Performance analysis of voice activity detection algorithm for robust speech recognition system under different noisy environment

Abstract

This study evaluates performance of objective measures in terms of predicting quality of noisy input speech signal usingvoice activity detection (VAD). Implementation process includes a speech-to-text system using isolated word recognition with avocabulary of 10 words (digits 0-9) and statistical modeling (Hidden Markov Model - HMM) for machine speech recognition. Intraining period, uttered digits were recorded using 8-bit pulse code modulation (PCM) with a sampling rate of 8 KHz and save asa wave format file using sound recorder software. HMM performs speech analysis using linear predictive coding (LPC) methodof degree. For a given word in vocabulary, system builds an HMM model and trains model during training phase. Training stepsfrom VAD to HMM model building are performed using PC-based Matlab programs. Current framework uses automatic speechrecognition (ASR) with HMM based classification and noise language modeling to achieve effective noise knowledge estimation.