Keun-Ho Kim

Extraction of Speech Features for Emotion Recognition

Emotion recognition is an important technology in the filed of human-machine interface. To apply speech technology to emotion recognition, this study aims to establish a relationship between emotional groups and their corresponding voice characteristics by investigating various speech features. The speech features related to speech source and vocal tract filter are included. Experimental results show that statistically significant speech parameters for classifying the emotional groups are mainly related to speech sources such as jitter, shimmer, F0 (F0_min, F0_max, F0_mean, F0_std), harmonic parameters (H1, H2, HNR05, HNR15, HNR25, HNR35), and SPI.

Development and Evaluation of Repeatability of the Integrated Constitutional Diagnosis System

Abstract Development and Evaluation of Repeatability of the Integrated Constitutional Diagnosis System Young-Ju Jeon, Jang-Woong Kim, Jae-Uk Kim, Jang-Han Bae, Jong-Yeol Kim, and Keun-Ho KimKorean Institute of Oriental MedicineObjectivesIn this study, we developed a mock-up of the system for Sasang Constitutional (SC) diagnosis. This system consistsof 5 devices which are the face analyzer, the voice analyzer, the skin analyzer, the pulse analyzer, and the computer-basedquestionnaire. Our goal is to evaluate the repeatability of the system.MethodsEach device is capable of classifying SC types. The classification probability of the integrated system for the SC types was obtained by summing the probability from each device. For evaluating the repeatability of the system,we collected data for 5 subjects, and repeated the measurement three times for each individual. The average and standard deviation were used for calculating the Coefficient of Variation.ResultsThe results showed that the repeatability of the classification probability of the integrated system is about 8%, which implies the system is repeatable. ConclusionsTo increase usability of this system, it is desirable for the system to offer information on health condition of the user. The integrated constitutional diagnosis system will be upgraded to complement the convenience and to develop the diagnostic algorithm for the user’s health condition.Key Words: Sasang Constitutional Medicine, Integrated Constitutional Diagnosis System, Diagnosis Instrument

Extraction Method of Geometry Information for Effective Analysis in Tongue Diagnosis

In Oriental medicine, the status of a tongue is the important indicator to diagnose the condition of internal organs in a body. A tongue diagnosis is not only convenient but also non-invasive, and therefore widely used in Oriental medicine. But tongue diagnosis has some problems that should be objective and standardized, it also exhaust the diagnosis tool that can help for oriental medicine doctor`s decision-making. In this paper, to solve the this problem we propose a method that calculates the tongue geometry information for effective tongue diagnosis analysis. Our method is to extract the tongue region for using improved snake algorithm, and calculates the geometry information by using convex hull and In-painting. In experiment, our method has stable performance as 7.2% by tooth plate and 8.5% by crack in region difference ratio.

Analysis of the Relationship Between Sasang Constitutional Groups and Speech Features Based on a Listening Evaluation of Voice Characteristics

Sasang constitution experts utilize voice characteristics as an auxiliary measure for deciding a person`s constitutional group. This study aims at establishing a relationship between speech features and the constitutional groups by subjective listening evaluation of voice characteristics. A speech database of 841 speakers whose constitutional groups have been already diagnosed by Sasang constitution experts was constructed. Speech features related to speech source and vocal tract filter were extracted from five vowels and one sentence. Statistically significant speech features for classifying the groups were analyzed using SPSS. The features contributed to constitution classification were speaking rate, Energy, A1, A2, A3, H1, H2, H4, CPP for males in their 20s, F0_mean, CPP, SPI, HNR, Shimmer, Energy, A1, A2, A3, H1, H2, H4 for females in their 20s, Energy, A1, A2, A3, H1, H2, H4, CPP for male in the 60s, and Jitter, HNR, CPP, SPI for females in their 60s. Experimental results show that speech technology is useful in classifying constitutional groups.

Study of Skin Elasticity and Perspiration of Elderly Female according to Sasang Constitution (SC)

Abstract Study of Skin Elasticity and Perspiration of Elderly Female according toSasang Constitution (SC) Chang-Jin Jung, Bon-Cho Ku, Jae-Chul Lee, Jaeuk-U. Kim, Young-Ju Jeon, Keun-Ho Kim, Jong-Yeol Kim, and Young-Min Kim Korea Institute of Oriental MedicineObjectivesSasang Constitution (SC) is determined by various physical and psychological attributes. Recently, skin propertieshave been used effectively to describe SC types in clinics. In this paper, we investigated the constitution dependenceof skin elasticity and skin perspiration by using quantitative measurement devices. MethodsThe skin elasticity of forearm and the skin perspiration of forehead and philtrum were measured in 223 elderly female subjects. To determine the subject’s constitution, we adopted the classification results from a newly developeddiagnostic tool. For the clarity of constitution, we excluded low-scored subjects in their SC classification. Results & ConclusionsAs a result, the elasticity hysteresis of forearm (EHFa) of Taeum-in group was significantly less than the EHFa of Soeum-in group. Soeum-in group has high perspiration difference between philtrum and forehead (Diff.PhFh) compared to Taeum-in group in a significance level of .05. Taeum-in and Soeum-in group were significantly classified by EHFa and Diff.PhFh using a Support Vector Machine.Key Words: Sasang Constitution, Body Mass Index, Skin elasticity, Skin hysteresis, Perspiration