Julia B. Hirschberg

Computer Science

Julia B. Hirschberg studies the prosody—intonation and melody—of speech, with the goal of teaching computers to understand subtle variations and reproduce them in natural-sounding speech. This involves understanding how prosody changes under different circumstances. Hirschberg established Columbia’s Spoken Language Processing Group.

Hirschberg has analyzed the prosody of charismatic and deceptive speech and developed a computer system that is more successful than humans at detecting lies. She studies entrainment— the tendency of people to mirror back the spoken mannerisms of those who are speaking to them—in voice-response systems. Hirschberg also does research on emotional speech, code-switching, and text-to-speech synthesis.

  • AT&T Labs, Technology Leader, Human-Computer Interface Research Department, 2000-2003
  • AT&T Labs, Division Manager, Human-Computer Interface Research Department, 1996–2000
  • AT&T Bell Laboratories, Division Manager, Human-Computer Interface Research Department, 1994–1996
  • AT&T Bell Laboratories, Member of Technical Staff, Linguistics Research Department, 1985–1994
  • Percy K. and Vida L. W. Hudson Professor of Computer Science, Columbia University, 2013–
  • Chair of Computer Ccience, Columbia University, 2012–
  • Professor of Computer Science, Columbia University, 2002–
  • Smith College, Assistant Professor of History, 177-82.
  • Smith College, Instructor in History, 1974-77.
  • Founding fellow, Association for Computational Linguistics
  • Fellow, American Association for Artificial Intelligence, 1994
  • Fellow, International Speech Communication Association, 2008
  • Fellow, Association for Computing Machinery, 2016
  • Fellow, Institute of Electrical and Electronics Engineers, 2017
  • Member, National Academy of Engineering, 2017
  • Elected to American Philosophical Society, 2014
  • James L. Flanagan Speech and Audio Processing Award, IEEE, 2011
  • ISCA Medal for Scientific Achievement, 2011
  • Columbia Engineering School Alumni Association Distinguished Faculty Teaching Award, 2009
  • Honorary doctorate, Royal Institute of Technology, Stockholm, Sweden, 2007
  • “Data Selection and Adaptation for Naturalness in HMM-based Speech Synthesis”
    Erica Cooper, Alison Chang, Yocheved Levitan and Julia Hirschberg. Interspeech 2016, September. San Francisco, CA.
  • “Babler - Data Collection from the Web to Support Speech Recognition and Keyword Search”
    Gideon Mendels, Erica Cooper and Julia Hirschberg. ACL WAC-X 2016, August. Berlin, Germany.
  • “Combining Acoustic-Prosodic, Lexical, and Phonotactic Features for Automatic Deception Detection,” Sarah Ita Levitan, Guozhen An, Min Ma, Rivka Levitan, Andrew Rosenberg and Julia Hirschberg. Interspeech 2016, September. San Francisco, CA.
  • 2015. J. Hirschberg and C. D. Manning, Advances in natural language processing, Science Magazine, 349(6):261-266.
  • “Acoustic-Prosodic Entrainment in Slovak, Spanish, English and Chinese: A Cross-Linguistic Comparison,” Rivka Levitan, Stefan Benus, Agustin Gravano and Julia Hirschberg. SIGDIAL 2015, September. Prague, Czech Republic.
  • 2011. Agustın Gravano and Julia Hirschberg, “Turn-taking cues in task-oriented dialogue,”
    Computer Speech and Language, 25(3):601-634