I was born in Pittsburgh, PA, grew up in Raleigh, NC,
and then returned to Pittsburgh to obtain a BS in Electrical & Computer
Engineering from Carnegie Mellon University.
While at CMU, I did my senior research work with Professor
Richard Stern, working to develop alternative methods of front end feature
extraction for speech recognition.
Continuing work in speech and language processing,
I acquired my M.S.E. in Electrical and Computer Engineering from Johns Hopkins in 2004.
In January 2009 I defended in my Ph.D. thesis Reconstructing Spontaneous Speech
[dissertation in pdf; slides in
in electrical and computer engineering
Center for Language and Speech Processing working with
Professor Frederick Jelinek.
My research focuses on the automatic reconstruction of disfluent and
ungrammatical spontaneous speech output via syntactic analysis and linguistic
formalisms for meaning extraction.
about our work with meaning representations in language understanding for
SMT and speech reconstruction.)
I currently serve as a Christine Mirzayan Science and Technology Policy Graduate Fellow
at the National Academies (see below for additional information).
Research Interests and Learning Tools:
| speech reconstruction, meaning representations, language modeling,
formal languages, computational linguistics
Using Neural Network Language Models
for LVCSR: Presentation given to JHU ECE Reading Group (based on Schwenk & Gauvain 2002)
Introduction to Lexical-Function Grammars:
Presentation given to JHU NLP Reading Group (based on Kaplan & Brenan 1982)
More in-depth descriptions of my recent endeavors to date to come.
As an undergraduate I had the opportunity to spend my summers interning with
Intel's Speech Applications Group (2000) and Microsoft's dotNet Speech product group
In the summer of 2003, I participated in the
JHU Summer Workshop, working with
George Foster, Simona Gandrabur, and others to research applications and
confidence estimation for natural language applications
such as machine translation.
Our team's final report and other resources are available
A reduced version of the paper was presented at COLING 2004 - view here.
In the summer of 2004, I took an internship at
BBN Technologies with the Speech Recognition
group under John Makhoul. I worked with Owen Kimball and Richard Schwartz on
the EARS Rich Transcription for Conversational Telephone
Speech task, using topic-specific information to dynamically alter
language models in an effort to improve ASR performance.
Since defending my thesis, I have served as a
Christine Mirzayan Science & Technology Policy Graduate Fellow at
The National Academies.
I work with the
Standing Committee for Technology Insight-Gauge, Evaluate & Review (TIGER) committee
(affiliated with the Air Force Studies Board) of the
Division on Engineering and Physical Sciences.
- E. Fitzgerald, R. Frank, and F. Jelinek. "What lies beneath: Semantic and syntactic analysis
of manually reconstructed spontaneous speech".
To appear in the Proceedings of the Association for Computational Linguistics (ACL), 2009.
- E. Fitzgerald, F. Jelinek, and K. Hall.
"Integrating sentence- and word-level error identification for disfluency correction".
To appear in the Proceedings of the Conference on
Empirical Methods on Natural Language Processing (EMNLP) Linguistics, 2009.
- E. Fitzgerald, K. Hall, and F. Jelinek. "Reconstructing false start errors in spontaneous speech text".
In the Proceedings of the European Association for Computational Linguistics (EACL), Athens, Greece. 2009.
- E. Fitzgerald and F. Jelinek. "Linguistic Resources for Reconstructing Spontaneous Speech Text".
In Proceedings of the Linguistic Resources and Evaluation Conference (LREC),
Marrakech, Morocco. 2008.
- E. Fitzgerald. "Speech Reconstruction Annotation Guide for Conversational Telephone Speech Conversations", version 5.2. October 2007. [doc]
- Y. Zhang, V. Kordoni, and E. Fitzgerald. "Partial Parse Selection for Robust Deep Processing".
In Proceedings of ACL Workshop on Deep Linguistic Processing, pg. 128-135. Prague, Czech Republic. 2007.
- J. Blatz, E. Fitzgerald, G. Foster, S. Gandrabur, C. Goutte, A. Kulesza,
A. Sanchis, and N. Ueffing. "Confidence Estimation for Machine Translation".
In COLING-2004, Geneva, Switzerland. 2004.
- Erin Fitzgerald. Reconstructing Spontaneous Speech. Ph.D. thesis, The Johns Hopkins University. 2009.
Awards and Honors: ||
- The National Academies Christine Mirzayan Science & Technology Policy Graduate Fellow (Winter 2009)
- Diversity Recognition Award, Johns Hopkins Institutions (2007)
- Wolman University Fellow (2002-2003)
- Rhodes Scholarship Semifinalist (2002)
- Carnegie Mellon University Student Body President (2000-2001)
- Intel Women in Science and Engineering (WiSE) Scholar (2000-2002)
In the summer of 2005, I started a group for the women graduate
students in the Johns Hopkins Whiting School of Engineering called
Women of Whiting (WoW).
We now have a mailing list of over 250 students and hold many
successful and well-attended social and professional events each semester.
I've given up my involvement (graduating does that), but encourage everyone
at Hopkins, men and women alike, to support them and attend what WoW events you can!
I love traveling. From January to May 2006, I lived and worked in Prague, continuing
my research alongside the UFAL
group at Charles University.
Follow my personal blog for
details of that and other international trips! (Paris, Dubai, Morocco, and more)
I also recently helped to plan the
Enloe High School class of 1998 10-year reunion.