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.

Room-temperature continuous-wave operation of InAs quantum-wire laser on InP(001) substrate

A self-assembled quantum-wire laser structure was grown by solid-source molecular beam epitaxy in an InAlGaAs-InAlAs matrix oil InP(001) substrate. Ridge-waveguide lasers were fabricated and demonstrated to operate at a heatsink temperature tip to 330 K in continuous-wave (CW) mode. The emission wavelength of the lasers with 5 mm-long cavity was 1.713 mu m at room temperature in CW mode. The temperature stability of the devices was analysed and the characteristic temperature was found to be 47 K in the mnge of 220-320 K.

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.

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.

crossmodal error correction of continuous handwriting recognition by speech

In recognition-based user interface, users’ satisfaction is determined not only by recognition accuracy but also by effort to correct recognition errors. In this paper, we introduce a crossmodal error correction technique, which allows users to correct errors of Chinese handwriting recognition by speech. The focus of the paper is a multimodal fusion algorithm supporting the crossmodal error correction. By fusing handwriting and speech recognition, the algorithm can correct errors in both character extraction and recognition of handwriting. The experimental result indicates that the algorithm is effective and efficient. Moreover, the evaluation also shows the correction technique can help users to correct errors in handwriting recognition more efficiently than the other two error correction techniques.