EE590: Speech Recognition and Synthesis

To provide an understanding of the fundamental concepts and algorithms used in speech recognition and synthesis.

NO. OF CREDITS: 3
COMPULSORY/OPTIONAL: OPTIONAL
PREREQUISITES: EE325

MAIN TOPICS AND INTENDED LEARNING OUTCOMES

ILO1: Describe the human speech production and perception systems and associated models.

ILO2: Write programs in a high-level language to analyze, visualize and extract features form speech signals.

ILO3: Apply speech processing techniques and algorithms learned for simple speech processing tasks.

ILO4: Build a language model for a selected language for speech recognition and synthesis purposes.

ILO5: Use open source speech recognition and speech synthesis toolkits to build systems for speech recognition and synthesis.

NO	RECOMMENDED TEXT
1	Lawrence Rabiner and Ronald Schafer, Digital Speech Processing Theory and Applications, Pearson, 2011
2	Daniel Jurafsky and James Martin (2020), Speech and Language Processing, Third Edition Draft, 2020
3	KBN Ratnayake, New approaches to Phoneme based speech recognition, Doctoral thesis, 1993
4	Steve Young, The HTK Book v3.4, Cambridge University Engineering Department, 2009
5	Paul Taylor, Text to Speech Synthesis, Cambridge University Press, 2009