At the end of the course, the student will be able to understand the basic concepts of speech processing and to discuss the performances of speech processing applications (as well for speech synthesis applications as for voice recognition applications).
Content and teaching methods
The organization of the course is fourfold :
1. Introduction to basic mathematical concepts necessary for a good understanding of speech processing applications;
2. Introduction to speech models and coding;
3. Overview of "text-to-speech" methods;
4. Overview of technologies in the field of speech processing.
Other information (prerequisite, evaluation (assessment methods), course materials recommended readings, ...)
Prerequisite.
Evaluation. Written exam
Support. Web site and videos