Gina-Anne Levow




Research Interests
Public Key

Gina-Anne Levow
Department of Linguistics
University of Washington
P.O. Box 352425
Guggenheim 418B
Seattle, WA 98195 USA

+1-206-616-5728 [Voice]
+1-206-685-7978 [Fax]
levow at uw dot edu
Formal Personal Statement

I'm an Associate Professor in the Linguistics Department at the University of Washington. My research concentrates on the use of intonation in spoken dialog, and my interests range over natural language processing, spoken language systems, and human-computer interfaces.

I am currently collaborating with Prof. Richard Wright and Prof. Mari Ostendorf on the NSF-funded ATAROS project to develop techniques to model and automatically recognize stance-taking in dyadic conversational speech. I am also working with Prof. Helen Meng and Prof. Patrick Wong of the Chinese University of Hong Kong on a project funded by the Hong Kong Research Grants Council to investigate the use of articulatory distinctive features in analysis and assessment of dysarthria, a neuro-physical speech disorder, in Cantonese. With Prof. Emily Bender, I am Principal Investigator of the NSF-funded EL-STEC project to develop shared tasks in speech and natural language processing that will facilitate research on and documentation of endangered languages. Many of my prior projects have aimed to interpret meaning transmitted through prosody. My NSF-funded project "Learning Tone" used a contextual model employing minimally supervised machine learning techniques to recognize lexical tones in Mandarin, Cantonese, isiZulu, and isiXhosa as well as prominence in English. Another NSF-funded project investigated automatic recognition of lexical and prosodic cues to conversational social dynamics, such as turn-taking and backchannels, across Arabic, English, and Spanish.

I also have long-standing interests in information retrieval in text and speech across a range of languages, in domains from news to medicine. I have particpated in projects and numerous shared tasks in cross-language and spoken document retrieval, focusing on general techniques for rapidly retargeting to other languages as well as specialized approaches for the Chinese-English language pair. I recently developed a system for the "Similar Segments in Social Speech" task at Mediaeval 2013, clustering related spans from informal video chat interactions.

I received my Ph.D. from the Massachusetts Institute of Technology in 1998. My doctoral thesis explored recognizing spoken corrections in human-computer dialogue, relying on acoustic-prosodic features. My Master's thesis examined discourse-neutral prosodic phrasing in Mandarin Chinese, analyzing the relationship between syntactic and prosodic structure. 

In addition to the research I have performed in a university setting, I have also participated in projects at a variety of governmental and corporate research laboratories. While at the Artificial Intelligence Laboratory of the U.S. Naval Research Laboratory, I designed and implemented an anaphora processing module which was subsequently incorporated into several of the laboratory's textual and spoken natural language systems, including a mobile robot. At Sun Microsystems Laboratories, I was a member of the team which developed SpeechActs, a proto-type speech-only spoken language interface to a collection of desktop applications and dynamic data feeds. I also participated in a government-funded (NIST) research effort at Kurweil Applied Intelligence, Inc. to design tools for expanding spoken natural language interfaces to a variety of applications, including that of a graphical design tool. 

When not hard at work recognizing tones or segmenting discourse, I enjoy gymnastics, T'ai Chi, and weight lifting. I was a member of a competitive USGF gymnastics team for eight years, and began studying T'ai Chi during my year as a Rotary Fellow in Taiwan. I am fluent in Mandarin Chinese and French. 

Here is the family photo, our transplanted British cats, and more great cats.

Last Updated: November 2014