Repository logo
 

Theses and dissertations (Engineering and Built Environment)

Permanent URI for this collectionhttp://ir-dev.dut.ac.za/handle/10321/10

Browse

Has files: YesSubject: search.filters.subject.Signal processing--Digital techniques

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Automatic speech recognition of the isiZulu language
    (2021-12-01) Shezi Nokwanda; Reddy, Seren
    A key component of artificial intelligence is human-to-machine communication. Such communication has been realised through virtual assistants such as Apple's Siri, Google's Now, Amazon's Alexa, etc. This technology is made possible through Automatic Speech Recognition (ASR). Only in recent years have the previously marginalised or developing countries started researching ASR for their indigenous languages. This research focuses on ASR in isiZulu, which is one of South Africa's most spoken indigenous language. The research involves two main fields of study i.e., digital signal processing (DSP) and machine learning (ML). DSP was applied in word boundary estimation and feature extraction. Machine learning was used to convert the work boundary estimation and feature extraction. Machine learning was used to convert the word boundary estimation problem to a classification problem as well as for word recognition. Word boundary estimation achieved an accuracy of 68.4%, which is on par with the current research. the Mel-frequency cepstrum coefficient (MFCC) was used for the feature extraction of the speech and deep neural networks were chosen for the ML component. For the detection and classification of a word in a sentence, the trained neural network was tested by considering the effect of including and excluding explicit boundaries on the overall recognition. Word recognition accuracy with manually demarcated boundaries was 78.18%. In sentence recognition accuracy achieved without demarcated boundaries was 17.74% while a 23.28% accuracy was achieved without demarcated using classification. While in-sentence recognition accuracy for the two algorithms was both low, the accurately recognised words were determined by different heuristics. Other factors, such as the complex differences between the indigenous isiZulu languages and other more commonly spoken languages, are also highlighted and further research avenues are proposed.
  • Thumbnail Image
    Item
    The design of digital signal processing electronics for a steel wire ropetesting instrument
    (1989) Nair, Dhavan; Scott, R. W.
    This thesis describes the design work undertaken at the Anglo American Electronics Laboratory to implement an electronic instrumentation system to evaluate the condition of steel wire ropes.
  • Thumbnail Image
    Item
    Development of a two element correlating radio telescope interferometer
    (2015) Callaghan, David James; MacPherson, Stuart David; Sokoya, O.
    A two element correlating radio telescope interferometer is the fundamental building block of modern radio telescope aperture synthesis arrays. Early radio telescopes consisted of a single antenna, usually a dish antenna. Larger and larger antennas were constructed in order to improve the resolution of the measurement of the direction and extent of radio frequency radiation coming from the sky. Telescope resolution is fundamentally limited by the ratio of the telescope aperture to the wavelength of the received radiation. For single element radio telescopes to approach the resolution of their optical telescope counterparts, they would need to be impractically large. Mathematical analysis of correlating two element radio telescope interferometers shows that very large aperture radio telescopes can be synthesized from a number of two element interferometers. An array of two element correlating radio telescope interferometers can be used to produce a synthesized aperture equal to the largest distance between two receiving antennas in the array. Telescope arrays thus enable very high resolution since the angular resolution of a telescope is proportional to the wavelength of the received signal divided by the aperture diameter. A spread of separation distances between antenna pairs is required to produce a complete image of the radiating sources in the field of view. Modern digital signal processing techniques can be used to provide cost effective performance and flexibility in two element correlating radio telescope interferometer design. The aim of this research project was to design and construct a two element correlating radio telescope interferometer using modern digital signal processing techniques and hardware. The relevant theory has been investigated together with suitable hardware and software platforms and tools used to produce such a system. The two element correlating radio telescope interferometer produced, will be used as a platform for further investigative research into its design, performance and application. The outcome of this research project was the successful completion of a working two element correlating radio telescope interferometer. The development process has been analysed and carefully documented. Some fringe measurements for a simple single frequency radiating point source have been taken and these measurements have been analysed according to theoretical expectation. Potential for further research, using the two element correlating radio telescope interferometer produced, has been identified and discussed.
  • Thumbnail Image
    Item
    Object motion detection, extraction and filtering using ANN ensembles
    (2009) Moorgas, Kevin Emanuel; Govender, Poobalan
    This research is devoted to the development of an intelligent image motion detection system based on artificial neural networks (ANN’s). Object motion detection, non-stationary image isolation and extraction, and image filtering is investigated, with the intention of developing a system that will overcome some of the shortcomings associated with the performance of conventional motion detection systems. Motion detection and image extraction finds popular application in medical imagery and engineering based diagnostics systems. Conventional image processing systems utilise Digital Signal Processing (DSP) to perform the non-stationary image motion detection function. Aliasing and filtering are problematic processes in DSP based image processing systems. The proposed ANN motion detection system overcomes some of these shortcomings. The study compares the performance of conventional DSP systems to that of the proposed ANN based system. The excellent noise immunity, ability to generalise and robustness of the ANN system is exploited in the design of the motion detection system. The ANN’s are arranged as ensembles in order to improve the computation time of the proposed motion detection system. A hybrid system comprising DSP and ANN ensembles is also proposed in the study. The hybrid system exploits the positive characteristics of DSP and ANN’s within a single system. The performance of the pure ANN system and the hybrid system is compared to that of DSP systems, using the image’s signal-to-noise ratio and computation times as a basis for comparison.