Synthesis System, a free software system which has been used by a large number of academic and industrial groups through out the world. He is also the author of the FestVox Voice Building tools which have been used to create speech synthesizers in over 40 different languages. He also wrote and distributes the small-footprint speech synthesizer Flite. With Prof. Tanja Scultz he has produced a web-based system for building recognizers and speech synthesizers in new languages.

With Dr. Maxine Eskenazi, he has developed real spoken dialog system platforms through the NSF funded Dialog Research Center (Dialrc) and he is the organizer for the Spoken Dialog Challenge 2010. In addition to speech synthesis he also carries out research in voice conversion and portable speech-to-speech translation systems. He was the pioneer if developing unit selection speech synthesis, where appropriate sub-word units are automatically selected from large databases of natural speech. This helped move the field of speech synthesis from a rule driven approach to a data driven approach.

Researchers

Kyusong Lee

Kyusong Lee is a postdoctoral associate at Language Technologies Institute (LTI), Carnegie Mellon University, advised by Maxine Eskenazi. He served for a year at Carnegie Mellon University as a research scholar. He earned a PhD from Pohang University of Science and Technology in South Korea. He has additionally served in research capacities for Microsoft Research Asia in Beijing and IBM Research in New York.

Yongjun He

Yongjun He received the B.S. degree in Computer Science and Technology from the Harbin University of Science and Technology, Harbin, China in 2003, the M.S. Ph.D. degrees in the School of Computer Science from the Harbin Institute of Technology, Harbin, China in 2006 and 2008, respectively. Currently, he is an associate professor in the school of Computer Science and Technology, Harbin University of Science and Technology. He is a visiting scholar in the CMU. His research interests include speech speaker recognition, speech recognition and machine learning.

Junki Ohmura

Junki Ohmura is a Sony’s AI researcher and now advised by Maxine Eskenazi as a visiting researcher at Language Technologies Institute (LTI), Carnegie Mellon University. He earned a Master degree from Waseda University in Japan. At Sony, he has been working as a human computer interaction researcher for developing consumer products such as PlayStation 4, smartphones and TV.

Graduate Students

Tiancheng (Tony) Zhao

Tiancheng Zhao is a PhD candidate at Language Technologies Institute (LTI) , Carnegie Mellon University, advised by Maxine Eskenazi and Alan W Black. His interest in general lies in spoken language processing and sequential decision-making for dialog systems. His current research focuses on developing deep-learning based end-to-end dialog systems that can carry out both task and chat-driven conversations in multiple real-world domains. Before becoming a PhD student at Carnegie Mellon University, he graduated from the Master of Language Technologies (MLT) program at LTI in 2016. Prior to that, Tiancheng obtained his bachelor degree in Electrical Engineering from University of California, Los Angeles and worked on speech signal processing, advised by Abeer Alwan.

Yulun Du

Yulun Du is a second-year graduate student of Language Technologies Institute in the School of Computer Science at Carnegie Mellon University. He is working under the supervisions of Dr. Maxine Eskenazi and Prof. Alan W. Black. He is broadly interested in research problems in intersection with Machine Learning and Natural Language Processing with a research goal to develop intelligent systems that can understand language and interact with human. Prior to coming to CMU, Yulun spent his undergraduate years at UIUC working with his esteemed professors Kevin C. Chang and Aditya Parameswaran.

Tzu Hsiang Lin

Tzu Hsiang is a first-year graduate student of Language Technologies Institute in the School of Computer Science at Carnegie Mellon University.
He is working under the supervision of Dr. Maxine Eskenazi. He is interested in Natural Language Processing and general Artificial Intelligence.
Prior coming to CMU, he received his bachelor’s degree in Electrical Engineering from National Taiwan University.

Alumni

Ting-yao Hu
Sungjin Lee