Speech Processing

Starting with an introduction that makes no assumptions about background knowledge, followed by text-to-speech synthesis, and automatic speech recognition.

This course is taught at the University of Edinburgh at advanced undergraduate and Masters levels.

This is the 2017-18 version of the course, with a much improved layout but mostly the same video content.

The content is ready for modules 1 to 5 (introduction, speech synthesis), and modules 6 and 7 (the start of the speech recognition section). The remaining modules (8,9) will be ready for you at least a couple of weeks before they are covered in class.

The previous version of this course remains available.