Advanced Natural Language Processing (CS 6998), Spring 2003: Speech Research and Technologies

Time: W  4:10-6:00 Place 825 MUD 
Professor:  Julia Hirschberg Office Hours:  TTh  2:30-3:30, CEPSR 705
Email: Phone:  212-939-7114

Announcements || Academic Integrity || Description
Links to Resources || Requirements || Syllabus || Readings


This course introduces students to the study of spoken language in computational linguistics, aka natural language processing (NLP). We will examine approaches to the analysis of the speech signal of particular interest to NLP research, look at several speech technologies in some detail, including approaches to recognizing and to generating speech, and consider several important application areas for these technologies, including spoken dialogue systems and speech data mining. There are no formal prerequisites for the course (i.e. no knowledge of speech or signal processing is assumed) but some knowledge of/serious interest in NLP is assumed. Format for the class will be lecture and discussion. NB: This course can be counted as a PhD elective in Advanced AI.


There is no text, but Speech and Language Processing by Jurafsky and Martin may be used as a reference text by those with no formal background in NLP. The early chapters of one of the following paperbacks, The Speech Chain by Peter Denes and Elliot Pinson (on reserve in Psychology Library), Elements of Acoustic Phonetics by Peter Ladefoged, or Acoustic & Auditory Phonetics by Keith Johnson will also be useful. Used copies of all these should be available in local bookstores, as well as from Amazon and other online providers. Most course readings will be available either on the web or in-class handouts (also available from Matthew Schlager, CEPSR 701). NB: '*' means that the reading is optional.


Class participation and a term project. Class participation will include a) bringing 3 discussion questions to class each week, based on the readings; and b) helping to lead one class discussion during the semester. The project (done alone or in collaboration) on one of the topics coverered in the course or some other topic in spoken language will be defined by each class participant in consultation with the professor. These projects will involve a) a project description; b) periodic project reports on progress; c) a class presentation of project results; and d) delivery of the final project. Project formats may include literature reviews, data collection and analysis, and/or systems or system components.

Academic Integrity:

Copying or paraphrasing someone's work (code included), or permitting your own work to be copied or paraphrased, even if only in part, is not allowed, and will result in an automatic grade of 0 for the entire assignment or exam in which the copying or paraphrasing was done. Your grade should reflect your own work. If you believe you are going to have trouble completing an assignment, please talk to the professor in advance of the due date.


Hirschberg & Ward '92 copies are incomplete. Please pick up complete copies by 10:30 today, 2/19, CEPSR 705 (where all papers are now).


Week Date Topic Readings and Assignments
1 Jan 22 Introduction to the Course *Optional
2 Jan 29 Interpreting Speech Variation Hirschberg03, ToBI labeling conventions, and see ToBI examples
3 Feb 5 Analyzing the Speech Signal Handout; Recommended: Johnson (Chs 1,2) or Denes&Pinson (Chs 1,3,4) (on reserve in Psychology Library)
  Feb 12 Speech Generation: From Concept and from Text HLT96-ch5, TTS systems
  Feb 19 Meanings of Intonational Contours (George) Pierrehumbert&Hirschberg '90, Bolinger '86 (pp.274-335), Liberman&Sag '75, Hirschberg&Ward '92* (complete version of this available today by 10:30)
  Feb 26 Predicting Accents and Phrasing (Max) Wang92 (figures handed out in class),Pan99,Sun02,Koehn00
  Mar 5 Information Status: Focus and Given/New (Mat) *Nakatani99,GBrown83, Bard99, *Theune97, Prince92
  Mar 12 Emotional Speech (Frank) Cowie00, Pereira00, Schroeder01, Bosch00, *Burkhardt00, *Ang02
  Mar 19   Spring Break
  Mar 26 Speech Recognition and Understanding HLT96-ch1
  Apr 2 Speech Acts and Topic Segmentation (Michel) Jurafsky98, Shriberg00, Nickerson&Chu-Carroll99, *Shriberg98
  Apr 9 Speech Disfluencies and Turntaking (Heba, Ilana) Turn-taking in Conversational Analysis (follow links) , *Sacksetal74, Bear92, *Brennan&Schober99, Hindle83,
  Apr 16 Spoken Dialogue Systems (Jackson,Christy) Walkeretal97, Bell&Gustafson99, Bell&Gustafson00, Krahmer01
  Apr 23 Speech Search, Data Mining, and Summarization (Andrew, Andrea) SCANMail demo, Furui02, Barzilay00, Hearst99
  Apr 30   Presentation of Term Projects (15 minutes each)
  May 7   Presentation of Term Projects (15 minutes each)
  May 16   Final Projects due

Announcements || Academic Integrity || Description
Links to Resources || Requirements || Syllabus || Text || Thanks