Isolated word recognition using MFCC-LPC-VQ and Hidden Markov Model

Speech recognition has been an integral part of human life acting as one of the five senses of human body, because of which application developed on the basis of speech recognition has high degree of acceptance. The analysis of the different steps involved in isolated word recognition using Mel Frequency cepstral coefficients (MFCC), Vector quantization (VQ) and Hidden Markov Model (HMM) is seen here. The simple and efficient approach is used here which can be utilised in embedded systems. After analysing the steps above we realised the process using small programs using MATLAB which is able to do small number of isolated word recognition.The work done here develops a speaker independent isolated word recognizer from the acoustic signals based on a discrete observation Hidden Markov Model (HMM). The study implements the HMM based isolated word recognizer in three steps- Speech Segmentation,Feature extraction and Feature Matching.

Autorentext

Mr. Mahesh N. Patil completed M.Tech (Structural Engineering), Mr. Aakash S. Pawar completed M.E. Civil (Infrastructure Engineering and Management) & Mr. Yogesh N. Sonawane completed M.Tech (Structural Engineering). All authors are currently working as assistant professor in RCPIT, Shirpur,Dhule, Maharashtra (India).