A comparative study of various speech recognition techniques.

UKZN ResearchSpace

Show simple item record

dc.contributor.advisor Broadhurst, Anthony D.
dc.creator Pitchers, Richard Charles.
dc.date.accessioned 2012-10-14T15:14:00Z
dc.date.available 2012-10-14T15:14:00Z
dc.date.created 1990
dc.date.issued 1990
dc.identifier.uri http://hdl.handle.net/10413/6896
dc.description Thesis (M.Sc.-Electronic Engineering)-University of Natal, 1990. en
dc.description.abstract Speech recognition systems fall into four categories, depending on whether they are speaker-dependent or independent of speaker population and on whether they are capable of recognizing continuous speech or only isolated words. A study was made of most methods used in speech recognition to date. Four speech recognition techniques for speaker-dependent isolated word applications were then implemented in software on an IBM PC with a minimum of interfacing hardware. These techniques made use of short-time energy and zero-crossing rates, autocorrelation coefficients, linear predictor coefficients and cepstral coefficients. A comparison of their relative performances was made using four test vocabularies that were 10, 30, 60 and 120 words in size. These consisted of 10 digits, 30 and 60 computer terms and lastly 120 airline reservation terms. The performance of any speech recognition system is affected by a number of parameters. The effects of frame length, pre-emphasis, window functions, dynamic time warping and the filter order were also studied experimentally. en
dc.language.iso en en
dc.subject Speech processing systems. en
dc.subject Automatic speech recognition. en
dc.subject Theses--Electronic engineering. en
dc.title A comparative study of various speech recognition techniques. en
dc.type Thesis en

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search UKZN ResearchSpace

Advanced Search


My Account