Jinkyu Lee

This paper presents a speech emotion recognition system using a recurrent neural network (RNN) model trained by an efficient learning algorithm. The proposed system takes into account the long-range context effect and the uncertainty of emotional label expressions. To extract high-level representation of emotional states with regard to its temporal dynamics, a powerful learning method with a bidirectional long short-term memory (BLSTM) model is adopted. To overcome the uncertainty of emotional l

This paper presents a new low-power test-data-compression scheme based on linear feedback shift register (LFSR) reseeding. A drawback of compression schemes based on LFSR reseeding is that the unspecified bits are filled with random values, which results in a large number of transitions during scan-in, thereby causing high-power dissipation. A new encoding scheme that can be used in conjunction with any LFSR-reseeding scheme to significantly reduce test power and even further reduce test storage

Many test data compression schemes are based on LFSR reseeding. A drawback of these schemes is that the unspecified bits are filled with random values resulting in a large number of transitions during scan-in thereby causing high power dissipation. This paper presents a new encoding scheme that can be used in conjunction with any LFSR reseeding scheme to significantly reduce test power and even further reduce test storage. The proposed encoding scheme acts as a second stage of compression after

The ignition resistance was investigated for CaO added Mg-Al alloys. The ignition resistance was examined by DTA for quantitative data, furnace chip ignition test for the safety of machined chips and torch ignition test for safety of products. The ignition resistances under all conditions greatly increased by CaO addition. AES depth profile was performed to evaluate the ignition resistance in terms of surface oxide stability. In the case of Mg-Al alloy without CaO, there was the thick and porous

This letter presents a phase-sensitive joint learning algorithm for single-channel speech enhancement. Although a deep learning framework that estimates the time-frequency (T-F) domain ideal ratio masks demonstrates a strong performance, it is limited in the sense that the enhancement process is performed only in the magnitude domain, while the phase spectra remain unchanged. Thus, recent studies have been conducted to involve phase spectra in speech enhancement systems. A phase-sensitive mask (

Trialkoxysilyl terminal groups were directly introduced into fluorescent organic dye molecules by consecutive allylation and hydrosilation reactions; the derivatized dye molecules were then successfully embedded into silica nanoparticles by the Stöber method. Those fluorescent silica nanoparticles (FSNPs) had emission colors corresponding to each fluorescent organic dye used (yellowish-green and red) and showed excellent thermal and photochemical stabilities. A white light-emitting diode (WLED)

The potential of multi-core chips for high performance and reliability at low cost has made them ideal computing platforms for embedded real-time systems. As a result, power management of a multi-core chip has become an important issue in the design of embedded real-time systems. Most existing approaches have been designed to regulate the behavior of average power consumption, such as minimizing the total energy consumption or the chip temperature. However, little attention has been paid to the

A hierarchically structured composite ion conductor film (AgI nanorod/γ-Al2O3) was chemically prepared using nanoporous anodic aluminium oxide (AAO) as a template, where ion conducting AgI nanorods (av. diameter = 75 nm) are periodically aligned within a hexagonally organized insulating Al2O3 matrix.

It is widely assumed that scheduling real-time tasks becomes more difficult as their deadlines get shorter. With deadlines shorter, however, tasks potentially compete less with each other for processors, and this could produce more contention-free slots at which the number of competing tasks is smaller than or equal to the number of available processors. This paper presents a policy (called CF policy) that utilizes such contention-free slots effectively. This policy can be employed by any work-c

The well-investigated method to prepare various nanoparticles is a thermolysis method in hot organic solutions. These nanoparticles are usually dispersible in nonpolar organic solvents, which sometimes causes problem to overcoat them with silica due to the polar alcoholic solvent in the silica forming process. We have developed a general procedure to incorporate high quality nanoparticles into silica beads. Organic-dispersible nanoparticles do not form precipitates in alcoholic solution in the p

LLF (Least Laxity First) scheduling, which assigns a higher priority to a task with smaller laxity, has been known as an optimal preemptive scheduling algorithm on a single processor platform. However, its characteristics upon multiprocessor platforms have been little studied until now. Orthogonally, it has remained open how to efficiently schedule general task systems, including constrained deadline task systems, upon multiprocessors. Recent studies have introduced zero laxity (ZL) policy, whic

This paper presents a joint learning algorithm for complex-valued time-frequency (T-F) masks in single-channel speech enhancement systems. Most speech enhancement algorithms operating in a single-channel microphone environment aim to enhance the magnitude component in a T-F domain, while the input noisy phase component is used directly without any processing. Consequently, the mismatch between the processed magnitude and the unprocessed phase degrades the sound quality. To address this issue, a

The purpose of this study was to investigate the effect of load carriage on the kinematics and kinetics of the ankle and knee joints during uphill walking, including joint work, range of motion (ROM), and stance time. Fourteen males walked at a self-selected speed on an uphill (15°) slope wearing military boots and carrying a rifle in hand without a backpack (control condition) and with a backpack. The results showed that the stance time significantly decreased with backpack carriage (p < .05).