The group focuses on issues related to Vietnamese language processing, such as sound and language modeling, building audio and text data warehouses, audio and music querying, speaker verification and recognition, and voice translation. Some results such as the system to automatically generate subtitles for Vietnamese news bulletins on Youtube channel and the system to support the automatic generation of meeting minutes from voice.


Research topics revolve around issues related to speech processing for Vietnamese, including:

  • Acoustic Modeling, Language Modeling for LVCSR
  • Corpus Developments (audio & text)
  • Audio, Music Retrieval
  • Unit Selection Synthesis, HMM Synthesis
  • Speaker Verification/Speaker Recognition
  • Speech Translation


  • Assoc.Prof. Dr. Vu Hai Quan (team leader)
  • Dr. Nguyen Duc Hoang Ha
  • Dr. Chau Thanh Duc
  • Dr. Dau Ngoc Ha Duong
  • Dr. Ngo Minh Nhut
  • MCs. Cao Xuan Nam
  • MCs. Pham Minh Nhut


  • Speech Translation for Vietnamese(2011-2012,National Key Project)
  • Acoustic Modelling of Under-Resourced Languages Exploiting Feature Space Constraints: Vietnamese Case Study (2011-2012, VNU-HCM National Key Project)
  • Voice Server and its applications (2010-2011, DOST-Ho Chi Minh city)
  • Video Retrieval Based on Semantic Concepts: Vietnamese Case Study (2009 – 2010, National Key Project)
  • Bioinformatics and its Applications for Repairing Vaccine (2008 – 2010, National key project)
  • Video Based Audio Search (2007 – 2008, Ministry of Science & Technology)
  • Vietnamese Unit Selection Synthesis (2008 – 2009, VNU-HCM National Key Project)

Possible collaborative activities

  • Microphone Array
  • VNCare
  • Vietcap
  • Smart Globe
  • Drip Monitoring Device
  • Sigma (Supreme Initiative Global Model for Alternated education)

Links of demo, website, video