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.

Method for detecting concurrence without the structural physical approximation by local operations and classical communication

We present a modified method for detecting the concurrence in an arbitrary two-qubit quantum state rho(AB) with local operations and classical communication. In this method, it is not necessary for the two observers to prepare the quantum state rho(AB) by the structural physical approximation. Their main task is to measure four specific functions via two local quantum networks. With these functions they can determine the concurrence and then the entanglement of formation.

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.

Investigation progress on key photonic integration for application in optical communication network

Proceeding from the consideration of the demands from the functional architecture of high speed, high capacity optical communication network, this paper points out that photonic integrated devices, including high speed response laser source, narrow band response photodetector high speed wavelength converter, dense wavelength multi/demultiplexer, low loss high speed response photo-switch and multi-beam coupler are the key components in the system. The, investigation progress in the laboratory will be introduced.

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.

High power 980 nm Al-free strained quantum-well lasers for erbium-doped fiber amplifiers

In this paper, we reported on the fabrication of 980 nm InGaAs/InGaAsP strained quantum-well (QW) lasers with broad waveguide. The laser structure was grown by low-pressure metalorganic chemical vapor deposition on a n(+)- GaAs substrate. For 3 mu m stripe ridge waveguide lasers, the threshold current is 30 mA and the maximum output power and the output power operating in fundamental mode are 350 mW and 200 mW, respectively. The output power from the single mode fiber is up to 100 mW, the coupling efficiency is 50%. We also fabricated 100 mu m broad stripe coated lasers with cavity length of 800 mu m, a threshold current density of 170 A/cm(2), a high slope efficiency of 1.03 W/A and a far-field pattern of 40 x 6 degrees are obtained. The maximum output power of 3.5 W is also obtained for 100 mu m wide coated lasers. (C) 2000 Elsevier Science B.V. All rights reserved.

Parallel optical communication subsystem based on VCSEL - art. no. 67833I

A parallel optical communication subsystem based on a 12 channels parallel optical transmitter module and a 12 channels parallel optical receiver module can be used as a 10Gbps STM-64 or an OC-192 optical transponder. The bit error rate of this parallel optical communication subsystem is about 0 under the test by SDH optical transport tester during three hours and eighteen minutes.

A 5GHz low power WLAN transceiver SiGe RFIC for personal communication terminal applications

A low-cost low-power single chip WLAN 802.11a transceiver is designed for personal communication terminal and local multimedia data transmission. It has less than 130mA current dissipation, maximal 67dB gain and can be programmed to be 20dB minimal gain. The receiver system noise figure is 6.4dB in hige-gain mode.

The application of parallel optical transmitter and receiver modules in communication subsystems

A new 12 channels parallel optical transmitter module in which a Vertical Cavity Surface Emitting Laser (VCSEL) has been selected as the optical source is capable of transmitting 37.5Gbps date over hundreds meters. A new 12 channels parallel optical receiver module in which a GaAs PIN (p-intrinsic-n-type) array has been selected as the optical receiver unit is capable of responding to 30Gbps date. A transmission system based on a 12 channels parallel optical transmitter module and a 12 channels parallel optical receiver module can be used as a 10Gbps STM-64 or an OC-192 optical transponder. The parallel optical modules and the parallel optical transmission system have passed the test in laboratory.

A 1Gb/s silicon photo-receiver in standard CMOS for 850-nm optical communication

A monolithic silicon CMOS optoelectronic integrated circuit (OEIC) was designed and fabricated with standard 0.6 mu m CMOS technology. This OEIC circuit consisted of an integrated double photodiode detector (DPD) and a preamplifier. The DPD detector exhibited high bandwidth by screening the bulk-generated diffusion carriers and suppressing the slow diffusion tail effect. The preamplifier exploited the regulated cascode (RGC) configuration as the input stage of receiver, thus isolating the influence of photodiode capacitance and input parasitic capacitance on bandwidth. Testing results showed that the bandwidth of OEIC was 700MHz, indicating the bit rate of 1Gb/s was achieved.

Object-recognition with oblique observation directions based on biomimetic pattern recognition

In this paper, we propose a new scheme for omnidirectional object-recognition in free space. The proposed scheme divides above problem into several onmidirectional object-recognition with different depression angles. An onmidirectional object-recognition system with oblique observation directions based on a new recognition theory-Biomimetic Pattern Recognition (BPR) is discussed in detail. Based on it, we can get the size of training samples in the onmidirectional object-recognition system in free space. Omnidirection ally cognitive tests were done on various kinds of animal models of rather similar shapes. For the total 8400 tests, the correct recognition rate is 99.89%. The rejection rate is 0.11% and on the condition of zero error rates. Experimental results are presented to show that the proposed approach outperforms three types of SVMs with either a three degree polynomial kernel or a radial basis function kernel.

Biomimetic pattern recognition for speaker-independent speech recognition

In speaker-independent speech recognition, the disadvantage of the most diffused technology ( 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 Speech in a speaker-independent manner. The vocabulary of the system consists of 15 Chinese dish's names. Neural networks based on Multi-Weight Neuron (MWN) model are used to train and recognize the speech sounds. Experimental results are presented to show that the system, which can carry out real time recognition of the persons from different provinces speaking common Chinese speech, outperforms HMMs especially in the cases of samples of a finite size.