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.

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.

End-pumped continuous-wave passively modelocked Nd : YVO4 laser with low pump power

A simple cw mode-locked solid-state laser, which is end-pumped by a low-power laser diode, was demonstrated by optimizing the laser-mode size inside the gain medium. The optimum ratio between mode and pump spot sizes inside the laser crystal was estimated for a cw mode-locked laser, taking into account the input pump power. Calculation and experiment have shown that the optimum ratio was about 3 when the pump power is 2 W, which is different from the value regularly used in passively mode-locked solid-state lasers. This conclusion is also helpful in increasing the efficiency of high-power ultrashort lasers. (C) 2006 Society of Photo-Optical Instrumentation Engineers.

Continuous speech research based on HyperSausage Neuron

In this paper, we presents HyperSausage Neuron based on the High-Dimension Space(HDS), and proposes a new algorithm for speaker independent continuous digit speech recognition. At last, compared to HMM-based method, the recognition rate of HyperSausage Neuron method is higher than that of in HMM-based method.

Size limit and spontaneous emission factor for equilateral triangle semiconductor microlasers

The size of equilateral triangle resonator (ETR) needed for confining the fundamental mode is investigated by the total reflection condition of mode light rays and the FDTD numerical simulation. The confinement of the TM modes can be explained by the total reflection of mode light rays, and the confinement of the TE modes requires a larger ETR than the TM modes, which may be caused by excess scattering or radiation loss for the TE modes. With the multilayer staircase approximation, it is found that the spontaneous emission factor of the ETR lasers has the same form as that of strip waveguide lasers.

Self-assembled quantum dots, wires and quantum-dot lasers

Molecular beam epitaxy-grown self-assembled In(Ga)As/GaAs and InAs/InAlAs/InP quantum dots (QDs) and quantum wires (QWRs) have been studied. By adjusting growth conditions, surprising alignment. preferential elongation, and pronounced sequential coalescence of dots and wires under specific condition are realized. The lateral ordering of QDs and the vertical anti-correlation of QWRs are theoretically discussed. Room-temperature (RT) continuous-wave (CW) lasing at the wavelength of 960 nm with output power of 3.6 W from both uncoated facets is achieved fi-om vertical coupled InAs/GaAs QDs ensemble. The RT threshold current density is 218 A/cm(2). A RT CW output power of 0.6 W/facet ensures at least 3570 h lasing (only drops 0.83 dB). (C) 2001 Elsevier Science B.V, All rights reserved.

A widely tunable continuous-time LPF for a direct conversion DBS Tuner

A continuous-time 7th-order Butterworth Gm-C low pass filter (LPF) with on-chip automatic tuning circuit has been implemented for a direct conversion DBS tuner in a 0.35um SiGe BiCMOS technology. The filter's -3dB cutoff frequency f(0) can be tuned from 4MHz to 40MHz. A novel translinear transconductor (Gm) cell is used to implement the widely tunable and high linear filter. The filter has -0.5dB passband gain, 28nV/Hz(1/2) input referred noise, -2dBVrms passband IIP3, 24dBVrms stopband IIP3. The I/Q LPFs with the tuning circuit draw 16mA (with f(0)=20MHz) from 3.3 V supply, and occupy an area of 0.45 mm(2).

Continuous-wave electrically injected InP/GaInAsP equilateral-triangle-resonator lasers

Equilateral-triangle-resonator (ETR) microlasers with an output waveguide connected to one of the vertices of the ETR are fabricated using standard photolithography and inductively-coupled-plasma etching techniques. Continuous-wave electrically injected 1550 nm ETR laser with side length ranged from 15 to 30 tm are realized at room temperature.

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.

Continuous speech research based on HyperSausage Neuron

In this paper, we presents HyperSausage Neuron based on the High-Dimension Space(HDS), and proposes a new algorithm for speaker independent continuous digit speech recognition. At last, compared to HMM-based method, the recognition rate of HyperSausage Neuron method is higher than that of in HMM-based method.

Period Continuous Tuning of an Efficient Mid-Infrared Optical Parametric Oscillator Based on a Fan-out Periodically Poled MgO-Doped Lithium Niobate

We report a period continuously tunable, efficient, mid-infrared optical parametric oscillator (OPO) based on a fan-out periodically poled MgO-doped congruent lithium niobate (PPMgLN). The OPO is pumped by a Nd:YAG laser and a maximum idler output average power of 1.65 W at 3.93 mu m is obtained with a pump average power of 10.5 W, corresponding to the conversion efficiency of about 16% from the pump to the idler. The output spectral properties of the OPO with the fan-out crystal are analyzed. The OPO is continuously tuned over 3.78-4.58 mu m (idler) when fan-out periods are changed from 27.0 to 29.4 mu m. Compared with temperature tuning, fan-out period continuous tuning has faster tuning rate and wider tuning range.

The Category-Theoretic Solution of Recursive Domain Equations

Recursive specifications of domains plays a crucial role in denotational semantics as developed by Scott and Strachey and their followers. The purpose of the present paper is to set up a categorical framework in which the known techniques for solving these equations find a natural place. The idea is to follow the well-known analogy between partial orders and categories, generalizing from least fixed-points of continuous functions over cpos to initial ones of continuous functors over $\omega $-categories. To apply these general ideas we introduce Wand's ${\bf O}$-categories where the morphism-sets have a partial order structure and which include almost all the categories occurring in semantics. The idea is to find solutions in a derived category of embeddings and we give order-theoretic conditions which are easy to verify and which imply the needed categorical ones. The main tool is a very general form of the limit-colimit coincidence remarked by Scott. In the concluding section we outline how compatibility considerations are to be included in the framework. A future paper will show how Scott's universal domain method can be included too.