• M Meher Vishal
• Tusar Kanti Mishra
• P Sai Charan Tej
• K Krishna Reddy

The importance of robust voice recognition has rapidly increased in latest years, as the numbers of applications and devices are increasing. This effect is strongly related to the Internet of Things framework, where these concepts are widely used in smart and under developing cities.In Computer Science, Context Awareness refers to the idea that devices and computer connected can both sense and react based on their environment. The use of this system can play a vital role in distinguishing between actual user and normal user so that it can customise the services. Driven by this motivation, in this paper we present a speaker recognition system design to get efficient output in challenging and robust conditions. We proposed this system by embedding a smart pre-processing method based on the features of voice which can efficiently extract features of the voice and detect the user by feature matching by using Gaussian Mixture Model algorithm. Moreover, it can reduce the influence of noise and other factors affecting the classification. Results shown that this system can improve the classification rate for detecting the actual user even in the case of noisy environment.

speaker recognition, smart pre-processing, Gaussian Mixture Model, noise.

"Smart and Robust Speaker Recognition for Context-Aware Applications", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.173-182, April-2019, Available :http://www.jetir.org/papers/JETIRBF06036.pdf

"Smart and Robust Speaker Recognition for Context-Aware Applications", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp173-182, April-2019, Available at : http://www.jetir.org/papers/JETIRBF06036.pdf