Abe Kazemzadeh's Homepage

About

Unless you're here by mistake, you probably want to know something about Ebrahim "Abe" Kazemzadeh, a professor at the University of St. Thomas in the Graduate Programs in Software (GPS) department. Thank you for visiting this page and be sure to listen to the following options as the menu has changed...

Click on one of the links to the right to browse. Fellow researchers will be most interested in the projects, publications, and resources links. My resume is provided for interested parties. My availability for consulting is dependent on my teaching load. The interests link is general purpose, both for my academic/professional interests and my personal interests. Friends may be interested in the projects and news links to see what I'm working on.

Also anyone can feel free to leave me a note using the text input or email me at a b e "dot" k a z e m z a d e h "AT" g m a i l "dot" c o m (without spaces). I'd especially like to hear from old friends, people who are interested in my research, or anyone who has a comment about the site. Please obfuscate your email as the postings are public.

News

  • The news at the moment is that my wife and I are making a big life transition by moving from sunny L.A., where we've lived for 20+ years, to somewhat less sunny but still very beautiful Minneapolis. It's going to be a big move. We'll be looking for places to live in Minneapolis, perhaps selling or perhaps shipping a 25 ft sailboat, and perhaps buying a new boat.

Publications

Below are papers that I've written or co-authored. The Google Scholar page may be more up-to-date

