Teaching

CS4706: Spoken Language Processing, Spring 2008

Time: Mon/Wed 2:40-3:55
Place: 1127 Mudd

Professor Julia Hirschberg (Office Hours Mon 4:00-6:00)
julia@cs.columbia.edu, 212-939-7114

Teaching Assistant Fadi Biadsy (Office Hours Wed 12:00-2:00)
fadi@cs.columbia.edu, 212-939-7111/7147

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

Description

This course introduces students to research in spoken language in computational linguistics, aka natural language processing (NLP). We will study the different `meanings' that can be conveyed by the way that speakers produce sentences, techniques for analyzing spoken language, methods of developing speech technologies, and applications of such technologies in the real world, such as text-to-speech systems, speech recognizers, spoken dialogue systems, and detectors for various types of emotional speech.  NB: This course can be counted as a PhD elective in Advanced AI .  It is a requirement for the MS NLP Track.  There are no official prerequisites for this course except Data Structures or equivalent, and no prior knowledge of NLP will be assumed.

Requirements

Four homework assignments, a midterm and a final exam. Each student in the course is allowed a total of 4 late days on homeworks with no questions asked; after that, 10% per late day will be deducted from the homework grade, unless you have a note from your doctor.  Do not use these up early!  Save them for real emergencies. 

All students are required to have a Computer Science Account for this class. To sign up for one, go to the CRF website and then click on "Apply for an Account".

Homework submission procedure.

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 instructor or TA in advance of the due date.

Readings

Required readings: Chapters from the second edition of Speech and Language Processing by Jurafsky and Martin available in draft form as a reader from the Village Copier on Amsterdam & 119th Street.  Recommended readings: Acoustic & Auditory Phonetics by Keith Johnson (Chapter 1 is available on line) and all other readings marked by ‘*’.

Course Requirements

Midterm and final; N lab homeworks.  The Speech Lab is available for use in homeworks on a signup basis.

Grading:
60% Homeworks
20% Midterm Exam
20% Final Exam

Late Policy
Each student starts the semester with 5 late days. Students use up late days when they turn in homework anytime after the due date and time.  For example, if homework is due at 2:40 pm on Wednesday, anything turned in after 2:40 pm on Wednesday, but before 2:40 pm on Thursday uses up one late day. Once the ‘free’ late days are exhausted, homework submitted after the due date will be penalized @10% per late day (e.g. 3 days late, grade will be penalized by 30%).
Late days can be used for all homeworks.
(Note:  Weekdays and weekends all count equally in the late day calculation.)

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.

Announcements

See some cool Praat manipulations below under Feb 4.

Resources

Syllabus

Date Topic Reading & Assignments Reports & HW
Jan 23 It's not what you said, it's how you said it Hirschberg03 [ps] [pdf]  
Jan 28 From Sounds to Language J&M 7.1-7.3  
Jan 30 Accoustics of Speech J&M 7.4; *Johnson, Ch. 1-2  
Feb 4 Tools for Speech Analysis Praat tutorial 1 Praat tutorial 2 (some good contours: 1, 2) HW1: Using Praat (assigned)
Feb 6 Studying Intonation:  How do people ask questions? Wilson 93; Hedberg & Sosa 02; Syrdal & Jilka 04; *Dohertyetal 04  
Feb 11 Representing Intonational Variation J&M 8.3.0-8.3.4  
Feb 13  ToBI and ToBI Labeling ToBI labeling conventions; Pierrehumbert & Hirschberg 90
Listen to the ToBI examples
HW1 due
HW2: ToBI (assigned)
Feb 18 Tobi Labeling (continued)    
Feb 20 Speech Generation J&M 8 (all); TTS-history  
Feb 25 Text Normalization J&M 8.1  
Feb 27 Predicting Accents and Phrasing J&M 8.3.4-8.3.7; Pan99, *Sun02, Rosenberg07 Guest Speaker:  Andrew Rosenberg
Mar 3 Modeling Pronunciation J&M 8.2; Fackrell&Skut04 HW2 due
HW3: Data Collection (assigned)
Mar 5 Information Status: Focus and Given/New Nakatani99, GBrown83, *Bard99, Prince92, Dahan02  
Mar 10 Speech Recognition and Understanding J&M 9 (all)  
Mar 12 Speech Recognition and Understanding (continued)    
Mar 17-21 Spring Break    
Mar 24 Speech Disfluencies

J&M 10.6; Hindle 83; Nakatani & Hirschberg 94; Bear 92; Liuetal03

 
Mar 26 Sentence  and Topic Segmentation J&M 10.6; Shriberg00, Choi00, *Utiyama01, HW3 due; HW4: TTS-oncampus, TTS-cvn (assigned)
Mar 31 Spoken Dialogue Systems: Overview J&M 24; *Bel l& Gustafson 00  
Apr 2 Managing Dialogue J&M 24.1.2; 24.5.1-2  
Apr 7 Dialogue Acts and Information State J&M 24.5.3 Hirschbergetal04, Rosset&Lamel04    
Apr 9 Confirmation Strategies and SDS Evaluation Walkeretal97, Goldberg03  
Apr 14 Entrainment in SDS Brennan96; Roth05  
Apr 16 Speech Data Mining and Distillation Maskeyetal04, Koumpis & Renals05 HW4 due; HW5: ASR (assigned)
Apr 21 ASR for SDS (HTK Toolkit)   Guest Lecturer:  Fadi Biadsy
Apr 24 Emotional Speech Cowie00, *Pereira00, Schroeder01, *Bosch00, Burkhardt00, Ang02,*Gobl&Chasaide03  
Apr 28 Deceptive Speech  DePauloetal83, Frank92, *Mehrabian77, Streeteretal71  
Apr 30 Charismatic Speech Boss76, Tuppen74, Weber47  
May 5 Summing Up   HW5 due
May 6-8 Study Days    
TBA (May 9-16) Final Exam   Covers the entire course

 

Julia Hirshberg Portrait

Julia Hirschberg
Professor, Computer Science

Columbia University
Department of Computer Science
1214 Amsterdam Avenue
M/C 0401
450 CS Building
New York, NY 10027

email: julia@cs.columbia.edu
phone: (212) 939-7114

Download CV

Columbia University Department of Computer Science / Fu Foundation School of Engineering & Applied Science
450 Computer Science Building / 1214 Amsterdam Avenue, Mailcode: 0401 / New York, New York 10027-7003
Tel: 1.212.939.7000 / Fax: 1.212.666.0140