Title :
The second-order derivatives of MFCC for improving spoken Arabic digits recognition using Tree distributions approximation model and HMMs
Author :
Hammami, Nacereddine ; Bedda, Mouldi ; Nadir, Farah
Author_Institution :
Lab. LabGed, Univ. Badji Mokhtar Annaba, Annaba, Algeria
Abstract :
Mel Frequency Cepstral Coefficients (MFCCs) are the most popularly used speech features in many speech and speaker recognition applications. In this paper, we study the effect of the second-order derivatives of MFCC on the recognition of the Spoken Arabic digits. The system was developed using the Hidden Markov Models (HMMs) and Tree distribution approximation model. Experimentally it has been shown that, the second-order derivatives of MFCC parameters compared to the MFCC yield improved rates of 4.60% for CHMM. We were able to reach an overall recognition accuracy of 98.41%, which is satisfactory compared to previous work on spoken Arabic digits speech recognition.
Keywords :
approximation theory; cepstral analysis; feature extraction; hidden Markov models; natural language processing; speaker recognition; trees (mathematics); HMM; MFCC; Mel frequency cepstral coefficients; hidden Markov models; second-order derivatives; speaker recognition applications; speech features; speech recognition applications; spoken Arabic digits recognition; tree distributions approximation model; Accuracy; Feature extraction; Hidden Markov models; Mel frequency cepstral coefficient; Speech; Speech recognition; Vectors; Arabic Speech recognition; Cross validation; Hidden Markov Models; Mel Frequency Cepstral Coefficients; Spoken Arabic Digits; Tree distribution approximation;
Conference_Titel :
Communications and Information Technology (ICCIT), 2012 International Conference on
Conference_Location :
Hammamet
Print_ISBN :
978-1-4673-1949-2
DOI :
10.1109/ICCITechnol.2012.6285769
