This module aims to let students understand spoken language processing and develop an understanding of the acoustic of speech signals and corresponding phonetics; time and frequency-based digital analysis of the speech signals; machine learning-based robust, scalable, and adaptive speech processing; automatic speech recognition and speech synthesis. This module also aims to let students get familiar with recent popular research outcomes of speech recognition and speech synthesis, and prepare students to develop spoken language processing systems of practical use.
A. Demonstrate a systematic and critical understanding of human speech generation, transmission, and perception. B. Demonstrate a theoretical and practical understanding of acoustic phonetics, phonology, and time and frequency-based processing. C. Demonstrate an understanding of the speech processing pipeline, and the mathematical models describing these processes. D. Develop basic speech recognition and synthesis methods. E. Appreciate and critically evaluate the new research and applications in speech processing.
Students will be expected to attend two hours of formal lectures as well as to participate in two hours of supervised practical (tutorial/lab) classes in a typical week. Students will be asked to devote eight and half hours of unsupervised time for reflection and consideration of lecture material and will be required to research and read widely on the subject, and where possible use their personal experiences from work placements.