The projects here are a mix of topics, some of which are only suitable for engineering students, but many others are good as well for IT students. I hope to augment the list over the next few days.
 
 

1. Localisation, analysis and measurement of sound

 
This topic has arisen from a recent request of collaboration from a university in turkey. The student will be expected to learn about sound transmission, echoes and reverberation. Using models from the literature, one can than postulate an analysis of the sound energy from a source as it is influenced by the shape and material of an enclosure. Requirements are DAT tapes of a sound source to be analysed.

Student        Cynthia Micallef

 

2. Wavelet Analysis and Synthesis

 
The use of wavelets for pseudo random signals and signals that change over time is now common. This project aims at developing software for the synthesis of a signal whether speech or music using a set of wavelet basis functions. It also aims at looking into the coding properties of wavelets. Requirements are subject knowledge and software tools available.
 
 
3. Speech synthesis using Harmonic + Noise Model

 
This project aims at developing software for speech synthesis using a newer model of speech. The student will be expected to learn the model, use speech data for analysis, development of the model parameters and eventual synthesis from the model parameters. Requirements are subject knowledge, existing speech corpora and software tools.
 
 
4. Automatic Segmentation of Speech using Neural Network

 
This is an ongoing project aimed at building annotated Maltese speech corpora. The first project used the American TIMIT corpus to build a phoneme based neural net. This was adapted in a second project to test Maltese sentences and adapt the American phoneme set to the Maltese phoneme set. The aim of this project is now to use the existing neural net and appropriate software to overcome the present limitations, to automatically segment existing Maltese speech corpora into its phonemic content, to be able to use this annotated corpus to train a Maltese based speech recognition system.
 
 
5. Speech Recognition in Noisy Background

 
This project is also known as robust speech recognition. It aims at looking into appropriate robust features that are immune to background noise ,such as in an office, while talking. The student will have to familiarise himself/herself with acoustics of speech and various speech parameters. Preliminary testing need not necessarily use neural nets or HMM.

Student        Daniel Grech

 

6. Speech pedagogical tools

 
This project is suitable both for engineering and IT students. It aims at producing a friendly user interface. There are various tools that can be developed, and the student will be concerned with one of them. Among others, a GUI showing time waveforms, acquisition of parameters on the sliding time waveform. Parameters including FFT, spectral envelope, various acoustic features.
Another is a GUI for various neural net types, aimed at showing the weights varying during training, effect of hidden layer node number etc.
 
 
7. Computer hardware pedagogical tool

 
This year a student developed a basic tool that can be used to demonstrate how hardwired control operates to execute instructions. This year the project aims at continuing the development to include other modules, such as a parallel floating point system that shows how the numbers are broken down the mantissas and exponents treated etc., or a pipeline system showing how the instruction operands move and change within the pipeline. Requirements are suitable IC's. Much of the development have used Xilinx FPGA's and the student will be expected to continue development on this platform.
 
 
8. Spoken Dialogue System for Lotto

 
This aims at developing a natural language model interlinked with a speech recognition system that is capable of recognising the bets on the various games such as lotto, superfive etc., the numbers being betted, and the price or type. The machine has to perform a suitable dialogue. This year there can be various developments including the natural language definitions, (suitable for IT students), a start on suitable recording of speech to extract training material for the recogniser, etc.

Requirements are a course on linguistics or natural language understanding and the student would have to learn on speech recognition systems. Could be a shared project between an IT and an engineering student in collaboration to develop the system

 

9. Data Acquisition System

 
This project is an industry related project being proposed by Methode Electronics (Malta). The system uses servomotors or linear motors, to measure distances in order to measure mechanical and electrical parameters relating to a product, such as a switch. The whole testing system is under PC control and the student is expected to develop programs in C or C++ to handle the switch, the test jig, and the motors performing the measurements. The project is expected to be developed in house at Methode Electronics (Malta), Mriehel.

Student        Jason Debono

 

10. Real Time Distributed Data System