This paper investigates the effectiveness of using neural networks in classifying Malay speech sounds according to their place of articulation and voicing. The system is very different from conventional speech recogni...
详细信息
This paper investigates the effectiveness of using neural networks in classifying Malay speech sounds according to their place of articulation and voicing. The system is very different from conventional speech recognition systems, where the systems do not classify the speech sounds into groups of voicing and place of articulation. The system proposed classifies 16 selected Malay syllables into their groups of phonetic features. The Malay syllables are initialized with stops and followed by succeeding vowels. The speech tokens are sampled at 16 kHz with 16-bit resolution. LPC-derived cepstrum is used to extract the speech features. A three-layer multilayer perceptron (MLP) is used to train and recognize the Malay syllables. The system gives an encouraging result, with an average accuracy of 92.92%.
Three structures of silicon light emitting sources are described, each presenting higher electrical-to-optical conversion efficiency. The advantage of these structures lay in the fact that they were all fabricated usi...
详细信息
Three structures of silicon light emitting sources are described, each presenting higher electrical-to-optical conversion efficiency. The advantage of these structures lay in the fact that they were all fabricated using conventional standard VLSI technology, without any alternation of the processing procedure.
Reports, to the best of the authors' knowledge, the first experimental determination of the Auger coefficients in quantum dots. In/sub 0.4/Ga/sub 0.6/As/GaAs self-organized quantum dot separate confinement heteros...
详细信息
ISBN:
(纸本)0780370147
Reports, to the best of the authors' knowledge, the first experimental determination of the Auger coefficients in quantum dots. In/sub 0.4/Ga/sub 0.6/As/GaAs self-organized quantum dot separate confinement heterostructure (SCH) lasers were grown by MBE. The active region consists of five coupled quantum dot layers. Single-mode ridge waveguide lasers with ridge widths 3/spl mu/m, 5/spl mu/m, and 8/spl mu/m and length 600/spl mu/m were fabricated by standard photolithographic techniques and cleaving of the facets. The peak lasing wavelength was measured to be 1.06/spl mu/m at room temperature, confirming lasing from ground state transitions. The lowest measured threshold current was 15 mA.
In a system for active computer vision, there is an intrinsic need for interfacing two different kinds of specific hardware devices: image digitizer and controllable camera. The architecture of software components res...
详细信息
Summary form only given. Research on GaAs-based quantum dot (QD) lasers operating at 1.3 /spl mu/m wavelength has been rapidly advancing since the demonstrations of room-temperature operation in pulsed-mode and contin...
详细信息
ISBN:
(纸本)1557526346
Summary form only given. Research on GaAs-based quantum dot (QD) lasers operating at 1.3 /spl mu/m wavelength has been rapidly advancing since the demonstrations of room-temperature operation in pulsed-mode and continuous wave (CW) operation. Native oxide confinement is of interest for this type of laser, similar to that used for quantum well edge-emitting lasers and quantum dot vertical cavity surface emitting lasers. The native oxide confinement is especially interesting due to the lateral "built-in" electronic confinement potentials that confine the current in lateral direction. We report on the room-temperature CW operation of oxide-confined single-layer InGaAs QD lasers with very low threshold current of 1.2 mA. The low threshold operation is achieved due to low optical waveguide loss of the native oxide.
A real-time system for tracking multiple quasi-rigid objects is presented. To enable the tracking of objects having similar gray-level intensity during contacts, we use dynamic information extracted by computing spars...
详细信息
A real-time system for tracking multiple quasi-rigid objects is presented. To enable the tracking of objects having similar gray-level intensity during contacts, we use dynamic information extracted by computing sparse optical flow along the object contours. Optical flow vectors are used for updating the positions of the tracked contours in a sequence of image frames. The local properties of optical flow enable the system to track the objects during and after contact, when parts of object contours become hidden. The missing dynamic information is reconstructed by using a model of constant optical flow along an object contour. To deal with the contours of changing-shape, a contour-correcting procedure based on an active contour model is added. The robustness of the tracking algorithm is improved by adding a supervision module, which detects tracking failures and reinitializes the lost contours. The system has been tested on real sequences with laboratory animals during pharmacological experiments and has been shown to be sufficiently robust and efficient.
作者:
A.B. PosavecDepartment for Electronics
Microelectronics Computer and Intelligent Systems at the Faculty of Electrical Engineering and Computing University of Zagreb Croatia
The expressive power and the epistemic adequacy of the Dempster-Shafer (DS) theory of evidence has often been acknowledged. DS theory of evidence is based on two components: a tool for representing belief for a statem...
详细信息
The expressive power and the epistemic adequacy of the Dempster-Shafer (DS) theory of evidence has often been acknowledged. DS theory of evidence is based on two components: a tool for representing belief for a statement, i.e. a pair of set functions (Bel, Pl) that quantify to what extent available evidence implies the statement and to what extent is available evidence consistent with the statement, respectively; and a tool for combining evidence. Thus DS theory deals with belief intervals rather than single numerical values of belief. There is an explicit differentiation between the notion of disbelief from that of lack of belief. However, as many other methodologies in the field of uncertain reasoning, DS theory addresses only the problem of representing the uncertainty of knowledge, without dealing with the problem of representing the knowledge itself. Saffiotti (1994) has proposed a framework for integrating the DS theory with a knowledge representation system. This approach introduces so-called belief bases, whose purpose is to allow embedding belief functions into a knowledge representation system which is better suited for representing the knowledge itself. Belief bases for a given knowledge representation system are built using three primitive operations, which utilize Dempster's combination rule. This paper describes an attempt at integrating appropriately modified belief bases into a knowledge representation system which utilizes Petri nets for representing knowledge.
A technique to control the transmission properties of arrays doped in silicon is described. Photonic excitation creates plasma, which alters array performance. This can be controlled using optical masks and the resona...
详细信息
A lateral double diffused DMOS (LDMOS) transistor has been integrated into a CMOS process. An effective RESURF of the drain drift region enables a high breakdown voltage of about 90V and GHz operation. The measured ou...
详细信息
A technique to control the transmission properties of arrays doped in silicon is described. Photonic excitation creates plasma, which alters array performance. This can be controlled using optical masks and the resona...
详细信息
A technique to control the transmission properties of arrays doped in silicon is described. Photonic excitation creates plasma, which alters array performance. This can be controlled using optical masks and the resonant frequency can be tuned.
暂无评论