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. 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.
This area is of high topical interest because of the
move towards direct speech machine - human interface
2. 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.
3. Speech Recognition in Noisy Background
This project is a sequel to last year's
project. 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.
4. 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
5. Acoustic Modelling
The continuation of a project started this year on acoustic
modelling. A basic program model has been developed and it is intended to
continue the development. Acoustic modelling implies the calculation of parameters
based on different models and there use to obtain the response at a receiver
based in a room. In this way room acoustics can be modelled prior to building.
Particularly in this area there can be subsets of work including: (i) A formal
analysis of the acoustic properties of Maltese building materials. This could
also require input from the Architecture Department, with whom there can
be collaboration on this. (ii) The building of a head auralisation model
to simulate the binaural model of hearing as opposed to the omnidirectional
model of reception.