Page 87 - R2017-REC-ECE-UG Syllabus

Department of ECE, REC

• Discuss hybrid soft computing
• Appreciate the role of soft computing in computational intelligence applications.

TEXT BOOKS:
1. J.S.R.Jang, C.T.Sun and E.Mizutani,Neuro-Fuzzy and Soft Computing, PHI, 2004 Pearson Education
2004.
2. N.P.Padhy, ―Artificial Intelligence and Intelligent Systems, Oxford University Press, 2006.

REFERENCES:
1. J.Ross, ―Fuzzy Logic with Engineering Applicationsǁ, McGraw-Hill, 1997.
2. Davis E.Goldberg, ―Genetic Algorithms: Search, Optimization and Machine Learning, Addison
Wesley, N.Y., 1989.
3. S. Rajasekaran and G.A.V.Pai, ―Neural Networks, Fuzzy Logic and Genetic Algorithms, PHI, 2003.
4. R.Eberhart, P.Simpson and R.Dobbins,―Computational Intelligence- PC Tools, AP Professional,
Boston, 1996.
5. Dr.S.N.Sivanandam and S.N.Deepa, ―Principles of Soft Computing, Wiley India, 2007.
6. Amit Konar, ―Artificial Intelligence and Soft Computing Behaviour and Cognitive model of the human
brain, CRC Press, 2008

EC17E67 SPEECH PROCESSING LT P C
3 0 0 3
PREREQUISITE: Knowledge on Digital signal processing

OBJECTIVES:
• To introduce speech production and acoustic phonetics of speech.
• To apply the computation techniques such as short time Fourier transform, linear predictive
coefficients and other coefficients in the analysis of speech.
• To understand different speech modeling procedures
• To implement the various issues for designing a speech recognition model
• To understand the concepts of different Text-to-Speech conversion techniques
UNIT I BASIC CONCEPTS 9
Speech Fundamentals: Articulatory Phonetics – Production and Classification of Speech Sounds; Acoustic
Phonetics – Acoustics of speech production; Review of Digital Signal Processing concepts; Short-Time
Fourier Transform, Filter-Bank and LPC Methods.

UNIT II SPEECH ANALYSIS 9
Features, Feature Extraction and Pattern Comparison Techniques: Speech distortion measures– mathematical
and perceptual – Log–Spectral Distance, Cepstral Distances, Weighted Cepstral Distances and Filtering,
Likelihood Distortions, Spectral Distortion using a Warped Frequency Scale, LPC, PLP and MFCC
Coefficients, Time Alignment and Normalization – Dynamic Time Warping, Multiple Time – Alignment
Paths.

UNIT III SPEECH MODELING 9
Hidden Markov Models: Markov Processes, HMMs – Evaluation, Optimal State Sequence – Viterbi Search,
Baum-Welch Parameter Re-estimation, Implementation issues.

UNIT IV SPEECH RECOGNITION 9
Architecture of a large vocabulary continuous speech recognition system – acoustic models and language
models – n-grams, context dependent sub-word units- creation of context dependent diphones and triphones-
using inter word training to create CD units-implementation issues using CD units-position dependent units-

Curriculum and Syllabus | B.E. Electronics and Communication Engineering | R2017 Page 87