ICA which is generally used for blind source separation
problem has been tested for feature extraction in Speech recognition
system to replace the phoneme based approach of MFCC. Applying
the Cepstral coefficients generated to ICA as preprocessing has
developed a new signal processing approach. This gives much better
results against MFCC and ICA separately, both for word and speaker
recognition. The mixing matrix A is different before and after MFCC
as expected. As Mel is a nonlinear scale. However, cepstrals
generated from Linear Predictive Coefficient being independent
prove to be the right candidate for ICA. Matlab is the tool used for
all comparisons. The database used is samples of ISOLET.
[1] Davis S. and P.Mermelstein," Comparison of parametric
representations for monosyllabic word recognition in
continuously spoken sentences," IEEE Trans. ASSP
28,pp.357-366,1980.
[2] Joseph W. Picone, "Signal Modeling Techniques in speech
recognition," Proceedings of the IEEE, vol.81, no.9, pp.1215-
1247,1993.
[3] Jutten C. and Herault, "Blind Separation of Sources, Part
I: An adaptive algorithm based on a neuromimetic
architecture," Signal Process., vol.24, no.1, pp.1-10,1991.
[4] Hyvarinen A., "A family of fixed-point algorithms for
Independent Component Analysis," ICASSP, pp 3917-3920,
1997.
[5] Blaschke and Laurenz Wiskott, "CuBICA: Independent
component analysis by simultaneous third and fourth order
cumulant diagonalization," IEEE Trans. on Signal Processing,
vol.52, no.3, pp.1250-1256,2004.
[6] Hyvarinen A. and Erkki Oja, "Independent Component
Analysis: Algorithms and Applications",
http://www.cis.hut.fi/projects/ica/
[7] Pierre Comon, "Independent Component Analysis, A new
concept?," Signal Processing, 36, pp.287-314,1994.
[8] Lawrence Rabiner & Biing-Hwang Juang, Fundamentals
of Speech Recognition. Pearson Education, 2003.
[9] The software generated for this purpose may be referred
by sending a mail at [email protected].
[10] Kishore S. Trivedi, ÔÇÿProbability and Statistics with
Reliability, Queing & Computer Science Applications-, PHI,
1999.
[1] Davis S. and P.Mermelstein," Comparison of parametric
representations for monosyllabic word recognition in
continuously spoken sentences," IEEE Trans. ASSP
28,pp.357-366,1980.
[2] Joseph W. Picone, "Signal Modeling Techniques in speech
recognition," Proceedings of the IEEE, vol.81, no.9, pp.1215-
1247,1993.
[3] Jutten C. and Herault, "Blind Separation of Sources, Part
I: An adaptive algorithm based on a neuromimetic
architecture," Signal Process., vol.24, no.1, pp.1-10,1991.
[4] Hyvarinen A., "A family of fixed-point algorithms for
Independent Component Analysis," ICASSP, pp 3917-3920,
1997.
[5] Blaschke and Laurenz Wiskott, "CuBICA: Independent
component analysis by simultaneous third and fourth order
cumulant diagonalization," IEEE Trans. on Signal Processing,
vol.52, no.3, pp.1250-1256,2004.
[6] Hyvarinen A. and Erkki Oja, "Independent Component
Analysis: Algorithms and Applications",
http://www.cis.hut.fi/projects/ica/
[7] Pierre Comon, "Independent Component Analysis, A new
concept?," Signal Processing, 36, pp.287-314,1994.
[8] Lawrence Rabiner & Biing-Hwang Juang, Fundamentals
of Speech Recognition. Pearson Education, 2003.
[9] The software generated for this purpose may be referred
by sending a mail at [email protected].
[10] Kishore S. Trivedi, ÔÇÿProbability and Statistics with
Reliability, Queing & Computer Science Applications-, PHI,
1999.
@article{"International Journal of Electrical, Electronic and Communication Sciences:52060", author = "Neeta Awasthy and J.P.Saini and D.S.Chauhan", title = "Spectral Analysis of Speech: A New Technique", abstract = "ICA which is generally used for blind source separation
problem has been tested for feature extraction in Speech recognition
system to replace the phoneme based approach of MFCC. Applying
the Cepstral coefficients generated to ICA as preprocessing has
developed a new signal processing approach. This gives much better
results against MFCC and ICA separately, both for word and speaker
recognition. The mixing matrix A is different before and after MFCC
as expected. As Mel is a nonlinear scale. However, cepstrals
generated from Linear Predictive Coefficient being independent
prove to be the right candidate for ICA. Matlab is the tool used for
all comparisons. The database used is samples of ISOLET.", keywords = "Cepstral Coefficient, Distance measures, Independent
Component Analysis, Linear Predictive Coefficients.", volume = "2", number = "7", pages = "1345-10", }