  • Natural Language Description of Emotion (Dissertation)
    Abe Kazemzadeh
    Defended Feb. 28, 2013, published Aug., 2013.
  • Fuzzy Logic Models for the Meaning of Emotion Words
    Abe Kazemzadeh, Sungbok Lee, and Shrikanth Narayanan
    IEEE Computational Intelligence Magazine, volume 8, issue 2, pages 34-49
  • A Sequential Bayesian Dialog Agent for Computational Ethnography
    Abe Kazemzadeh, James "Jimmy" Gibson, Juanchen Li, Sungbok Lee, Panayiotis Georgiou, and Shrikanth Narayanan.
    In Proceedings of Interspeech, Portland, OR, Sept. 2012
  • A System for Real-Time Twitter Sentiment Analysis of 2012 U.S. Presidential Election Cycle
    Hao Wang, Dogan Can, Abe Kazemzadeh, François Bar, and Shrikanth Narayanan
    In Proceedings of ACL, Jeju Island Korea, 2012
  • Emotion Twenty Questions (EMO20Q): Toward a Crowd-sourced Theory of Emotions
    Abe Kazemzadeh, Sungbok Lee, Panayiotis Georgiou, and Shrikanth Narayanan.
    In Proceedings of Affective Computing and Intelligent Interaction (ACII2011),Memphis, TN, Oct. 2011
  • Toward a Computational Approach for Natural Language Description of Emotions.
    Abe Kazemzadeh
    In Proceedings of Affective Computing and Intelligent Interaction (ACII2011),Memphis, TN, Oct. 2011
    URL (Note: this is a precis of my dissertation proposal. It won the Fiorella De Rosis best doctoral consortium paper award at ACII 2011.) .
  • EMO20Q Questioner Agent
    Abe Kazemzadeh, James Gibson, Panayiotis Georgiou, Sungbok Lee, and Shrikanth Narayanan.
    In Proceedings of Affective Computing and Intelligent Interaction (ACII2011),Memphis, TN, Oct. 2011
  • Determining Which Question To Ask, with the Help of Spectral Graph Theory
    Abe Kazemzadeh, Sungbok Lee, Panayiotis Georgiou, and Shrikanth Narayanan.
    In Proceedings of Interspeech, Florence, Italy. August, 2011.
  • An Interval Type-2 Fuzzy Logic System to Translate Emotion Words from Spanish to English
    Abe Kazemzadeh
    In Proceedings of FUZZ-IEEE at The World Conference on Computational Intelligence (WCCI), Barcelona, Jul. 2010.
  • An Interval Type-2 Fuzzy Logic System to Translate between emotion-related vocabularies
    Abe Kazemzadeh, Sungbok Lee, and Shrikanth Narayanan.
    In Proceedings of First Interspeech, Brisbane, Australia, Sept. 2008.
  • Using model trees for evaluating dialog error conditions based on acoustic speech information.
    Abe Kazemzadeh, Sungbok Lee, and Shrikanth Narayanan.
    In Proceedings of First International Workshop on Human-Centered Multimedia (ACM Multimedia), Santa Barbara, CA, October 2006.
  • Automatic detection of voice onset time contrasts for use in pronunciation assessment.
    Abe Kazemzadeh, Joseph Tepperman, Jorge Silva, Hong You, Sungbok Lee, Abeer Alwan, and Shrikanth Narayanan.
    In Proceedings of InterSpeech ICSLP, Pittsburgh, PA, September 2006.
  • Tball data collection: the making of a young children's speech corpus.
    Abe Kazemzadeh, Hong You, Markus Iseli, Barbara Jones, Xiaodong Cui, Margaret Heritage, Patti Price, Elaine Andersen, Shrikanth Narayanan, and Abeer Alwan.
    In Proceedings of Eurospeech, Lisbon, Portugal, October 2005.
  • Acoustic correlates of user response to errors in human-computer dialogues.
    Abe Kazemzadeh, Sungbok Lee, and Shrikanth Narayanan.
    In Proceedings of IEEE ASRU, St. Thomas, U.S. Virgin Islands, December 2003.
  • Automatic pronunciation verification of english letter-names for early literacy assessment of preliterate children.
    Matthew Black, Joseph Tepperman, Abe Kazemzadeh, Sungbok Lee, and Shrikanth Narayanan.
    In Proceedings of ICASSP, Taipei, Taiwan, Apr 2009.
  • IEMOCAP: Interactive emotional dyadic motion capture database
    Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Abe Kazemzadeh, Emily Mower, Samuel Kim, Jeannette Chang, Sungbok Lee, and Shrikanth Narayanan.
    Journal of Language Resources and Evaluation, In press, 2008.
    URL: coming soon... .
  • Pronunciation verification of english letter-sounds in preliterate children.
    Matthew Black, Joe Tepperman, Abe Kazemzadeh, Sungbok Lee, and Shrikanth Narayanan.
    In Proceedings of Interspeech, Brisbane, Australia, Sep 2008.
  • A text-free approach to assessing nonnative intonation.
    Joseph Tepperman, Abe Kazemzadeh, and Shrikanth Narayanan.
    In Proceedings of InterSpeech ICSLP, Antwerp, Belgium, August 2007.
  • A bayesian network classifier for word-level reading assessment
    Joseph Tepperman, Matthew Black, Sungbok Lee, Abe Kazemzadeh, Matteo Gerosa, Margaret Heritage, Abeer Alwan, and Shrikanth Narayanan.
    In Proceedings of InterSpeech ICSLP, Antwerp, Belgium, August 2007.
  • A system for technology based assessment of language and literacy in young children: the role of multiple information sources.
    Abeer Alwan, Yijian Bai, Matt Black, Larry Casey, Matteo Gerosa, Margaret Heritage, Markus Iseli, Barbara Jones, Abe Kazemzadeh, Sungbok Lee, Shrikanth Narayanan, Patti Price, Joseph Tepperman, and Shizhen Wang.
    In Proceedings of IEEE International Workshop on Multimedia Signal Processing, Chania, Greece, October 2007.
  • A study of emotional speech articulation using a fast magnetic resonance imaging technique.
    Sungbok Lee, Erik Bresch, Jason Adams, Abe Kazemzadeh, and Shrikanth Narayanan.
    In Proceedings of InterSpeech ICSLP, Pittsburgh, PA, September 2006.
  • Pronunciation verification of children?s speech for automatic literacy assessment.
    Joseph Tepperman, Jorge Silva, Abe Kazemzadeh, Hong You, Sungbok Lee, Abeer Alwan, and Shrikanth Narayanan.
    In Proceedings of InterSpeech ICSLP, Pittsburgh, PA, September 2006.
  • An articulatory study of emotional speech production.
    Sungbok Lee, Serdar Yildirim, Abe Kazemzadeh, and Shrikanth Narayanan.
    In Proceedings of Eurospeech, Lisbon, Portugal, October 2005.
  • Investigating the role of phoneme-level modifications in emotional speech resynthesis.
    Murtaza Bulut, Carlos Busso, Serdar Yildirim, Abe Kazemzadeh, Chul Min Lee, Sungbok Lee, and Shrikanth Narayanan.
    In Proceedings of Eurospeech, Lisbon, Portugal, October 2005.
  • An articulatory study of emotional speech production.
    Sungbok Lee, Serdar Yildirim, Abe Kazemzadeh, and Shrikanth Narayanan.
    In Proceedings of Eurospeech, Lisbon, Portugal, October 2005.
  • Pronunciation variations of spanish-accented english spoken by young children.
    Hong You, Abeer Alwan, Abe Kazemzadeh, and Shrikanth Narayanan.
    In Proceedings of Eurospeech, Lisbon, Portugal, October 2005.
  • Emotion recognition based on phoneme classes.
    C. M. Lee, S. Yildirim, M. Bulut, A. Kazemzadeh, C. Busso, Z. Deng, S. Lee, and S. Narayanan.
    In Proceedings of ICSLP, Jeju, Korea, October 2004.
  • An acoustic study of emotions expressed in speech.
    S. Yildirim, M. Bulut, C. M. Lee, A. Kazemzadeh, C. Busso, Z. Deng, S. Lee, and S. Narayanan.
    In Proceedings of ICSLP, Jeju, Korea, October 2004.
  • Recognizing expressions of commonsense psychology in English Text
    Andrew Gordon, Abe Kazemzadeh, Anish Nair, and Milena Petrova
    Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (ACL-2003) Sapporo, Japan, July 7-12, 2003.
  • Analysis of user behavior under error conditions in spoken dialogs.
    Jongho Shin, Shrikanth Narayanan, Laurie Gerber, Abe Kazemzadeh, and Dani Byrd.
    In Proceedings of ICSLP, Denver, CO, 2002.

