Vowel-Plosive of English Word Recognition using HMM
This paper discusses a speech recognition based on spoken English words formed by vowel, diphthong and plosive and it has been developed and experimented for single speaker.
The success rate of recognition of individually uttered words in experiments is excellent and has reached about 98.86 %. The miss rate of about 1.14% was almost only because of false acceptance. In phonemes classification on an average we have reached 85% and miss classification rate was 15%. We have successfully tested all the words formed by vowel followed by vowel-plosive or plosive-vowels or diphthong-plosive and reached high success rate in recognition of the words. All computations are performed in MATLAB and PRAAT software.
Keywords: Speech Production and Speech Analysis, frequency, Acoustic-phonetic.
Download Full-Text
ABOUT THE AUTHOR
Hemakumar G
I Hemakumar G. B.Sc, M.Sc, M.Phil. I am having 7 years’ teaching experience and 3 years of research experience. I am working for UGC Sponsored minor research project and My interest areas of research are Automatic Speech Recognition, Pattern Recognition and Digital Signal Processing.
Hemakumar G
I Hemakumar G. B.Sc, M.Sc, M.Phil. I am having 7 years’ teaching experience and 3 years of research experience. I am working for UGC Sponsored minor research project and My interest areas of research are Automatic Speech Recognition, Pattern Recognition and Digital Signal Processing.