Paper Details

Automatic Speech Recognition has been an active research topic for more than four decades. With theadvent of digital computing and signal processing, the problem of speech recognition was clearly posed and thoroughlystudied .These developments were complemented with an increased awareness of the advantages of conversationalsystems. The goal of Automatic Speech Recognition is to develop techniques and systems that enable computers to acceptspeech input. The speech recognition problem may be interpreted as speech to text conversion problem. Since the early80’s,compact implementations of accurate, real-time speech recognizers have found wide spread applications, whichincludes voice activated transcription, simplified man machine communication, aids for hearing impaired individualsand the physically disabled telephone assistance and other man-machine interface tasks. The aim of this work is todevelop a speech recognition (SR) system based on Vector Quantization (VQ) approach. This system receives speechinputs from users, analyzes the speech inputs, searches and matches the input speech with the pre-recorded and storedspeeches in the trained database or codebook. First the feature extraction from the speech signal is done by aparameterization of the wave formed signal into relevant feature vectors by Mel Frequency Cepstral Coefficients (MFCC) algorithm and Modified MFCC .This parametric form is then used by the recognition system both in training the modelsand testing.

Boda Aruna, D Srinivas, Prakash Nakirekanti, Ravi Boda, “Modified MFCC Algorithm for Speech Recognition”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 5, Issue 2, pp. 51-55, February 2018.