Title :
Fuzzy Logic vs. HMM for phoneme recognition
Author :
Ben Fredj, Ines ; Ouni, Kais
Author_Institution :
Higher Sch. of Technol. & Comput. Sci., Carthage Univ., Tunis, Tunisia
Abstract :
We report on a comparison of fuzzy and HMM phoneme recognizers of data Timit corpus. We aimed to check an optimal number of signal cepstral coefficients for both a1pproaches. For this purpose, we used different parameterization techniques such as MFCC, LPCC and PLP. Also, coefficient numbers has been varied from 12 to 39 including first and second derivatives and signal energy to introduce signal temporal variation. Results showed that an appropriate number of acoustic parameters lead to an extensive performance recognition for both systems.
Keywords :
fuzzy logic; hidden Markov models; speech recognition; HMM; LPCC parameterization techniques; MFCC parameterization techniques; PLP parameterization techniques; acoustic parameters; data Timit corpus; fuzzy logic; phoneme recognition; signal cepstral coefficients; signal energy; signal temporal variation; Analytical models; Markov processes; Mel frequency cepstral coefficient; Fuzzy Logic; HMM; LPCC; MFCC; PLP; Timit;
Conference_Titel :
Electrical Sciences and Technologies in Maghreb (CISTEM), 2014 International Conference on
DOI :
10.1109/CISTEM.2014.7076913
