Research on continuous speech recognition with small vocabulary based on biomimetic pattern recognition

Based on biomimetic pattern recognition theory, we proposed a novel speaker-independent continuous speech keyword-spotting algorithm. Without endpoint detection and division, we can get the minimum distance curve between continuous speech samples and every keyword-training net through the dynamic searching to the feature-extracted continuous speech. Then we can count the number of the keywords by investigating the vale-value and the numbers of the vales in the curve. Experiments of small vocabulary continuous speech with various speaking rate have got good recognition results and proved the validity of the algorithm.

Cognitive models in biomimetic pattern cognition

We describe a new model which is based on the concept of cognizing theory. The method identifies subsets of the data which are embedded in arbitrary oriented lower dimensional space. We definite k-mean covering, and study its property. Covering subsets of points are repeatedly sampled to construct trial geometry space of various dimensions. The sampling corresponding to the feature space having the best cognition ability between a mode near zero and the rest is selected and the data points are partitioned on the basis of the best cognition ability. The repeated sampling then continues recursively on each block of the data. We propose this algorithm based on cognition models. The experimental results for face recognition demonstrate that the correct rejection rate of the test samples excluded in the classes of training samples is very high and effective.

Keyword spotting system based on biomimetic pattern recognition

The mandarin keyword spotting system was investigated, and a new approach was proposed based on the principle of homology continuity and point location analysis in high-dimensional space geometry theory which are both parts of biomimetic pattern recognition theory. This approach constructed a hyper-polyhedron with sample points in the training set and calculated the distance between each test point and the hyper-polyhedron. The classification resulted from the value of those distances. The approach was tested by a speech database which was created by ourselves. The performance was compared with the classic HMM approach and the results show that the new approach is much better than HMM approach when the training data is not sufficient.

Structural characterization of AlGaN/GaN superlattices by x-ray diffraction and Rutherford backscattering

We report on structural characterization of AlGaN/GaN superlattices grown on sapphire. The superlattice formation is evidenced by high-resolution x-ray diffraction and transmission electron microscopy. The high resolution x-ray diffraction spectra exhibit a pattern of satellite peaks. The in-plane lattice constants of the superlattices indicate the coherent growth of the AlGaN layer onto GaN. The average At composition in the superlattices is determined to be 0.08 by Rutherford backscattering spectroscopy. The average parallel and perpendicular elastic strains for the SLs are determined to be (e(parallel to)) = +0.25% and (e(perpendicular to)) = -0.17%. (c) 2006 Elsevier Ltd. All rights reserved.

Study on text-dependent speaker recognition based on Biomimetic Pattern Recognition

We studied the application of Biomimetic Pattern Recognition to speaker recognition. A speaker recognition neural network using network matching degree as criterion is proposed. It has been used in the system of text-dependent speaker recognition. Experimental results show that good effect could be obtained even with lesser samples. Furthermore, the misrecognition caused by untrained speakers occurring in testing could be controlled effectively. In addition, the basic idea "cognition" of Biomimetic Pattern Recognition results in no requirement of retraining the old system for enrolling new speakers.

A speaker-independent continuous speech recognition system using biomimetic pattern recognition

In speaker-independent speech recognition, the disadvantage of the most diffused technology (HMMs, or Hidden Markov models) is not only the need of many more training samples, but also long train time requirement. This paper describes the use of Biomimetic pattern recognition (BPR) in recognizing some mandarin continuous speech in a speaker-independent manner. A speech database was developed for the course of study. The vocabulary of the database consists of 15 Chinese dish's names, the length of each name is 4 Chinese words. Neural networks (NNs) based on Multi-weight neuron (MWN) model are used to train and recognize the speech sounds. The number of MWN was investigated to achieve the optimal performance of the NNs-based BPR. This system, which is based on BPR and can carry out real time recognition reaches a recognition rate of 98.14% for the first option and 99.81% for the first two options to the persons from different provinces of China speaking common Chinese speech. Experiments were also carried on to evaluate Continuous density hidden Markov models (CDHMM), Dynamic time warping (DTW) and BPR for speech recognition. The Experiment results show that BPR outperforms CDHMM and DTW especially in the cases of samples of a finite size.

MQW electroabsorption modulator-integrated DFB laser modules for high-speed transmission

Details of the design, fabrication and testing of a strained InGaAsP/InGaAsP multiple quantum well (MQW) electroabsorption modulator (EAM) monolithically integrated with a DFB laser by ultra-low-pressure selective area growth (SAG) are presented. The method greatly simplifies the integration process. A study of the controllability of band-gap energy by SAG has been performed. After being completely packaged in a seven-pin butterfly compact module, the device successfully performs 10 Gb s(-1) nonreturn to zero (NRZ) operation on uncompensated transmission span >53 km in a standard fibre with a 8.7 dB dynamic extinction ratio. A receiver sensitivity of -18.9 dBm at a bit error rate (BER) of 10(-10) is confirmed. 10 GHz short pulse trains with 15.3 ps pulsewidth have also been generated.

Monolithic integration of electroabsorption modulator and DFB laser for 10-Gb/s transmission

A strained InGaAsP-InP multiple-quantum-well DFB laser monolithically integrated with electroabsorption modulator by ultra-low-pressure (22 mbar) selective-area-growth is presented. The integrated chip exhibits superior characteristics, such as low threshold current of 19 mA, single-mode operation around 1550 nm range with side-mode suppression ratio over 40 dB, and larger than 16 dB extinction ratio when coupled into a single-mode fiber. More than 10 GHz modulation bandwidth is also achieved. After packaged in a compact module, the device successfully performs 10-Gb/s NRZ transmission experiments through 53.3 km of standard fiber with 8.7 dB dynamic extinction ratio. A receiver sensitivity of -18.9 dBm at bit-error-rate of 10(-1)0 is confirmed. (c) 2005 Elsevier B.V. All rights reserved.

