Mats Blomberg, mail: matsb at speech.kth.se,
Web: http://www.speech.kth.se/~matsb
Kjell Elenius, mail: kjell at speech.kth.se,
Web http://www.speech.kth.se/~kjell
Joakim Gustafson, mail: jocke at speech.kth.se,
Web:
http://www.speech.kth.se/~jocke/ (Responsible for the class)
David House, mail: davidh at speech.kth.se,
Web: http://www.speech.kth.se/~davidh
KTH, CSC, Dept. Speech, Music and Hearing, Stockholm, Sweden
This is a distance course with two meetings at KTH in stockholm. The first meeting will take place 4-5 November 2009, and the closing seminar will be held in January 2010.
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 intended for both students with a limited knowledge of the field and for students with a more extensive background in speech technology. The students will be expected to take a more active part in the discussion of current research. The course is also meant to contribute to the common platform for students with different backgrounds in the graduate school of language technology (GSLT).
The course is divided into 4 parts:
1. Reading the listed books and the distributed articles
2. Meeting where papers are discussed and practical exercises are done
3. Preparing a term paper
4. Closing seminar where the term papers are presented and discussed.
Individual practical exercises will include speech analysis and specific tasks related to speech technology. The results should be reported and discussed during the fall period.
During the course a term paper should be prepared by each student. The paper should be presented during the closing seminar in January (Stockholm).
Date |
Time |
Content |
Teacher |
4/11-5/11 |
Fantum, TMH, KTH, Stockholm |
Speech and Speaker Recognition |
Mats Blomberg |
2010 |
Fantum, TMH, KTH, Stockholm |
Closing seminar |
All teachers |
Phonetic
analysis: Each student should carry out an acoustic investigation
of their own speech. This exercise will make the student familiar
with speech analysis and the basic structure of speech sounds.
The results should be summarised and all students should prepare to
present and discuss their solutions at the first meeting in November.
More
information here
During the course a term paper should be prepared by each student and reviewed by two other students. The paper should be presented during the closing seminar.
The closing seminar includes: Presentation of term papers; Discussion of the reading material and the term papers.
Acoustic and Auditory Phonetics, Keith Johnson, ISBN# 0-631-20094-0 (a second edition is also available)
An Introduction to Text-To-Speech Synthesis, Thierry Dutoit, ISBN# 0-7923-7923-4498-7
Holmes, John and Wendy Holmes (2001 2nd): Speech Synthesis and Recognition, London: Taylor & Francis, ISBN 0-7484-0856-8 (hardback), ISBN 0-7484-0857-6 (paperback)
Michael F McTear (2002) Spoken dialogue technology: enabling the conversational interface. ACM Computing Surveys, Volume 34 , Issue 1 (March 2002), pp. 90 - 169. http://www.infj.ulst.ac.uk/~cbdg23/interests.html
A selection of articles will be used as
additional reading material for each subtopic:
Acoustic Phonetics
Speech synthesis
Speech recognition
Speaker recognition
Dialogue systems
The students should read all articles so that they are able to participate in a discussion about them at the first meeting. Each student also has to select one article per topic that they are willing to present at the first meeting. Before the meeting the teachers will inform the students which of their choosen articles they actually are actually going to present. The articles are available here: Zip with papers
In order to pass the course the students must: Complete the practical exercises; Read, prsent and discuss the articles at the first meeting, Prepare and present the term paper; Review two term papers; Participate actively in the discussions in the closing seminar.
Last updated: January 7, 2009