论文信息 - A Common Feature Representation for speech Frames and Image Contours

A Common Feature Representation for speech Frames and Image Contours

The technique of independent component analysis (ICA) in Fourier space is pro- posed for the detection of base functions, that can be applied both in speech cod- ing and contour-based shape description in digital images. Our aim is to compare our coding scheme with the Mel cepstrum features of speech and the complex contour Fourier features of image contours. The basic advantage of ICA-based features is that they adapt to the available learning samples.

Wlodzimierz Kasprzak | Adam F. Okazaki | Robert Seta | Włodzimierz Kasprzak | Robert Seta

[1] Chengjun Liu,et al. Independent component analysis of Gabor features for face recognition , 2003, IEEE Trans. Neural Networks.

[2] Takio Kurita,et al. Complex Autoregressive Model for Shape Recognition , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[3] Jean-Claude Junqua,et al. Robustness in Automatic Speech Recognition , 1996 .

[4] Terrence J. Sejnowski,et al. The “independent components” of natural scenes are edge filters , 1997, Vision Research.

[5] Biing-Hwang Juang,et al. Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[6] E. Oja,et al. Independent Component Analysis , 2013 .

[7] Heinrich Niemann. Pattern Analysis and Understanding , 1990 .

[8] Justinian P. Rosca,et al. CEPSTRUM-LIKE ICA REPRESENTATIONS FOR TEXT INDEPENDENT SPEAKER RECOGNITION , 2003 .

[9] Andrzej Cichocki,et al. Adaptive blind signal and image processing , 2002 .

[10] Matti Pietikäinen,et al. An Experimental Comparison of Autoregressive and Fourier-Based Descriptors in 2D Shape Classification , 1995, IEEE Trans. Pattern Anal. Mach. Intell..