International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 92 - Number 15 |
Year of Publication: 2014 |
Authors: Taabish Gulzar, Anand Singh, Sandip Vijay |
10.5120/16082-5106 |
Taabish Gulzar, Anand Singh, Sandip Vijay . An Improved Endpoint Detection Algorithm using Bit Wise Approach for Isolated, Spoken Paired and Hindi Hybrid Paired Words. International Journal of Computer Applications. 92, 15 ( April 2014), 1-12. DOI=10.5120/16082-5106
Silence removal and endpoint detection using preset threshold values have already been used for locating the endpoints of an utterance. This paper presents a survey of bit by bit basis method for detecting the accurate endpoints of Isolated, Spoken Paired and Spoken Hindi Hybrid Paired words. Various parameters such as Number of samples, Time duration, Root Mean Square value and Mean Power (Intensity) in air are analyzed. The experiment results show that the proposed algorithm reduces the computational complexity.