• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.245-246
• /
• 2006

In this paper, we proposed using MFCC coefficients(Mel-Scaled Cepstral Coefficients) and a simple but efficient classifying method. Many other features: IAV, zero crossing, LPCC, $\ldot$ and their derivatives are also tested and compared with MFCC coefficients in order to find the best combination. GMM and HMM (Discrete and Continuous Hidden Markov Model), are studied as well in the hope that the use of continuous distribution and the temporal evolution of this set of features will improve the quality of emotion recognition.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.337-340
• /
• 2002

본 논문에서는 휠체어 시스템에 화자 독립 고립단어 인식을 위한 임베디드 시스템 설계에 관한 내용을 서술한다. 실제 환경에서는 잡음이 포함되어 있어 인식률을 저하시키므로, 잡음을 제거하는 방식 중 가장 간단한 방식인 스펙트럼 차감법(Spectral subtraction method)을 사용하여 잡음을 제거했다 전처리 단계에서는 12차 LPC&Cepstrum 방식을 사용했고, 인식 알고리즘은 DHMM (Discrete Hidden Markov Model)을 전반부 인식기로 사용했다. 이 알고리즘을 적용하기 위해서는 데이터 간소화를 위해 벡터양자화(Vector Quantization) 처리가 전제되어야한다 또한 인식알고리즘은 인식률을 향상을 위해 후처리 인식기로 신경망(MLP:Multi-layer Perceptron)을 통해서 인식률을 향상시켰다 화자 독립 시스템에 맞는 인식 단어의 구성은 총 7개단어로 남녀 총 25명 목소리로 구성하였다. 그리고 하드웨어 구성은 32-bits floating point 방식인 TMS320C32를 적용했고, 메모리 부분은 4Mbyte로 설계를 했으며, 메인보드의 설계는 현재 완성 단계에 있다.

• Journal of Industrial Technology
• /
• v.26 no.B
• /
• pp.233-242
• /
• 2006

Continuous, discrete and semi continuous HMM systems are used for the speech recognition. Discrete systems have the advantage of low run-time computation. However, vector quantization reduces accuracy and this can lead to poor performance. Continuous systems let us get good correctness but they need much calculation so that occasionally they are unable to be used for practice. Although there are semi-continuous systems which apply advantage of continuous and discrete systems, they also require much computation. In this paper, we proposed the way which reduces calculation for continuous systems. The proposed method has the same computational load as discrete systems but can give better recognition accuracy than discrete systems.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.3
• /
• pp.21-26
• /
• 2002

This paper presents the new approach of identifying human emotional states such as anger, happiness, normal, sadness, or surprise. This is accomplished by using discrete duration continuous hidden Markov models(DDCHMM). For this, the emotional feature parameters are first defined from input speech signals. In this study, we used prosodic parameters such as pitch signals, energy, and their each derivative, which were then trained by HMM for recognition. Speaker adapted emotional models based on maximum a posteriori(MAP) estimation were also considered for speaker adaptation. As results, the simulation performance showed that the recognition rates of vocal emotion gradually increased with an increase of adaptation sample number.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.8
• /
• pp.2262-2270
• /
• 1999

In this paper, we describe gesture recognition algorithm using computer vision sensor and HMM. The automatic hand region extraction has been proposed for initializing the tracking of the tele-operation gestures. For this, distance informations(disparity map) as results of stereo matching of initial left and right images are employed to isolate the hand region from a scene. PDOE(positive difference of edges) feature images adapted here have been found to be robust against noise and background brightness. The KNU/KAERI(K/K) gesture instruction set is defined for tele-operation in atomic electric power stations. The composite recognition model constructed by concatenating three gesture instruction models including pre-orders, basic orders, and post-orders has been proposed and identified by discrete HMM. Our experimental results showed that consecutive orders composed of more than two ones are correctly recognized at the rate of above 97%.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.197-197
• /
• 2016

