University of Patras, Electrical and Computer Engineering Department (UPATR)

Contact person: Prof. Nikos Fakotakis (Wire Communication Lab.)

26 500 Rio, GREECE

Tel.: +30.2610.996216

Fax: +30.2610.997.336

e-mail: fakotakis@wcl.ee.upatras.gr

http://slt.wcl.ee.upatras.gr/Fakotakis/index.asp

• Collective development-curricula, dissemination and marketing.

• Teaching program for Module Phonetics and Phonology,Natural Language Processing, Speech Signal Processing, Pattern Recognition, Programming User.Languages
• Advanced courses in the main points:Signal language processing, specially in Speech Encoding, Speech Synthesis
• Coordination of the dissertation in Signal language processing.

• Semantic Networks.
• Semantic Parsing.
• Knowledge Representation.
• Discourse and Reference.
• Natural Language generation.
• Other approaches to Natural Language Processing.

Introduction

• Phonetics.
• Phonology.
• Morphology.
• Syntax-grammar.

• Semantic Interpretation: Semantic and alogical form, semantic interpretation, strategies and issues in semantic interpretation.
• Context and world knowledge: Knowledge representation, reference, discourse structure. Dialogue Systems.
• Text generation.

Applications

• Automatic Translation,
• Lexicography,
• Automatic Access to Databases,
• Speech Understanding Systems,
• Man-machine communication.

• Speech production. Hearing, speech perception. Speech signal analysis. Feature Extraction
• Coding of speech signals: Waveform coding, Spectrum coding, Analysis-Synthesis coding, Linear Predictive coding.
• Speech enhancement.
• Pattern recognition (Hidden Markov models (HMM), Artificial Neural Networks (ANN), Dynamic Programming (DP))
• Speech synthesis.

Applications

Speech recognition: Continuous speech recognition, Word spotting, Isolated word recognition. Speaker recognition: Speaker identification, Speaker verification. Language identification. Spoken dialogue systems.

• User interface design methodologies.
• User analysis.
• Dialogue design, Command language Grammar (CLG). Diagrammatic dialogue specification.
• Presentation design.
• User modelling techniques.
• Natural Language interfaces.
• Introduction to Computer graphics. Basic computer graphics algorithms. Raster graphics fundamentals 3D graphics techniques.
• Multimedia and virtual reality.
• Advanced techniques for human-computer interaction, user-centred system design, advanced graphics techniques.

• Introduction developments in audio technology.
• Theory of digital audio: sampling quantization, over-sampling, low-bit conversion.
• Audio data storage, file and data formats, storage devices, multimedia applications, audio data transmission and broadcasting.
• Specialist topics in audio DSP: multi-channel coding and reproduction, equalisation, noise removal, hardware implementation.
• Music synthesis and studio technology.

• Basic concepts of pattern recognition. Supervised and unsupervised training. Estimation of the probability of classification error-Error bounds.
• Distance functions. Minimum distance pattern classification. k-nearest neighbour classification. Single and multiply prototypes.
• Decision functions. Linear decision functions. Perceptron and k-means algorithm. Bayes classifier. Bayes decision rule for minimum risk. Estimation of probability density function: Maximum entropy criterion, Parzen estimate, ortho-normal functions approximation. Stochastic approximation of the probability density function: Robbins-Monro and LMS algorithm.
• Neural networks structure. Error correction, competitive and hebbian learning. Multilayer perceptron. Back-propagation of error. Radial-Basis function networks. Hopfield machine.
• Syntactic pattern recognition. Formal languages. Type-0,1,2,3. CYK algorithm. Stochastic languages.
• Grammatical inference.
• Error correction.

• Training pattern recognition systems: Line search, gradient descent, Conjugate gradients, Newton, the Levenberg-Marquart algorithm, Bayes learning, Monte Carlo methods, simulated annealing, Genetic algorithms.
• Minimum description length principle.
• Pre-processing and feature selection.
• Karhunen-Leove expansion.
• Syntactic pattern recognition and error correction.
• Markov and hidden Markov models, recurrent neural networks and non-linear temporal processing.
• Image recognition applications.

• Introduction.
• PROLOG rules.
• Matching.
• Recursion.
• Cutting.
• List processing.
• Built-in functions.
Assert-Retract.
• Defining operators.
• Reserved streams.
• DCG rules.

• Introduction to embedded systems design and programming.
• Design and Development of Object-Oriented Applications. Introduction to OO design using UML, use cases, class diagrams, object-interaction diagrams. Aggregation, Inheritance, polymorphism, late binding, Exception Handling, Garbage Collection, Event Handling, Networking. Case study: Reverse Polish Notation Calculator.
• Concurrent Programming Introduction, Concurrent Programming abstraction, the Mutual Exclusion problem, Dekker’s Algorithm, Semaphores, Monitors, Producer-consumer, Java constructs for Concurrent programming. Case study: The problem of the Sleeping Barber.
• Low Level Programming – System level programming C constructs for low level programming, bit-wise operators, bit-fileds, unions, typedefs, pointers. Dynamic memory allocation. Interfacing with Assembly, Interfacing with the operating system.
• Interfacing with hardware devices. Case study: The RS232 interface-Programming the 8250 UART.