A Stochastic Analysis on Translating Nam Speech into Normal Speech
B. Vaidianathan1, S. Arul Selvi2, B. Karthik3
1B. Vaidianathan, Research Scholar, Department of ECE, Bharath Institute of Higher Education and Research, Chennai (Tamil Nadu), India.
2Dr. S. Arul Selvi, Associate Professor, Department of ECE, Bharath Institute of Higher Education and Research, Chennai (Tamil Nadu), India.
3Dr. B. Karthik, Associate Professor, Department of ECE, Bharath Institute of Higher Education and Research, Chennai (Tamil Nadu), India.
Manuscript received on 20 February 2019 | Revised Manuscript received on 11 March 2019 | Manuscript Published on 08 June 2019 | PP: 839-842 | Volume-7 Issue-5S4, February 2019 | Retrieval Number: E11700275S419/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: NAM is generally described as a very delicate whispered voice which is been recognized only by NAM microphone, which is generally termed as body conducting microphones. The vocal chord movements is been generally identified by this vocal instrument. In this paper, we have proposed a methodology that actually checks the up and down movements of vocal chords which then generally converts into speech. Generally the hand gesture recognition system is only been used for communication between two humans. It has many problems such as miss communications. To solve this problem only we are proposing a method of NAM to speech conversion to get normal voices. Generally Wavelet examination is used to separate the information generated from the mumble and then classification is done in order to get the corresponding words.
Keywords: Discrete Wavelet Transform, Nam Microphone, Voice Conversion, Threshold, Interference, Speech Recognition.
Scope of the Article: Speech interface; Speech processing