Current Trends in Signal Processing
Performance Analysis of Speech Performance Analysis of Speech Recognition using Advanced Algorithm
Abstract
In this paper, the authors have worked on a speech processing technique wherein they took audio speech as input signal from user and by recognition process, they perceived recorded word. Specifically, the authors concentrated on the amplitude and zero cross of speech signal, and two of the most important and useful terms, namely MFCC and Mahalanobis distance, for the purpose of getting an efficient outcome. The authors evaluated the proposed method with some quality matrices of different speech signals and based on the results they concluded that the proposed method provides accurate process of speech recognition against various models for comparing speech processing.References (7)
- Sahidullah Md, Saha Goutam. Design, Analysis and Experimental Evaluation of Block Based Transformation in MFCC Computation for Speaker Recognition. Speech Communicat ion 54 : May 2012; http://www.sciencedirect.com/ science/article/pii/S0167639311001622.
- Design of a Speaker Recognition Code using MATLAB - E. Darren Ellis, of Computer and Electrical Engineering – University of Tennessee, Knoxville, Tennessee 37996 (Submit ted: 09 May 2001)
- Davis S , Merlmestein P. Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Sentences . IEEE Trans. on ASSP, Aug 1980; 357-366p.
- www.cic.unb.br/~lamar/te073/Aulas/mfcc. pdf
- Min Xu et al. HMM -Based Audio Keyword Generation (http://books.google.com /books?id=Ijdp9UWb5ZYC&pg=PA569& dq=Mel-frequency-cepstrum). In Kiyoharu Ai-zawa, Yuichi Nakamura, Shin'ichi Satoh (Eds). Advances in Multimedia Information Process ing - PCM 2004: 5th Pacific Rim Conference on Multimedia. Springer. 2004. ISBN3-540-23985-5. http://books.google.com/books?id=Ijdp9U Wb5ZYC&pg=PA569&dq=Mel- frequency-cepstrum.
- www.cs.dartmouth.edu/~dwagn/aiproj/spe ech.html
- clasiion.sicyon.com/References/M_distanc e.pdf