COURSE OUTLINE: Oral Speech may be the most natural, common and direct mode of human communication. Since the middle of the last century, Speech has become an area of intense and active research and development (R&D) to become a prime means of direct HumanComputer Interactions (HCI). The pace of such R&D as further got boosted with the general abundance of cheap computing power in the form of PC, PDA or Mobile Handset. While man to machine in speech mode is yet to reach the minimum threshold level for widespread deployment, spoken messages directly by machine. This needs research in speech science and the development of speech technology. The course provides the foundation knowledge on speech production and perception along with the processing of speech signals in the digital domain.
Overview
Syllabus
Introdution to Digital Speech Processing.
Digitization and Recording.
Review of DSP Concepts.
Review of DSP Concepts (Contd).
Human Speech Production and Source Filter Model.
Place and Mannerat Articulation.
Articulatory and Acoustic Phonetics.
Handson on Acoustic Phonetics.
Uniform Tube Modeling of Speech Processing - I.
Uniform Tube Modeling of Speech Processing - II.
Uniform Tube Modeling of Speech Processing - III.
Uniform Tube Modeling of Speech Processing - IV.
Uniform Tube Modeling of Speech Processing - V.
Uniform Tube Modeling of Speech Processing - VI.
Uniform Tube Modeling of Speech Processing - VII.
Speech Perception - Part I.
Speech Perception - Part II.
Speech Perception - Part III.
Time Domain Methods in Speech Processing.
Time Domain Methods in Speech Processing (Contd).
Introduction to Linear Prediction.
Autocorrelation Method of LPC analysis.
Autocorrelation Method of LPC analysis ( Contd.).
Lattice Formulations of Linear Prediction.
Lattice Formulations of Linear Prediction ( Contd.).
Overview of Short - Time Fourier Transform (STFT).
Short - Time Fourier Transform Analysis.
Short-Time Fourier Transform Synthesis.
Lattice Formulations of Linear Prediction.
Lattice Formulations of Linear Prediction ( Contd.).
Segmental and Supra-segmental features of speech signal.
Cepstral Transform Coefficients (CC) Parameters extraction.
Mel Frequency Cepstral Coefficients.
MFCC features vector.
Fundamental Frequency(F0) Detection of speech signal.
Frequency Domain Fundamental Frequency Detection Algorithms.
Text to Speech Synthesis.
Text to Speech Synthesis ( Contd.).
Automatic Speech Recognition.
Statistical Modeling of Automatic Speech Recognition.
Speech based Technology Development for e-learning.
Prosody Modeling.
Fundamental frequency countur modeling.
Fundamental frequency contour modeling (Contd.).
Taught by
Digital Speech Processing
