期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2016
卷号：5
期号：10
页码：18434
DOI：10.15680/IJIRSET.2016.0510047
出版社：S&S Publications
摘要：Speech recognition is an analysis side of the main topics machine speech processing. The synthesis sidemay be called speech production. These two taken together allow computers to cooperate with spoken language. Mystudy specializes in isolated word speech recognition in Gujarati language. Special message recognition, in humans, is1000s of years old. On our planet it would be traced backed millions of years to your dinosaurs. Our topic might farbetter be called automatic speech recognition (ASR). I give a limited survey of MFCC (Mel Frequency CepstralCoefficient). A very simple computer experiment, using MatLab, into isolated word speech recognition is described incertain detail. I experimented with distinctive recognition algorithms and implemented training and testing data withtwo distinct vocabularies. My exercise and testing data was built-up and recorded with both men and female voices.
