1. Connected speech recognition for authentication
Authors : Sheena Christabel Pravin, S.satheesh Kumar
Pages : 303-310
DOI : http://dx.doi.org/10.21172/1.83.045
Keywords : Phonetics, MFCC, HMM, MATLAB, Word Boundary Detection Abstract :In today’s fast world we don't have time to sit and type our complicated alpha-digit codes used for Product key, for Password Security Code (PSC) to access a person’s authenticated details containing unique set of connected alpha-digit. Recognition of spoken alphabets and digits is difficult task in automatic speech recognition due to phonetic similarities among certain group of vocabulary sets. In this paper, knowledge based features are used along with conventional Mel Frequency Cepstral Coefficients (MFCC) to enhance the overall correctness of the PSC recognizer by overcoming phonetic similarity difficulties. HMM (Hidden Markov Model) is used as the statistical classifier which determines the likelihood of every speech sample. In this paper, we achieve speech to text conversion using MATLAB. It extracts and labels the waveform and gives output in the text format. Word Boundary detection followed by HMM based classification results in a PSC recognition accuracy of 83%.
Citing this Journal Article :Sheena Christabel Pravin, S.satheesh Kumar, "Connected speech recognition for authentication", Volume 8 Issue 3 - May 2017, 303-310
Click here to Submit Copyright Takedown Notice for this article.