The course covers the basics of automatic speech recognition and synthesis systems.
The first part is dedicated to speech recognition and covers the following topics:
Data collection for speech recognition – Acoustic feature extraction – Acoustic modeling - Language modeling - Evaluation and optimization of a speech recognition system – Overview of state-of-the-art speech recognition systems - Development of a speech recognition system
The second part of the course is about text-to-speech synthesis and will cover the following topics:
Data collection for speech synthesis - Types of speech synthesis systems - Text processing for Speech synthesis – Speech modeling for parametric speech synthesis- State-of-the-art speech synthesis systems - Development of a speech synthesis system
Last, the course will cover the basics of the application of these technologies in speech-to-speech translation and spoken dialogue systems.
nkatsamathenarc [dot] gr (Nasos Katsamanis)
antsiamics [dot] ntua [dot] gr (Antigoni Tsiami)