Experiences

Academic

09/2001~03/2008, Graduate Research Assistant, CSLU , OGI at OHSU , Portland, OR, USA.
  • "Make dysarthric speech intelligible" project.
  • "Predict and synthesize spectral balance" project.
  • Implementation of the sum-of-product duration model in Festival.
7/1998~09/1995, Research Assistant, National Laboratory of Pattern Recognition , Institute of Automation, CAS, China.
  • Project of Speaker Independent, Large Vocabulary, Continuous Chinese Dictation System.
  • Project of Robustness in Speech Recognition. 

Industrial

06/2009~present, Research Engineer / Sr. Software Engineer, TeleNav, Inc., Sunnyvale, CA, USA.
  • Building ASR and TTS platforms in "cloud" for mobile devices.
03/2008~06/2009, Software Engineer (II), Become, Inc., Mountain View, CA, USA.
  • Applying Machine Learning and NLP techniques to help people searching products on the Internet.
06/2007~09/2007, Software Engineer (Internship), Google, Inc., New York City, NY, USA.
  • Working on Language Identification project for audio indexing of multimedia data on the Internet.
07/2004~10/2004, Text-to-Speech Consultant (Internship), Sensory, Inc., Portland, CA, USA.
  • Implementing and evaluating speech synthesis algorithms for low resource American English TTS systems.
09/1998~08/2001, Staff Research Member, IBM China Research Laboratory , Beijing, China.
  • Cantonese Speech Synthesis System Project, first HMM based Cantonese synthesis prototype system in IBM.
  • Mandarin Speech Synthesis System Project, first HMM based Mandarin synthesis prototype system in IBM.
  • Acoustic Model for Mandarin ViaVoice Telephony Engine.
  • Acoustic Model for ViaVoice'99 Mandarin Version.

CSLU | OGI
Page modified May 3, 2011