Below are abstracts that I've written or co-authored:

  • Recognition of voice onset time for use in pronunciation modeling.
    Abe Kazemzadeh, Sungbok Lee, and Shrikanth Narayanan.
    J. Acoust. Soc. Am., 2005.
  • Some articulatory details of emotional speech.
    Sungbok Lee, Serdar Yildirim, Murtaza Bulut, Abe Kazemzadeh, and Shrikanth Narayanan.
    J. Acoust. Soc. Am., 2005.

Below are some class projects and work in progress

  • A Fuzzy Logic System to Encode Emotion-Related Words and Phrases
    Abe Kazemzadeh
    Final Project for Prof. Mendel's fuzzy logic class (2008)
  • The Emotion Mirror: Recognizing Emotion In Speech and Displaying The Emotion in an Avatar
    Abe Kazemzadeh, Samuel Kim, and Yoonji Kim
    Prof. Gratch and Marsella's Affective Computing Class (spring 2007)
  • An Interval Type-2 Fuzzy Logic System to Translate Between Emotion-Related Vocabularies
    Abe Kazemzadeh, Sungbok Lee, and Shrikanth Narayanan
    Submitted to interspeech 2008

A patent we applied for when I did an internship at ATT with Michael Johnston

  • System and Method for Speech-Enabled Access to Media Content
    Michael Johnston and Abe Kazemzadeh
    Application number: 12/573,448, Publication number: US 2011/0082696 A1, Filing date: Oct 5, 2009

Teaching

My first semester at UST, I'll be teaching Data Analysis and Visualization. I also have experience tutoring and volunteering in after-school programs.

Biography

Actually, this is technically an autobiography...

