• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.99-100
• /
• 2008

This paper proposes a Gaussian Mixture Model (GMM) - based speech emotion recognition methods using four feature parameters; 1) Fast Fourier Transform(FFT) spectral entropy, 2) delta FFT spectral entropy, 3) Mel-frequency Filter Bank (MFB) spectral entropy, and 4) delta MFB spectral entropy. In addition, we use four emotions in a speech database including anger, sadness, happiness, and neutrality. We perform speech emotion recognition experiments using each pre-defined emotion and gender. The experimental results show that the proposed emotion recognition using FFT spectral-based entropy and MFB spectral-based entropy performs better than existing emotion recognition based on GMM using energy, Zero Crossing Rate (ZCR), Linear Prediction Coefficient (LPC), and pitch parameters. In experimental Results, we attained a maximum recognition rate of 75.1% when we used MFB spectral entropy and delta MFB spectral entropy.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.8
• /
• pp.727-734
• /
• 2002

A simple algorithm for discriminating voiced sounds in a speech is proposed in this paper. In addition to low-frequency energy and zero-crossing rate (ZCR), both of which have been widely used in the past for identifying voiced sounds, the proposed algorithm incorporates pitch variation to improve the discrimination rate. Based on TIMIT corpus, evaluation result shows an improvement of 13% in the discrimination of voiced phonemes over that of the traditional algorithm using only energy and ZCR.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.12
• /
• pp.1635-1643
• /
• 1995

This paper proposes an algorithm for machine recognition of phonemes in continuously spoken Korean. The proposed algorithm is a static strategy neural network. The algorithm uses, at the stage of training neurons, features such as the rate of zero crossing, short-term energy, and either PARCOR or auditory-like perceptual linear prediction(PLP) but not both, covering a time of 171ms long. Numerical results show that the algorithm with PLP achieves approximately the frame-based phoneme recognition rate of 99% for small vocabulary recognition experiments. Based on this it is concluded that the proposed algorithm with PLP analysis is effective in phoneme recognition.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10b
• /
• pp.473-478
• /
• 1987

The purpose of this study is to design a phoneme-class recognition system for Korean language using filter-bank analysis and zero crossing rate method. First, the speech signals are separated in 16 bandpass filters to obtain short-time spectrum of speech signals, and digitized by 16-ch A/D converter. And then, with the set of features which extracted from patterns of ratios of each channel energy level to overall energy level, the decision rules are made for recognize unknown speech signal. In this experiment, the recognition rate was about 93.1 percent for 7 vowels under multitalker environment and 74.4 percent for 10 initial sounds at single speaker.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.3
• /
• pp.14-24
• /
• 1992

This paper is a study on the consonant recognition using neural network. First, the part of consonant was separated from the sound of vowel and consonant by the use of acoustic parameter. The rate of length vs. zero crossing rate in the sound of consonant had been studied by dividing each consonant into several groups. Finally, for the purpose of consonant recognition, the composite neural network which consists of a control network and several sub-network is proposed. The control network identifies the group to which the input consonant belongs and the sub-network recognizes the consonant in each group.

• KIEE International Transactions on Electrophysics and Applications
• /
• v.5C no.4
• /
• pp.152-154
• /
• 2005

We demonstrate a simple $CO_2$ laser by controlling firing angle of a TRIAC switch in ac power line. The power supply for our laser system switches the voltage of the AC power line (60Hz) directly. The power supply does not need elements such as a rectifier bridge, energy-storage capacitors, or a current-limiting resistor in the discharge circuit. In order to control the laser output power, the pulse repetition rate is adjusted up to 60Hz and the firing angle of TRIAC gate is varied from $45^{circ}$ to $135^{circ}$. A ZCS(Zero Crossing Switch) circuit and a PIC one-chip microprocessor are used to control the gate signal of the TRIAC precisely. The maximum laser output of 40W is obtained at a total pressure of 18 Torr, a pulse repetition rate of 60Hz, and a TRAIC gate firing angle of $90^{circ}$.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.3
• /
• pp.193-197
• /
• 2012

This paper focuses on identifying which appliance is currently operating by analyzing electrical load signature for home energy monitoring system. The identification framework is comprised of three steps. Firstly, specific appliance features, or signatures, were chosen, which are DC (Duty Cycle), SO (Slope of On-state), VO (Variance of On-state), and ZC (Zero Crossing) by reviewing observations of appliances from 13 houses for 3 days. Five appliances of electrical rice cooker, kimchi-refrigerator, PC, refrigerator, and TV were chosen for the identification with high penetration rate and total operation-time in Korea. Secondly, K-NN and Naive Bayesian classifiers, which are commonly used in many applications, are employed to estimate from which appliance the signatures are obtained. Lastly, one of candidates is selected as final identification result by majority voting. The proposed identification frame showed identification success rate of 94.23%.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.40-48
• /
• 2023

Speech Emotions recognition has become the active research theme in speech processing and in applications based on human-machine interaction. In this work, our system is a two-stage approach, namely feature extraction and classification engine. Firstly, two sets of feature are investigated which are: the first one is extracting only 13 Mel-frequency Cepstral Coefficient (MFCC) from emotional speech samples and the second one is applying features fusions between the three features: Zero Crossing Rate (ZCR), Teager Energy Operator (TEO), and Harmonic to Noise Rate (HNR) and MFCC features. Secondly, we use two types of classification techniques which are: the Support Vector Machines (SVM) and the k-Nearest Neighbor (k-NN) to show the performance between them. Besides that, we investigate the importance of the recent advances in machine learning including the deep kernel learning. A large set of experiments are conducted on Surrey Audio-Visual Expressed Emotion (SAVEE) dataset for seven emotions. The results of our experiments showed given good accuracy compared with the previous studies.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.35 no.1
• /
• pp.47-56
• /
• 2019

As the zero interest rate era was over with the end of quantitative easing, the economy of several global markets observed the fluctuations of the base interest rate. Interest rate, which is the change of money value with respect to time, is negatively correlated with construction investment. Considering the characteristics of interest rates and construction investment as economic variables, the necessity of cross-border analysis between base interest rate and construction investment was suggested in this paper. Cross-correlation analysis between base interest rates and construction investment crossing the border was performed. The effective correlations were confirmed with values varying by countries. Similar characteristics were also observed among countries with similar economy, which were then divided into three groups. Additionally, identifying the base interest rate that affects the construction investment of a particular country was made possible by reflecting a self-cycle of base interest rates. Lastly, from the result of examining the influence of each rise and fall of the interest rate, it was verified that the difference was more than twice as large in some countries. These results are expected to contribute to construction-related policy makers or investors to make decisions in response to the economic status of the construction market.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.12
• /
• pp.2109-2112
• /
• 2016

The rate of rise of the fault current in DC grids is very high compared to AC grids because of the low line impedance of DC lines. In AC grids the arc of the circuit breaker under current interruption is extinguished by the zero current crossing which is provided naturally by the system. In DC grids the zero current crossing must be provided by the circuit breaker itself. Unlike AC girds, the magnetic energy of DC grids is stored in the system inductance. The DC circuit breaker must dissipate the stored energy. In addition the DC breaker must withstand the residual overvoltage after the current interruption. The main contents of this paper are to ${\cdot}$ Explain the theoretical background for the design of DC circuit breaker. ${\cdot}$ Develop the simulation model in PSIM of the real scaled DC circuit breaker for 1,800V DC railway. ${\cdot}$ Suggest design guidelines for the DC circuit breaker based on the experimental work, simulations and design process.