VIANNA In this Lecture the students will develop a methodology to analyze code, recognize and synthesize audio signals using signal processing techniques. More concrete the student should acquire the theoretical and practical competences related to:
- Fundamentals of acoustics, physiological and perception of sound
- Fundamentals of digital signal processing of audio signals
- Methods for modeling and processing audio and speech signals
Content:
- Introduction
- Fundamentals of speech acoustics: Mechanisms of speech production speech, sound classification, sound representation
- Fundamentals of perception: pitch, intensity and timbre
- Spectral analysis of audio and speech signals
- Speech Models: Physical models of speech
- Fundamentals of speech perception
- Spectral transforms of audio and speech signals
- Models based of speech production: Predictive analysis based on speech production (LPC)
- Application 1: Text-to-Speech Synthesis
- Application 2: Automatic Speech Recognition: Cepstrum analysis, Hidden Markov Models