Geographical Stats

I grew up in Eau Claire and Altoona Wisconsin , and partly Minneapolis Minnesota. I moved to Los Angeles for college and ended up staying for grad school and work. I've lived in various places around town including near USC campus, Hollywood, Santa Monica, Culver City, and West Covina and my wife and I have a small sailboat in Marina del Rey.

As of August '18, I will have moved back to the Twin Cities area to teach at University of St. Thomas.

Family

I have a big family: 4 brothers (5 including myself), and 3 sisters. I'm the oldest, then (in order of age) Yuey (Yusef), Vince (Vincent), Christina, Mark, Erika, Kurt, and Clare. One unusual characteristic is that among us brothers, the height is inversely proportional to age/order, so the younger brothers are taller than the older ones. Most of my immediate family lives in either Wisconsin or Minnesota, but I have extended family here in the "Southland" (i.e., Southern California), Portland, NYC, North Dakota, England, Sweden, Germany, and Iran.

When I got married to my wife Elly, I inherited another branch to my family, the Setiadi/Lie family, that lives in LA and Indonesia.

Also when I was a single student in LA I was adopted by a Mexican family, la familia Martinez, who gave me room, board, and a warm family environment for a very reasonable rent.

Education

In education, I have tried to advance both my personal interests and skills that will make me a productive member of society: theory and practice, if you will. As my studies have progressed, these two branches have grown closer together, which I interpret as moving in the right direction.

In high school, my favorite subjects were math and English, so I decided to major in linguistics when I started college at USC . Linguistics at an undergraduate level is a great way to explore human being's incredible language capacity, but it's not too practical -- or so I thought at the time -- so I also did pre-med course work, which I applied toward my minor in natural sciences. Towards the end of my undergrad experience, Prof. Jean-Roget Vergnaud introduced me to Prof. Shri Narayanan and I started doing work on human-computer dialog analysis with Shri, Prof. Dani Byrd , Lauri Gerber, and Jongho Shin.

Working with Shri at the SAIL lab really opened my eyes to the practical applications of linguistics and opened many opportunities for me as well. Seeing in computers the practical side of linguistics, and having some traumatic experiences volunteering at LA County hospital, made me decide to do my masters in computational linguistics (CL) rather than going to med school.

Combining theoretical interests in linguistics with practical applications using computers was not easy. The clash between the theoretical concerns of linguistics and the engineering concerns of computer science was difficult to overcome with the CL masters program suspended precariously between the lingustics and computer science (CS) departments. Two things helped me very much in this regard. First, working at the institute for creative technology (ICT) with Dr. Andrew Gordon , Milena Petrova, Anish Nair, and Reid Swanson gave me a good experience working with ontologically driven text processing. Second, the SAIL lab is a sturdy bridge between the CS and linguistics departments based on speech science foundations of speech processing and phonetics. Under Dr. Sungbok Lee's patient mentoring I studied speech processing and participated in the emotion and pronunciation (TBALL) subgroups of the SAIL lab (the TBALL project is joint between USC, UCLA, and Berkeley). Furthermore, at the SAIL lab I worked on developing my programming skills, which helped me successfully apply to the PhD program in the CS department.

Currently, it was hard coming up with my dissertation topic but once I did I had a lot of fun. My thesis is that natural language descriptions of emotions are definite descriptions that refer to intersubjective theoretical entities. Pardon the technical jargon. In plain English, this just means that different people may describe their emotions differently, but yet they can come to mutual understanding. Making a theory about how people do this despite the fact that emotions are abstract and hard to objectively measure is the scientific component of my thesis . The technological component is to make a computer agent that can simulate such human behavior .

Around the time of working on my dissertation I bought a boat for myself for Christmas in 2011. That improved my morale and led me to learn about boating safely and volunteering in the Coast Guard Auxilary. After defending my dissertation I've worked in a range of small, medium, and big companies, and I also did tutoring and contracting. My friend Brian Gabelman got me into radio and I have my General license, call sign KK6RWQ

Up Close And Personal

To really get inside of my head, you can see this magnetic resonance movie and various images .