Electroabsoorption-modulated laser light-source module using selective area growth for 10 Gb/s transmission

In this work, a novel light source of strained InGaAsP/InGaAsP MQW EAM monolithically integrated with DFB laser is fabricated by ultra-low-pressure (22 x 10(2) Pa) selective area growth ( SAG) MOCVD technique. Superior device performances have been obtained, sue h as low threshold current of 19 mA, output light power of about 7 mW, and over 16 dB extinction ratio at 5 V applied voltage when coupled into a single mode fiber. Over 10 GHz 3 dB bandwidth in EAM part is developed with a driving voltage of 3 V. After the chip is packaged into a 7-pin butterfly compact module, 10-Gb/s NRZ transmission experiments are successfully performed in standard fiber. A clearly-open eye diagram is achieved in the module output with over 8.3 dB dynamic extinction ratio. Power penalty less than 1.5 dB has been obtained after transmission through 53.3 km of standard fiber, which demonstrates that high-speed, low chirp EAM/DFB integrated light source can be obtained by ultra-low-pressure (22 x 102 Pa) SAG method.

High-performance EML grown on taper-masked pattern substrates by ultra-low-pressure MOCVD

A novel in-plane bandgap energy controlling technique by ultra-low pressure (22 mbar) selective area growth (SAG) has been developed. To our knowledge, this is the lowest pressure condition during SAG process ever reported. In this work, high crystalline quality InGaAsP-InP MQWs with a photoluminescence (PL) full-width at half-maximum (FWHM) of less than 35meV are selectively grown on mask-patterned planar InP substrates by ultra-low pressure (22 mbar) metal-organic chemical vapor deposition (MOCVD). In order to study the uniformity of the MQWs grown in the selective area, novel tapered masks are designed and used. Through optimizing growth conditions, a wide wavelength shift of over 80 nm with a rather small mask width variation (0-30 mu m) is obtained. The mechanism of ultra-low pressure SAG is detailed by analyzing the effect of various mask designs and quantum well widths. This powerful technique is then applied to fabricate an electroabsorption-modulated laser (EML). Superior device characteristics are achieved, such as a low threshold current of 19mA and an output power of 7mW. (c) 2005 Elsevier B.V. All rights reserved.

A new development on ANN in China - Biomimetic pattern recognition and multi weight vector neurons

A new model of pattern recognition principles-Biomimetic Pattern Recognition, which is based on "matter cognition" instead of "matter classification", has been proposed. As a important means realizing Biomimetic Pattern Recognition, the mathematical model and analyzing method of ANN get breakthrough: a novel all-purpose mathematical model has been advanced, which can simulate all kinds of neuron architecture, including RBF and BP models. As the same time this model has been realized using hardware; the high-dimension space geometry method, a new means to analyzing ANN, has been researched.

Structural properties and Raman measurement of AlN films grown on Si (111) by NH3-GSMBE

Epitaxial growth of AlN has been performed by molecular beam epitaxy (MBE) with ammonia. The structural properties of materials were studied by cross-sectional transmission electron microscopy (TEM), X-ray diffraction (XRD), and atomic force microscopy (AFM). XRD and TEM diffraction pattern confirm the AlN is single crystalline 2H-polytype with the epitaxial relationship of (0001)AlNparallel to(111)Si, [11 (2) over bar0](AlN)parallel to[110](Si), [10 (1) over bar0](AlN)parallel to[11 (2) over bar](Si). Micro-Raman scattering measurement shows that the E-2 (high) and A(1) (LO) phonon mode shift 9 cm(-1) toward the low frequency, which shows the existence of large tensile strain in the AlN films. Furthermore, the appearance of forbidden A, (TO) mode and its anomalous shift toward high frequency was found and explained. (C) 2002 Elsevier Science B.V. All rights reserved.

Anisotropic radiation pattern from InGaAlP quantum well mesa-like microdisks

To overcome the isotropic directional emission of an ideal circular microdisk, two kinds of cylindrical mesa-like InGaAlP single quantum well (SQW) microdisks emitting at a visible red wavelength of 0.66 mu m have been fabricated. An anisotropic luminescence pattern was revealed by the microscopic fluorescence (FL) image. FL intensity, preferentially enhanced with twofold symmetry, appeared at the circumference of the InGaAlP SQW microdisks. Our results demonstrated that anisotropic radiation can be achieved by geometry shaping of the disks on the top view two-dimensional boundary slightly deformed from circular shape and/or on the side-view cross-section of the circular mesa by wet etching anisotropic undercut. (C) 2000 Elsevier Science Ltd. All rights reserved.

Measurement of the optical transmission modes and losses of the poled guest-host polymer NAEC/PEK-c planar waveguides

The polyetherketone (PEK-c) guest-host polymer planar waveguides doped with (4'-nitro)-3-azo-9-ethyl-carbazole (NAEC) were prepared. The waveguide films were poled by corona-onset poling at elevated temperature (COPET), and the corona poling setup includes a grid voltage making the surface-charge distribution uniform. By using the prism-in coupling method, the dark-line spectrum given by the reflected intensity versus the angle of incidence have been obtained, and the optical transmission losses of mth modes have been measured for the poled polymer waveguides at lambda = 632.8 nm. The measurement result showed that the optical loss of the fundamental mode is less than 0.7 dB cm(-1) for the TE polarization. (C) 2000 Elsevier Science Ltd. All rights reserved.