Forecasting future drought events in a region plays a major role in water management and risk assessment of drought occurrences. The creeping characteristics of drought make it possible to mitigate drought's effects with accurate forecasting models. Drought forecasts are inevitably plagued by uncertainties, making it necessary to derive forecasts in a probabilistic framework. In this study, a new probabilistic scheme is proposed to forecast droughts, in which a discrete-time finite state-space hidden Markov model (HMM) is used aggregated with the Representative Concentration Pathway 8.5 (RCP) precipitation projection (HMM-RCP). The 3-month standardized precipitation index (SPI) is employed to assess the drought severity over the selected five stations in South Kore. A reversible jump Markov chain Monte Carlo algorithm is used for inference on the model parameters which includes several hidden states and the state specific parameters. We perform an RCP precipitation projection transformed SPI (RCP-SPI) weight-corrected post-processing for the HMM-based drought forecasting to derive a probabilistic forecast that considers uncertainties. Results showed that the HMM-RCP forecast mean values, as measured by forecasting skill scores, are much more accurate than those from conventional models and a climatology reference model at various lead times over the study sites. In addition, the probabilistic forecast verification technique, which includes the ranked probability skill score and the relative operating characteristic, is performed on the proposed model to check the performance. It is found that the HMM-RCP provides a probabilistic forecast with satisfactory evaluation for different drought severity categories, even with a long lead time. The overall results indicate that the proposed HMM-RCP shows a powerful skill for probabilistic drought forecasting.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.5
• /
• pp.54-63
• /
• 2000

In this paper, we implemented cyber character that can do speech recognition, speech synthesis, Motion tracking and 3D animation. For speech recognition, we used Discrete-HMM algorithm with K-means 128 level vector quantization and MFCC feature vector. For speech synthesis, we used demi-syllables TD-PSOLA algorithm. For PC based Motion tracking, we present Fast Optical Flow like Method. And for animating 3D model, we used vertex interpolation with DirectSD retained mode. Finally, we implemented cyber character integrated above systems, which game calculating by the multiplication table with user and the cyber character always look at user using of Motion tracking system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.573-580
• /
• 2005

In this paper, we propose an emotion recognition using static and dynamic facial images to effectively design human interface. The proposed method is constructed by HMM(Hidden Markov Model), PCA(Principal Component) and wavelet transform. Facial database consists of six basic human emotions including happiness, sadness, anger, surprise, fear and dislike which have been known as common emotions regardless of nation and culture. Emotion recognition in the static images is performed by using the discrete wavelet. Here, the feature vectors are extracted by using PCA. Emotion recognition in the dynamic images is performed by using the wavelet transform and PCA. And then, those are modeled by the HMM. Finally, we obtained better performance result from merging the recognition results for the static images and dynamic images.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.748-754
• /
• 2015

This paper proposes a sequential state estimation model consisting of continuous and discrete variables, as a way of generalizing all discrete-state factorial HMM, and gives a design of gait motion model based on the idea. The discrete state variable implements a Markov chain that models the gait dynamics, and for each state of the Markov chain, we created a Gaussian process over the space of the continuous variable. The Markov chain controls the switching among Gaussian processes, each of which models the rotation or various views of a gait state. Then a particle filter-based algorithm is presented to give an approximate filtering solution. Given an input vector sequence presented over time, this finds a trajectory that follows a Gaussian process and occasionally switches to another dynamically. Experimental results show that the proposed model can provide a very intuitive interpretation of video-based gait into a sequence of poses and a sequence of posture states.

• ETRI Journal
• /
• v.33 no.4
• /
• pp.569-579
• /
• 2011

This paper presents a novel approach for human activity recognition (HAR) using the joint angles from a 3D model of a human body. Unlike conventional approaches in which the joint angles are computed from inverse kinematic analysis of the optical marker positions captured with multiple cameras, our approach utilizes the body joint angles estimated directly from time-series activity images acquired with a single stereo camera by co-registering a 3D body model to the stereo information. The estimated joint-angle features are then mapped into codewords to generate discrete symbols for a hidden Markov model (HMM) of each activity. With these symbols, each activity is trained through the HMM, and later, all the trained HMMs are used for activity recognition. The performance of our joint-angle-based HAR has been compared to that of a conventional binary and depth silhouette-based HAR, producing significantly better results in the recognition rate, especially for the activities that are not discernible with the conventional approaches.