Course

• LO1: To introduce the concepts of signal processing with application to speech processing
• LO2: To provide insights on feature extraction for speech coding, synthesis, and recognition
• LO3: To enable understanding of deep learning applications to speech processing and health care

• CO1: Ability to understand concepts of Speech signal processing
• CO2: Ability to apply the concepts of signal processing to feature extraction of speech/audio signals
• CO3: Ability to analyse and process speech data for speech coding, synthesis, and recognition
• CO4: Ability to evaluate speech/audio processing techniques in healthcare applications

Introduction to signal processing – FIR and IIR filters – DFT – FFT – Speech analysis overview – Modelling of speech production – Speech perception and models – Feature extraction for speech processing – Auditory system as a filter bank – Linear predictive coding – Spectrum – Cepstrum – Mel-frequency cepstral coefficients. Introduction to music synthesis – Music signal analysis – Source separation -Speech recognition – Synthesis and coding – Introduction to deep neural networks – Applications of deep learning techniques to speech processing – Applications of speech and audio processing in healthcare – Case studies – Dysarthria – Aphasia. Analysis of speech/audio – Experiment with speech analysis and synthesis – Experiment with deep learning techniques for speech recognition – Analyse the speech signals of controls with dysarthria and aphasia.

1. B. Gold, N. Morgan, D. Ellis, Speech, and Audio Signal Processing: Processing and Perception of Speech and Music, Wiley, 2011.
2. Xuedong Huang, Alex Acero, Hsiao-Wuen Hon, Spoken Language Processing: A guide to theory, algorithm and system development, Prentice Hall Inc., 2001.
3. U Kamath, J Liu, J Whitaker, Deep Learning for NLP and speech recognition, Springer, 2019.
4. Nancy Helm-Estabrooks, Martin L. Albert, & Marjorie Nicholas, Manual of Aphasia and Aphasia Therapy, Third Edition, Pro-Ed, 2013.