GSLT: Speech Technology 1

Fall semester 2002
Graduate School of Language Technology

__________________________________________________

Introductory lectures
Reading material
Term paper
Practical assignments
Closing seminar
Requirements
Teachers

Overview

The aim of this course is to give an overview of speech technology, some of the underlying theories and models and how these are integrated into applications, such as multimodal dialog systems.

The course is aimed both at students with limited knowledge of the field, for whom it is compulsory within GSLT, and at students with a more extensive background in speech technology, who will be expected to take a more active part in the discussion of current research. In this way, the course is meant to contribute to the common platform for students with different backgrounds within GSLT.

The course is divided into 5 parts:
Introductory lectures; Reading the listed material; Individual practical exercises; Preparing a term paper; and a Closing seminar including discussions, practical exercises and presentation of the term papers.

Introductory lectures September and October in Göteborg

These lectures will give an overview of the field with an emphasis on basic concepts and standard methods.

Introductory lecture slides will be linked to each topic.

Date

Time

Content

Teacher

9/9

8-10

Introduction
Acoustic Phonetics

Rolf Carlson
David House

9/9

10-12

Speech Recognition
Part1, Part2

Kjell Elenius & Mats Blomberg

9/9

13-15

Speech Recognition
Speaker Verification

Kjell Elenius& Mats Blomberg

24/10

13-15

Speech Synthesis

Björn Granström

25/10

8-10

Dialog Systems

Rolf Carlson

Time Table 2002 - 2003

Week/Date

Content

Place

37

Lectures

GU, Göteborg

38-42

Reading, practical  assignments

 

October 16

Last day to mail assignment reports

 

43

Lectures, assignment reports

GU, Göteborg

44-5

Reading, term paper

 

December 12

Mail draft by author to reviewer

 

January 9

Mail review to author

 

January 26

Mail final paper to rolf (KTH)

 

February 6-7

Closing seminar

KTH, Stockholm

Reading material

Acoustic and Auditory Phonetics, Keith Johnson, ISBN# 0-631-20094-0

An Introduction to Text-To-Speech Synthesis, Thierry Dutoit, ISBN# 0-7923-7923-4498-7

Speech and Audio Signal Processing: Processing and Perception of Speech and Music, Ben Gold & Nelson Morgan ISBN# 0-471-35154-7

Michael F McTear (2001) Spoken dialogue technology: enabling the conversational influence. Submitted to ACM Computing Surveys.
http://www.infj.ulst.ac.uk/~cbdg23/interests.html

A selection of papers and other publications will be used as additional reading material for each subtopic.

Practical assignments

Each student should carry out an acoustic investigation of their own voice. This exercise will make the student familiar with speech analysis and the basic structure of speech sounds. The results should be summarised, distributed and presented during week 43. More information on Practical assignment – Phonetic analysis

Last day to send results of recognition/verification problems October 16 to David House davidh@speech.kth.se

Assignments on speech recognition/verification problems will be distributed during the introductory lectures in September. The results should be summarised, distributed and discussed by all students during week 43. The recognition/verification problems can be found on http://www.speech.kth.se/~matsb/GSLT/GSLT_02_ovn_uppg_eng.pdf

Last day to send results of recognition/verification problems October 16 to Mats Blomberg mats@speech.kth.se

During the closing seminar additional obligatory exercises will be included.

Term paper

During the course a term paper should be prepared by each student. The paper should be presented during the closing seminar.

More information here

Closing seminar

The closing seminar includes:

 

More information here

Requirements

In order to pass the course the students must:

Teachers

Rolf Carlson rolf@speech.kth.se (Responsible for the course) http://www.speech.kth.se/~rolf
Mats Blomberg mats@speech.kth.se http://www.speech.kth.se/~matsb
Kjell Elenius kjell@speech.kth.se http://www.speech.kth.se/~kjell
Björn Granström bjorn@speech.kth.se http://www.speech.kth.se/~bjorn
David House davidh@speech.kth.se http://www.speech.kth.se/~davidh

Dept. Speech, Music and Hearing, KTH (Royal Institute of Technology)
SE-100 44 Stockholm, Sweden
http://www.speech.kth.se
http://www.speech.kth.se/info/location.html