You are here

2016 SJTU Speech and Language Processing Workshop

Date: 2016.3.18-19

Place: 3-410

 

Topic 1: Welcome and introduction of research at SJTU SpeechLab

Time: 9:30 - 11:30 3.18

Speaker: Kai Yu (SJTU)

 

Topic 2: Towards self-learning adaptable open domain vocal interfaces, ongoing work at LIA, Avignon

Time: 12:40 - 13:40 3.18

Speaker: Fabrice Lefèvre (Univ. of Avignon)

Bio: Fabrice Lefèvre received a degree in electrical engineering from ENSEA-Cergy and the Ph.D. degree in computer science from the University Paris VI, Paris, France, in 2000. He was appointed an Assistant Professor position at the University of Orsay, Paris XI, in 2001 where he worked in the Spoken Language Processing Group at LIMSI-CNRS. He joined the University of Avignon in 2005, and he is now Professor and head of the Vocal Interactions Group at LIA since 2010. He was an academic visitor in the Engineering Department of Cambridge University in 2009. His primary research activities include automatic speech recognition, speech understanding, stochastic machine translation and spoken dialog systems. He is the author/co-author of over 100 peer-reviewed papers for journals and conferences. He was involved in several European and US projects (CORETEX, AMITIES, EARS, LUNA and Classic). He participated in several international (NIST) and French (AUPELF, Technolangue) spoken language recognition and understanding system evaluation campaigns. F. Lefevre is member of the International Speech Communication Association, member of IEEE, served on the IEEE signal processing society, speech and language processing technical committee (SLTC) as an elected member (2012-14) and was cofounder of the French Spoken Communication Association (AFCP).

 

Visiting Laboratory

Time: 14:00-16:00 3.19

Place: 3-502, 3-520, 3-225

 

Topic 3: Speech, Language, and Related Technologies at Apple

Time: 9:30-11:30 3.19

Speaker: Jerome Bellegarda (Apple)

Bio: Dr. Jerome R. Bellegarda is Apple Distinguished Scientist in Human Language Technologies at Apple Inc., Cupertino, California, which he joined in 1994. Prior to that, he was a Research Staff Member at the IBM T.J. Watson Center, Yorktown Heights, New York. Among his diverse contributions to speech and language advances over the years, he pioneered the use of tied mixtures in acoustic modeling and latent semantics in language modeling. In addition, he was instrumental to the due diligence process leading to Apple's acquisition of Siri personal assistant technology and its integration into iOS. His general interests span statistical modeling algorithms, voice-driven man-machine communications, multiple input/output modalities, and multimedia knowledge management. In these areas he has written close to 200 publications, and holds approximately 100 U.S. and foreign patents. He has served on many international scientific committees, review panels, and advisory boards. In particular, he has worked as Expert Advisor on speech and language technologies for both the U.S. National Science Foundation and the European Commission, was Associate Editor for the IEEE Transactions on Audio, Speech and Language Processing, and is currently an Editorial Board member for Speech Communication. He is also serving on the IEEE Signal Processing Society Speech Technical Committee, and is a member of the International Advisory Committee of ISCA (International Speech Communication Association). He is a Fellow of both IEEE and ISCA.

 

Topic 4: Overview of NTT research activities for distant speech recognition

Time: 12:30-14:30 3.19

Speaker: Marc Delcroix (NTT)

Bio: Marc Delcroix is a senior research scientist at the media information laboratory, NTT Communication Science Laboratories, Kyoto, Japan. He received the M.Eng. degree from the Free University of Brussels, Belgium, and the Ecole Centrale Paris, France, in 2003 and the Ph.D. degree from the Graduate School of Information Science and Technology, Hokkaido University, Japan, in 2007. His main research interest is robust speech recognition, including speech  enhancement, dereverberation, acoustic modeling and adaptation.  Takuya Yoshioka is a research scientist at the media information laboratory, NTT Communication Science Laboratories, Kyoto, Japan. He received the Ph.D. degree in informatics from Kyoto University, Japan, in 2010. Since joining NTT in 2006, he has been working on the development of algorithms for far-field speech recognition and  microphone array signal processing.

 

Topic 5: Denoising/dereverberation with DNN for SRE

Time: 15:00-17:00 3.19

Speaker: Karafiat Martin, Lukas Burget, Oldrich Plchot, Karel Vesely (BUT)