• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.1
• /
• pp.121-128
• /
• 2017

In this paper, we propose a dual-channel acoustic event detection (AED) method using nonnegative tensor factorization (NTF) and hidden Markov model (HMM) in order to improve detection accuracy of AED in multisource environments. The proposed method first detects multiple acoustic events by utilizing channel gains obtained from the NTF technique applied to dual-channel input signals. After that, an HMM-based likelihood ratio test is carried out to verify the detected events by using channel gains. The detection accuracy of the proposed method is measured by F-measures under 9 different multisource conditions. Then, it is also compared with those of conventional AED methods such as Gaussian mixture model and nonnegative matrix factorization. It is shown from the experiments that the proposed method outperforms the convectional methods under all the multisource conditions.

• 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 the Korean Institute of Telematics and Electronics B
• /
• v.31B no.9
• /
• pp.85-100
• /
• 1994

This paper proposes a recognition system of constrained handwritten Hangul and alphanumeric characters using discrete hidden Markov models (HMM). HMM process encodes the distortion and similarity among patterns of a class through a doubly stochastic approach. Characterizing the statistical properties of characters using selected features, a recognition system can be implemented by absorbing possible variations in the form. Hangul shapes are classified into six types by fuzzy inference, and their recognition is performed based on quantized features by optimally ordering features according to their effectiveness in each class. The constrained alphanumerics recognition is also performed using the same features used in Hangul recognition. The forward-backward, Viterbi, and Baum-Welch reestimation algorithms are used for training and recognition of handwritten Hangul and alphanumeric characters. Simulation result shows that the proposed method recognizes handwritten Korean characters and alphanumerics effectively.

• Journal of Soil and Groundwater Environment
• /
• v.21 no.3
• /
• pp.21-34
• /
• 2016

In the present study, we applied various machine learning techniques comparatively for prediction of subsurface structures based on multiple secondary information (i.e., well-logging data). The machine learning techniques employed in this study are Naive Bayes classification (NB), artificial neural network (ANN), support vector machine (SVM) and logistic regression classification (LR). As an alternative model, conventional hidden Markov model (HMM) and modified hidden Markov model (mHMM) are used where additional information of transition probability between primary properties is incorporated in the predictions. In the comparisons, 16 boreholes consisted with four different materials are synthesized, which show directional non-stationarity in upward and downward directions. Futhermore, two types of the secondary information that is statistically related to each material are generated. From the comparative analysis with various case studies, the accuracies of the techniques become degenerated with inclusion of additive errors and small amount of the training data. For HMM predictions, the conventional HMM shows the similar accuracies with the models that does not relies on transition probability. However, the mHMM consistently shows the highest prediction accuracy among the test cases, which can be attributed to the consideration of geological nature in the training of the model.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.10
• /
• pp.407-420
• /
• 2014

In general, the Korean morpheme analysis procedure is divided into two steps. In the first step as an ambiguity generation step, an Eojeol is analyzed into many morpheme sequences as candidates. In the second step, one appropriate candidate is chosen by using contextual information. Hidden Markov Model(HMM) is typically applied in the second step. This paper proposes Sub-word Conditional Probability(SCP) model as an alternate algorithm. SCP uses sub-word information of adjacent eojeol first. If it failed, then SCP use morpheme information restrictively. In the accuracy and speed comparative test, HMM's accuracy is 96.49% and SCP's accuracy is just 0.07% lower. But SCP reduced processing time 53%.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.373-377
• /
• 2017

This paper presents a voice-activity detection (VAD) method for sound sequences with various SNRs. For real-time VAD applications, it is inadequate to employ a post-processing for the removal of burst clippings from the VAD output decision. To tackle this problem, building on the bi-level hidden Markov model, for which a state layer is inserted into a typical hidden Markov model (HMM), we formulated a robust method for VAD not requiring any additional post-processing. In the method, a forward-inference-ratio test was devised to detect the speech endpoints and Mel-frequency cepstral coefficients (MFCC) were used as the features. Our experiment results show that, regarding different SNRs, the performance of the proposed approach is more outstanding than those of the conventional methods.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.499-503
• /
• 2008

In this paper, a novel human activity recognition method is proposed which utilizes independent components of activity shape information from image sequences and Hidden Markov Model (HMM) for recognition. Activities are represented by feature vectors from Independent Component Analysis (ICA) on video images, and based on these features; recognition is achieved by trained HMMs of activities. Our recognition performance has been compared to the conventional method where Principle Component Analysis (PCA) is typically used to derive activity shape features. Our results show that superior recognition is achieved with our proposed method especially for activities (e.g., skipping) that cannot be easily recognized by the conventional method.

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.12
• /
• pp.951-959
• /
• 2000

본 논문의 병렬음성인식 모델은 연속 은닉 마코프 모델(HMM; hidden Markov model)에 기반한 병렬 음소인식모듈과 계층구조의 지식베이스에 기반한 병렬 문장인식모듈로 구성된다. 병렬 음소인식 모듈은 수천개의 HMM을 병렬 프로세서에 분산시킨 수, 할당된 HMM에 대한 출력확률 계산과 Viterbi 알고리즘을 담당한다. 지식베이스 기반 병렬 문장인식모듈은 음소모듈에서 공급되는 음소열과 지안하는 병렬 음성인식 알고리즘은 분산메모리 MIMD 구조의 다중 트랜스퓨터와 Parsytec CC 상에 구현되었다. 실험결과, 병렬 음소인식모듈을 통한 실행시간 향상과 병렬 문장인식모듈을 통한 인식률 향상을 얻을 수 있었으며 병렬 음성인식 시스템의 실시간 구현 가능성을 확인하였다.

• Journal of Information Technology Application
• /
• v.1 no.3_4
• /
• pp.1-23
• /
• 1999

본 연구에서는 HMM(Hidden Markov Model) 및 Levelbuilding 알고리즘을 이용하여 인식대상 음소열의 표본 집합(훈련패턴 집합)을 입력으로 하는 음성의 자동 분할 시스템을 구현하였다. 본 시스템은 자연스럽게 발음되어진 연결음 음성으로부터 표준 음소모델을 생성한다. 본 시스템의 구성은 초기화 과정, HMM학습과정 그리고 Levelbuilding을 이용한 분리 및 CLustering 과정으로 구성되어 있다. 초기화 과정에서는 제어 정보를 이용하여 훈련패턴 집합으로부터 초기 음소 집합 군을 생성한다. Levelbuilding을 이용한 분리 및 Clustering 단계에서는 음소 모델과 제어 정보를 이용하여 훈련패턴들을 음소 단위로 분리하고, 분리된 후보 음소들을 Clustering하여 음소집합 군을 생성한다. 음소모델의 구성에 변화가 없을 때까지 이 작업을 반복 수행하여 최적의 음소모델을 생성한다. 본 연구에서는 3개 이하의 숫자단어로 구성된 연결되어 음성 패턴을 대상으로 실험하였다. 연결단어에 대한 음소의 표준모델 생성과정에서 가장 중요한 처리인 훈련패턴의 자동분할 과정을 분석하기 위하여 각 반복과정에서 분리된 정보를 그래프로 도시화하여 확인하였다.

• 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.