Continuous speech recognition based on ICA and geometrical learning

We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.

Immune condition of Apostichopus japonicus during aestivation

Aestivation is an indispensable state in the life history of sea cucumbers, Apostichopus japonicus. The immune characteristics of the coelomic fluid of A. japonicus, were investigated during aestivation. Samples were collected between July and November 2006 from a coastal pond located off the Yellow Sea in Jiaonan, Shandong Province, China. The total coelomocytes counts (TCC), total superoxide dismutase (T-SOD), catalase (CAT), myeloperoxidase (MPO), and lysozyme (IZM) in the coelomic fluid were measured. The activities of catecholamines, [adrenaline (AD), noradrenaline (NA), and dopamine (DOP)] were estimated. TCC decreased from July to September, indicating weakness of the cellular immune activity at that time. Activities of SOD, CAT, MPO, and LZM changed significantly from July to October. Catecholamines AD and NA in coelomic fluid were significantly higher on August 21 and November 27. There was no significant variation in DOP during the sampling period. Thus, immune characters in coelomic fluid of A. japonicus changed significantly during aestivation. Water temperature was significantly and negatively correlated with TCC, and salinity was significantly and positively correlated with AD and NA. The mechanism of aestivation in A. japonicus is complex and might not be attributed only to environmental changes, such as temperature and salinity, as shown in previous studies. (C) 2008 Elsevier B.V. All rights reserved.