Search
Now showing items 1-10 of 15
Investigation of the impact of high frequency transmitted speech on speaker recognition
(Stellenbosch : Stellenbosch University, 2002-04)
ENGLISH ABSTRACT: Speaker recognition systems have evolved to a point where near perfect performance can be
obtained under ideal conditions, even if the system must distinguish between a large number
of speakers. Under ...
Phonene-based topic spotting on the switchboard corpus
(Stellenbosch : Stellenbosch University, 2002-04)
ENGLISH ABSTRACT: The field of topic spotting in conversational speech deals with the problem of identifying
"interesting" conversations or speech extracts contained within large volumes of speech
data. Typical applications ...
Analysis and implementation of the speaker adaptation techniques : MAP, MLLR, and MLED
(Stellenbosch : Stellenbosch University, 2002-12)
ENGLISH ABSTRACT: The topic of this thesis is speaker adaptation, whereby speaker-independent speech models
are adapted to more closely match individual speakers by utilising a small amount of
data from the targeted ...
Evaluation of modern large-vocabulary speech recognition techniques and their implementation
(Stellenbosch : University of Stellenbosch, 2009-03)
In this thesis we studied large-vocabulary continuous speech recognition.
We considered the components necessary to realise a large-vocabulary speech
recogniser and how systems such as Sphinx and HTK solved the ...
Automatic classification of spoken South African English variants using a transcription-less speech recognition approach
(Stellenbosch : Stellenbosch University, 2004-03)
ENGLISH ABSTRACT: We present the development of a pattern recognition system which is capable of classifying
different Spoken Variants (SVs) of South African English (SAE) using a transcriptionless
speech recognition ...
The design of a high-performance, floating-point embedded system for speech recognition and audio research purposes
(Stellenbosch : Stellenbosch University, 2008-03)
This thesis describes the design of a high performance, floating-point, standalone embedded
system that is appropriate for speech and audio processing purposes.
The system successfully employs the Analog Devices TigerSHARC ...
A comparison of Gaussian mixture variants with application to automatic phoneme recognition
(Stellenbosch : University of Stellenbosch, 2007-12)
The diagonal covariance Gaussian Probability Density Function (PDF) has been a very
popular choice as the base PDF for Automatic Speech Recognition (ASR) systems. The
only choices thus far have been between the spherical, ...
Automatic alignment and error detection for phonetic transcriptions in the African speech technology project databases
(Stellenbosch : University of Stellenbosch, 2006-03)
The African Speech Technology (AST) project ran from 2000 to 2004 and involved collecting speech data for five South African languages, transcribing the data and building automatic speech recognition systems in these ...
Automatic syllabification of untranscribed speech
(Stellenbosch : Stellenbosch University, 2005-03)
ENGLISH ABSTRACT: The syllable has been proposed as a unit of automatic speech recognition due to its
strong links with human speech production and perception. Recently, it has been proved
that incorporating information ...
Fast accurate diphone-based phoneme recognition
(Stellenbosch : University of Stellenbosch, 2009-03)
Statistical speech recognition systems typically utilise a set of statistical models of subword
units based on the set of phonemes in a target language. However, in continuous
speech it is important to consider co-articulation ...