Evaluation of Mel and Gammatone Filter Banks Used For Spectral Analysis in Comparison With the Direct Use of Fft
Saimir Tola1, Alfred Daci2, Gentian Zavalani3
1Saimir Tola, Department of Mathematical Engineering, Faculty of Mathematical and Physic Engendering, Polytechnic University of Tirana.
2Alfred Daci, Department of Mathematical Engineering, Faculty of Mathematical and Physic Engendering, Polytechnic University of Tirana.
3Gentian Zavalani, Department of Mathematical Engineering, Faculty of Mathematical and Physic Engendering, Polytechnic University of Tirana.
Manuscript received on 08 July 2019 | Revised Manuscript received on 18 August 2019 | Manuscript Published on 27 August 2019 | PP: 949-953 | Volume-8 Issue-2S4 July 2019 | Retrieval Number: B11880782S419/2019©BEIESP | DOI: 10.35940/ijrte.B1188.0782S419
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: This paper analyses the development of Automatic Speech Recognition systems in relation to the varied types of spectral analysis methods used. A critical evaluation of Mel and Gammatone filter banks used for spectral analysis in comparison with the direct use of FFT spectral values is considered. Research was based on understanding the effectiveness of existing Automatic Speech Recognition systems are specifically focused on Mel and Gammatone filter banks in comparison with FFT spectral values.
Keywords: Automatic Speech Recognition (ASR), Mel, Gammatone, Fast Furier Transformation (FFT).
Scope of the Article: Cryptography and Applied Mathematics