Keynote Speakers

 

  • Dilek Hakkani-Tür (Amazon), Neural Response Generators for Social Conversations
  • John H.L. Hansen (University of Texas, Dallas), Challenges and Advancements in Speaker Diarization & Recognition for Naturalistic Data Streams
  • Mark A. Hasegawa-Johnson (University of Illinois, Urbana-Champaign), Automatic Discovery of Phoneme Inventories for Speech Technology in Under-resourced Languages