(archive site)

Audio and Multimedia Researchers @ ICSI

Research Area Director:

Research Staff:

Graduate Student Researchers:

Visiting Researchers:

Researcher Biographies, Contact Info, and Publications


Gerald Friedland, Director of Audio & Multimedia Research

Gerald Friedland studied at Freie Universitaet in Berlin, receiving his master’s degree in 2002 and his doctorate summa cum laude in 2006. He moved to Berkeley for a postdoctoral fellowship at ICSI funded by the German Academic Exchange Service (DAAD), and in 2008, he accepted a position as a senior researcher. He has received the European Academic Software Award and the IEEE Computer Society Distinguished Service Award. In 2011, he was named associate editor of the year by ACM Transactions on Multimedia Computing, Communications, and Applications. He is a co-founder of the IEEE International Conference on Semantic Computing and the IEEE Summer School of Semantic Computing and was a program co-chair of the International Conference on Multimedia and Expo 2012. In 2009, he won the ACM Multimedia Grand Challenge, and in 2011, he served as its chair. He leads ICSI’s research efforts in multimedia understanding; his work focuses on audio techniques such as speaker diarization and acoustic event detection and their applications to multimedia content analysis.

Julia Bernd, Researcher

Julia Bernd received her MA in Linguistics from Stanford University in 2002, and has since then applied her academic training to practical causes by working on a wide variety of social-science and public-health research projects around the Bay Area. She currently works on the Teaching Privacy project at ICSI; she came to the institute to work on the research and evaluation team for the California Connects project. She is also an independent research consultant; a professional editor; and a member of the Board of Directors of Peninsula Peace and Justice Center in Palo Alto.

  • Email: jbernd@icsi.berkeley.edu
  • Phone: (510) 666-2883

Jaeyoung Choi, Researcher

Jaeyoung Choi’s research focuses on merging visual, acoustic, and natural language processing techniques for large-scale multimedia retrieval, and on the online privacy issues arising from these types of retrieval technologies. He is the lead software engineer for the Teaching Privacy project, which has gotten a lot of news media attention. He has also been taking the lead on the Multimodal Location Estimation project since he joined ICSI as a graduate student in 2010. He holds a BS in Computer Science from KAIST and an MS in Computer Science from the University of California–Berkeley.

Benjamín Elizalde, Affiliated Researcher

Benjamín Elizalde joined the AMM group in early 2012, to work on a project under IARPA’s ALADDIN program for video event detection on user generated content, and has recently also been collaborating on a Livermore Labs (LLNL) multimedia project. His research interests include video content analysis, focusing mostly on audio, and multimedia systems. He received his BS and MS from Tecnológico de Monterrey (ITESM) in Mexico. He is currently a PhD student at Carnegie Mellon University. He has also worked as an IT Consultant at WSS in Spain, on software projects for companies like Royal Bank Canada–Dexia and John Deere.

Adam Janin, Senior Researcher

Dr. Adam Janin has more than 16 years of experience in audio processing and speech recognition. He received a PhD in Computer Science from the University of California–Berkeley in 2004 and a BS in Physics from the California Institute of Technology in 1990. His work includes improving robustness to noise through novel neural network architectures, features, and feature combinations, and on exploiting parallel hardware to improve audio processing. Dr. Janin coordinated ICSI’s activities in AMI (a large collaborative project related to meeting analysis), led ICSI’s efforts in the NIST Rich Transcription evaluations in 2006 and 2007, and was heavily involved in developing the ICSI Meeting Corpus, one of the first open corpora of “natural” meetings. He works closely with multimedia and language researchers at ICSI, providing expertise in audio processing. Prior work includes pioneering research in Augmented Reality at Boeing.

  • Email: janin@icsi.berkeley.edu
  • Phone: (510) 666-2977

Liping Jing, Visiting Researcher

Liping Jing’s research focuses on machine learning and its application in multimedia data analysis, recommendation systems, traffic data analysis, etc. At ICSI, she is working on automatic analysis of videos to detect human-defined events. She is currently a Professor at the School of Computer and Information Technology, Beijing Jiaotong University, China. She received her PhD in applied mathematics from the University of Hong Kong in 2007. She then worked as a Research Associate with the Department of Mathematics, Hong Kong Baptist University, and a Research Fellow with the Department of Computer Science, University of Texas at Dallas (2007–2008).

TJ Tsai, Graduate Student Researcher

TJ Tsai completed his BS and MS in electrical engineering at Stanford University in 2006 and 2007. From 2008 to 2010, he worked at SoundHound, a startup that allows users to search for music by singing, humming, or playing a recorded track. He is currently a PhD student in the Electrical Engineering and Computer Science department at the University of California–Berkeley. He is currently working on multiple projects at ICSI involving audio signal processing.

  • Email: tjtsai@eecs.berkeley.edu

Student Research Interns

Jessica Larson

Regina Ongowarsito

Melody Valdez

AMM Research Alumni Contact Info and Publications

Howard Lei

  • Current Role: Assistant Professor of Engineering, California State University–East Bay
  • Role @ ICSI: Postdoctoral Researcher, 2006-2013; Affiliated Faculty, 2013-Present
  • Publications @ ICSI

Luke Gottlieb

  • Current Role: Build Engineer, Synopsis, Inc.
  • Role @ ICSI: Researcher, 2004-2015
  • Email: luke@icsi.berkeley.edu
  • Publications @ ICSI

Amanda Halperin

Miranda Braselton

  • Current Role: Adjunct Instructor, Chabot College
  • Role @ ICSI: Visiting Researcher, 2015
  • Email: mbraselton@chabotcollege.edu

Martha Larson

Xiaoyong Wei

Sree Hari Krishnan Parthasarathi

Damian Borth

Daniel Göhring

Robert Mertens

Nils Peters

Bryan Morgan

  • Current Role: Associate Product Manager Intern, Workday
  • Role @ ICSI: Graduate Student Researcher, 2013-2015
  • Email: brynamo@icsi.berkeley.edu
  • Publications @ ICSI

EunKwang Joo

  • Current Role: Hustler/Coder, Team POPONG
  • Role @ ICSI: Graduate Student Researcher, 2013

Chan Kim

  • Current Role: User Experience Designer, Oracle
  • Role @ ICSI: Graduate Student Researcher, 2013-2014
  • Web: http://96chany.com

Oriol Vinyals

  • Current Role: Research Scientist, Google
  • Role @ ICSI: Graduate Student Researcher, 2007-2013
  • Publications @ ICSI

Former Student Interns and Volunteers

Megan Carey
Alexis Conway
Isha Doshi
Karina Goot
Melia Henderson
Fatima Ibrahim-Biangoro
Jeffrey Jacinto
Justin Kim
Florin Langer
Itzel Martinez
Marissa Pitta
Micky Prochaska-Saglio
Arany Uthayakumar