HMM Based Gujarati Tricky Words Recognition

Image Processing

Many researcher are working to make computer to understand naturally spoken language. For international language like English this technology has grown to a matured level. we present a model which recognize Gujarati spoken by human and convert it into text. The aim is recognition Guajarati tricky words. In this dissertation Work, proposed method extracts by speech using MFCC feature extraction technique and HMM model. The recognizer is work in abundance of three essential structure squares to be specific Feature extraction, Training and Testing(Recognition).The plan proposed here executes the Mel recurrence Cepstral Coefficient(MFCC) with a specific end goal to figure the otherworldly components of the discourse signal. Utilizing HMM (Hidden Markov Model) to perceive discourse test to give fantastic results for secluded words. It comprises of detached words that are isolated by quiets. This proposed system provide high accuracy for Guajarati word.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.