EC1020 SPEECH PROCESSING 3 0 0 100
AIM
To introduce the characteristics of Speech signals and the related time and frequency domain methods for speech analysis and speech compression
OBJECTIVE
• To introduce the models for speech production
• To develop time and frequency domain techniques for estimating speech parameters
• To introduce a predictive technique for speech compression
• To understand speech recognition, synthesis and speaker identification.
UNIT I NATURE OF SPEECH SIGNAL 9
Speech production mechanism, Classification of speech, sounds,
nature of speech signal, models of speech production.
Speech signal processing: purpose of speech processing, digital models for speech signal, Digital processing of speech signals, Significance, short time analysis.
UNIT II TIME DOMAIN METHODS FOR SPEECH PROCESSING 9
Time domain parameters of speech, methods for extracting the parameters, Zero crossings, Auto correlation function, pitch estimation.
UNIT III FREQUENCY DOMAIN METHODS FOR SPEECH PROCESSING 9
Short time Fourier analysis, filter bank analysis, spectrographic analysis, Format extraction, pitch extraction, Analysis - synthesis systems.
UNIT IV LINEAR PREDICTIVE CODING OF SPEECH 9
Formulation of linear prediction problem in time domain, solution of normal equations, Interpretation of linear prediction in auto correlation and spectral domains.
UNIT V HOMOMORPHIC SPEECH ANALYSIS 9
Central analysis of speech, format and pitch estimation, Applications of speech processing - Speech recognition, Speech synthesis and speaker verification.
TOTAL : 45
TEXTBOOK
1. L.R. Rabiner and R.E Schafer : Digital processing of speech signals, Prentice Hall, 1978.
REFERENCES
1. J.L Flanagan : Speech Analysis Synthesis and Perception - 2nd Edition - Sprenger Vertag, 1972.
2. I.H.Witten :Principles of Computer Speech , Academic press, 1983.
AIM
To introduce the characteristics of Speech signals and the related time and frequency domain methods for speech analysis and speech compression
OBJECTIVE
• To introduce the models for speech production
• To develop time and frequency domain techniques for estimating speech parameters
• To introduce a predictive technique for speech compression
• To understand speech recognition, synthesis and speaker identification.
UNIT I NATURE OF SPEECH SIGNAL 9
Speech production mechanism, Classification of speech, sounds,
nature of speech signal, models of speech production.
Speech signal processing: purpose of speech processing, digital models for speech signal, Digital processing of speech signals, Significance, short time analysis.
UNIT II TIME DOMAIN METHODS FOR SPEECH PROCESSING 9
Time domain parameters of speech, methods for extracting the parameters, Zero crossings, Auto correlation function, pitch estimation.
UNIT III FREQUENCY DOMAIN METHODS FOR SPEECH PROCESSING 9
Short time Fourier analysis, filter bank analysis, spectrographic analysis, Format extraction, pitch extraction, Analysis - synthesis systems.
UNIT IV LINEAR PREDICTIVE CODING OF SPEECH 9
Formulation of linear prediction problem in time domain, solution of normal equations, Interpretation of linear prediction in auto correlation and spectral domains.
UNIT V HOMOMORPHIC SPEECH ANALYSIS 9
Central analysis of speech, format and pitch estimation, Applications of speech processing - Speech recognition, Speech synthesis and speaker verification.
TOTAL : 45
TEXTBOOK
1. L.R. Rabiner and R.E Schafer : Digital processing of speech signals, Prentice Hall, 1978.
REFERENCES
1. J.L Flanagan : Speech Analysis Synthesis and Perception - 2nd Edition - Sprenger Vertag, 1972.
2. I.H.Witten :Principles of Computer Speech , Academic press, 1983.
EmoticonEmoticon