ELEC9344: Speech and Audio Processing

ELEC9344: Speech and Audio Processing (UNSW). Taught by Professor E. Ambikairajah, this course provides an introduction to speech and audio processing. Fundamentals of speech production, speech analysis: pitch and period extraction, formant estimation, voiced - unvoiced decision. Non-linear smoothing. Linear prediction. Inverse filtering. Implementation of speech/speaker recognition systems. Auditory modelling, auditory masking. Audio signal processing. Speech and audio compression. Compression standards. Speech enhancement.

Lecture 01 - Introduction to Speech Processing
Lecture 02 - Speech Analysis
Lecture 03 - Linear Predictive Coding (LPC)
Lecture 04 - Speech Coding I
Lecture 05 - Time-Frequency Analysis
Lecture 06 - Auditory Masking; Widebank Audio Coding