Prof Julia Hirschberg from Columbia University shares her work on investigating two types of speaker state: charisma and deception. She discusses the acoustic, prosodic, and lexical characteristics of charismatic speech and deceptive speech, and proposes algorithms for identifying these automatically.
Free and open to the public. Seating is on a first-come first-served basis.
In recent years speech researchers have expanded their studies of how to recognize emotional states using acoustic, prosodic and lexical information to include other types of speaker states such as medical conditions, suicidal tendencies, likeability, degree of interest, and personality. In this talk the speaker will discuss work at the Columbia Speech Lab on two other types of speaker state: charisma and deception. In ongoing work, the speaker and her research group have examined the acoustic, prosodic, and lexical characteristics of charismatic speech and deceptive speech, to propose algorithms for identifying these automatically. They have particularly examined cross-cultural differences and similarities of speech perceived to be charismatic and are currently studying cross-cultural differences and similarities in production and perception of deceptive speech.
About the speaker
Prof Julia Hirschberg received her PhD in Computer and Information Science from the University of Pennsylvania in 1985, after previously doing a PhD in sixteenth-century Mexican social history at the University of Michigan in 1976 and teaching history at Smith College. She was a Member of Technical Staff, Department Head, and Technology Leader at Bell Laboratories and AT&T Laboratories, creating the Human-Computer Interface Research Department at Bell Labs. She joined Columbia University in 2002 and is currently Professor and Chair of Computer Science.
Prof Hirschberg’s research interests focus on computational linguistics/natural-language processing, including empirical and corpus-based studies of intonation and discourse, emotion in speech, spoken dialogue systems, audio browsing and retrieval, speech understanding, text-to-speech systems, labeling standards for speech corpora and human-computer Interaction. She served as editor-in-chief of Computational Linguistics and of Speech Communication and is now on the Editorial Board. She was on the Executive Board of the Association for Computational Linguistics (ACL) from 1993-2003, has been on the Permanent Council of International Conference on Spoken Language Processing since 1996, and served on the board of the International Speech Communication Association (ISCA) from 1999-2007 (as President 2005-2007). She is on the board of the Computer Research Association's Committee on the Status of Women in Computing Research and has been active in working for diversity at AT&T and at Columbia.
Prof Hirschberg has been a Fellow of the American Association for Artificial Intelligence since 1994, an ISCA Fellow since 2008, and is a founding Fellow of the ACL since 2011. She received numerous awards including the James L. Flanagan Speech and Audio Processing Award from Institute of Electrical and Electronics Engineers in 2011, the ISCA Medal for Scientific Achievement and the IBM Faculty Awards, etc. She has also received funding from the National Science Foundation, the Department of Homeland Security, Defense Advanced Research Projects Agency, Knowledge Discovery and Data Mining, Lockheed Martin, and the Simons Foundation. She holds 5 patents for text-to-speech synthesis and audio browsing/retrieval.
Free and open to the public. Seating is on a first-come first-served basis.
