ECE

SPEECH@SV

CMU

Principal Investigator

Ian Lane

Ian Lane
Ian Lane is an associate research professor at Carnegie Mellon University, Silicon Valley. His research interests include speech recognition, natural language processing, machine learning and applications of these technologies. He has published extensively in these fields, and received several patents and awards. He has been involved in the development of numerous speech translation systems, both research systems (GALE, TransTAC, TC-STAR, and IWSLT) and commercial products including Jibbigo. He has an affiliated appointment in LTI and a courtesy appointment in ECE. Before joining Carnegie Mellon University Ian was an intern researcher at ATR Spoken Language Communication Laboratories, Japan. He performed his postgraduate studies at Kyoto University culminating in a Ph.D. degree in 2006 and obtained his B.Tech. degree from Massey University, New Zealand in 2000.

PhD Students

Jungsuk Kim

Jungsuk Kim
Jungsuk Kim received the B.A. and M.S. in Electrical Engineering from the Seoul National University. He is currently PhD candidate at Carnegie Mellon University (Electrical and Computer Engineering). He have performed extensive work on parallel processing, including developing real-time Large Vocabulary Continuous Speech Recognition (LVCSR). Jungsuk Kim is the lead developer of the GPU/CPU hybrid LVCSR engine, HYDRA, at CMU.
www.akshayc.com

Akshay Chandrashekaran

Akshay Chandrashekaran
Akshay Chandrashekaran is currently a PhD student at Carnegie Mellon University in the Department of Electrical and Computer Engineering. Akshay graduated with an MS in Electrical and Computer Engineering from Carnegie Mellon University in 2011 and a B.E. in Electronics and Telecommunications in 2010 from the University of Pune, India. His past industry experiences includes internships at Lenovo Speech Labs and Baidu USA SVAIL. His current research is in the data driven optmization of acoustic model, feature and decoder hyper-parameters for speech recognition in low power systems.
bingliu.me

Bing Liu

Bing Liu
Bing Liu is a PhD student in the Department of Electrical and Computer Engineering at Carnegie Mellon University. His research interests include using machine learning for natural language processing, spoken language understanding, and spoken dialog systems. Bing graduated with a Bachelor degree in Electrical and Electronic Engineering from Nanyang Technological University (Singapore) in 2011. Before joining CMU in 2013, he was at Oracle building big data solutions on Hadoop.

Suyoun Kim

Suyoun Kim
Suyoun Kim is currently a PhD student at Carnegie Mellon University in the Department of Electrical and Computer Engineering. Suyoun graduated with a MS in Language Technologies Institute, School of Computer Science at Carnegie Mellon University in 2014. Her research interests includes speech recognition, deep learning, machine learning.

Guan-Lin Chao

Guan-Lin Chao
Guan-Lin Chao is currently a second-year PhD student in Electrical and Computer Engineering, Carnegie Mellon University under the supervision of Prof. Ian Lane. She received her bachelor's degree in Electrical Engineering from National Taiwan University in 2014. Her research interests are audiovisual speech recognition, machine learning and computer vision.

Benjamin Elizalde

Benjamin Elizalde
Benjamin Elizalde is currently a PhD student at Carnegie Mellon University under the supervision of Ian Lane and Bhiksha Raj. His research interests are machine hearing, audio signal processing, machine learning and multimedia. Benjamin worked as a Staff Researcher for three years at ICSI-UC Berkeley in the Audio & Multimedia lab. He graduated with an MSc in Information Technology and a BSc in ECE from ITESM. The list of his publications can be seen in Google Scholar.

Alumni

williamchan.ca

William Chan

William Chan
William Chan is now a Research Scientist at Google Brain Toronto. He completed his PhD at Carnegie Mellon University in the Department of Electrical and Computer Engineering in 2016. William completed his undergraduate studies with a BASc in Computer Engineering from the University of Waterloo in 2011. His past industry experiences include internships at Google, Amazon, Intel, NVIDIA, AMD and TD Securities. His current research crosses the fields of machine learning, deep learning and speech recognition.

Rahul Rajan

Rahul Rajan
Rahul Rajan is a 5th year ECE PhD candidate at CMU. His research interests lie at the intersection of Human-Computer Interaction and Machine Learning. His current focus is on building user interfaces that adapt in realtime to the cognitive load and stress being experienced by the user, using psycho-physiological measures. He has a BS and MS degree in ECE from Georgia Tech.

David Cohen

David Cohen
David got his BS in EE from UCLA in 2011 and is a 4th year PhD student at Carnegie Mellon. His research is in spoken dialog system architecture and his primary research interests are intelligent systems, particularly dialog systems. He is the creator of the open-source YODA spoken dialog system architecture, which allows rapid and inexpensive prototyping of spoken dialog systems.