Seminar Speech Recognition 2003

(Last updated: 23-2 2004)

• Period
• Time
• Place

• Organizers
• Abstract
• Requirements
• Recommended Books
• Schedule

• Links

Previous Seminars

• Speech Recognition 2002

Time: Wednesday 13.45 – 15.30

Place: LIACS, Room 407

Organizers:

Dr Erwin M. Bakker

Room 147 and LIACS Media Lab (LML), Tel. , Email: erwin@liacs.nl

Drs Joost Broekens (Teaching Assistant)

Room 120, Tel: 071 527 5779, Email: broekens@liacs.nl

NB E-mail your name, phone, and college card number to erwin@liacs.nl with subject 'SR2003'.

Abstract:

In this seminar all aspects of a state of the art speech recognition system will be studied. The main goal is to apply our studies to design and develop different modules of a speaker independent small vocabulary Dutch speech recognition system. The participation and contribution of the students is of great importance. There will be several programming assignments, reports, and presentations by the students.

Requirements: C, C++

Grading (7.2 ECTS): Design, Programming and Documentation for your speech recognition module plus further presentations (70% of grade). Class discussions, attendance, and problem sets (30% of grade). It is necessary to be at every class. If you can not be there, you must contact Dr. Bakker (erwin@liacs.nl) before the class!

List of recommended books:

Spoken Language Processing: A Guide to Theory, Algorithm and System Development by Xuedong Huang , Alex Acero , Hsiao-Wuen Hon , Raj Reddy (Hardcover, 980 pages; Publisher: Prentice Hall PTR; ISBN: 0130226165; 1st edition, April 25, 2001) 

Speech Recognition: Theory and C++ Implementation by Claudio Bechetti and Lucio Prina Ricotti (Hardcover, 407 pages; Publisher: John Wiley & Sons; ISBN: 0471977306; 1st edition April, 1999)

Fundamentals of Speech Recognition by Lawrence Rabiner, and Biing-Hwang Juang (Hardcover, 507 pages; Publisher: Pearson Education POD; ISBN: 0130151572; 1st edition, April 12, 1993)

Tentative Schedule:

1. 03-09-03: Introduction Speech Recognition

2. 10-09-03: Continuous Speech Recognition (A technical overview)

3. 17-09-03: SPHINX Workshop (cmusphinx.org)

4. 24-09-03: Project Groups and Preliminary Proposals

5. 01-10-03

• Signal Processing Front-End

• Pre-emphasis and Hamming Windowing

• Power Spectrum Analysis

• Mel-Spectrum Computation

• Mel-Spectrum to Mel-Cepstrum

6. 08-10-03: Project Proposals

• Acoustic Modeling & Robustness

• Cepstral to Feature Stream

• HMM model

7. 15-10-03

• Phonemes

• Triphones

• Language Model

8. 22-10-03: MS Speech and CSLU Toolkit Workshop (Babble code)

9. 29-10-03: Speech Recognition: Search Algorithms

10. 05-11-03: Preliminary Project Presentations and Discussions

11. 12-11-03: Speech Recognition: Applications

12. 19-11-03: Speech Synthesis

13. 26-11-03: Final Presentations and Demos of Student Projects

Projects

Here you can find the example project page. Do not forget to mail me the link to your project page.

• English Accent Recognition Tool

• The Digital Reception Desk

• Noise Reduction

• Tune Recognition

• Say What: Robust Speech Recognition

• Voice Authentication

• ASR on PDA using a Server

• Programming by Voice

• VoiceXML

• Chemical Equations TTS

Links

• ISIP Project Site Automatic Speech Recognition

• Center for Spoken Language Understanding

• The Center for Speech Technology Research, University of Edingburgh

• The CMU Sphinx Group Open Source Speech Recognition Engines

VoiceXML

• www.bevocal.com

• www.heyanita.com

• cafe.bevocal.com/wiley/10projects