• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.681-682
• /
• 2006

일반적으로 축구 비디오 데이터는 멀티모달과 멀티레이어 속성을 지닌다. 이러한 데이터를 다루기 적합한 모델은 동적 베이지안 네트워크(Dynamic Bayesian Network: DBN) 형태의 위계적 은닉 마르코프 모델(Hierarchical Hidden Markov Model: HHMM)이다. 이러한 HHMM 중 다중속성의 특징들이 서로 상호작용하는 PHHMM(Product Hierarchical Hidden Markov Model)이 있다. 본 논문에서는 PHHMM 을 축구 경기의 Play/Break 이벤트 검색 및 분석에 적용하였고 바람직한 결과를 얻었다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.3
• /
• pp.164-170
• /
• 2013

Recent years have been higher demands for automatic speech recognition (ASR) systems that are able to operate robustly in an acoustically noisy environment. This paper proposes an improved product hidden markov model (HMM) used for bimodal speech recognition. A two-dimensional training model is built based on dependently trained audio-HMM and visual-HMM, reflecting the asynchronous characteristics of the audio and video streams. A weight coefficient is introduced to adjust the weight of the video and audio streams automatically according to differences in the noise environment. Experimental results show that compared with other bimodal speech recognition approaches, this approach obtains better speech recognition performance.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.3
• /
• pp.8-14
• /
• 2009

A Hidden Markov Model(HMM)-based information extraction method is proposed in this paper. The proposed extraction method is applied to extraction of products' prices. The input of the proposed IESHMM is the URLs of a search engine's interface, which contains the names of the product types. The output of the system is the list of extracted slots of each product: name, price, image, and URL. With the observation data set Maximum Likelihood algorithm and Baum-Welch algorithm are used for the training of HMM and The Viterbi algorithm is then applied to find the state sequence of the maximal probability that matches the observation block sequence. When applied to practical problems, the proposed HMM-based system shows improved results over a conventional method, PEWEB, in terms of recall ration and accuracy.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.2
• /
• pp.71-79
• /
• 1997

In this paper, a codeword-dependent distance normalization(CDDN) and an instar-formed fuzzy smoothing of output distribution are proposed for robust estimation of output probabilities in the FVQ(fuzzy vector quantization)-DHMM(discrete hidden Markov model). The FVQ-DHMM is a variant of DHMM in which the state output probability is estimated by the sum oft he product of the output probability and its weighting factor for each codeword on an input vector. As the performance of the FVQ-DHMM is influenced by weighting factor and output distribution from a state, it is required to get a method to get robust estimation of weighting factors and output distribution for each state. From experimental results, the proposed CDDN method has reduced 24% of error rate over the conventional FVQ-DHMM, and also reduced 79% of error rate when the smoothing of output distribution is also applied to the computation of an output probability. These results indicate that the use of CDDN and the fuzzy smoothing of output distribution to the FVQ-DHMM lead to improved recognition, and therefore it may be used as an alternative to the robust estimation of output probabilities for HMMs.

• Journal of IKEEE
• /
• v.19 no.4
• /
• pp.541-547
• /
• 2015

In current semiconductor manufacturing, as the feature size of integrated circuit (IC) devices continuously shrinks, detecting endpoint in plasma etching process is more difficult than before. For endpoint detection, various kinds of sensors are installed in semiconductor manufacturing equipments, and sensor data are gathered with predefined sampling rate. Generally, detecting endpoint is performed using OES data of by-product. In this study, OES data of both by-product and etchant gas are used to improve reliability of endpoint detection. For the OES data pre-processing, a combination of Signal to Noise Ratio (SNR) and Principal Component Analysis (PCA),are used. Polynomial Regression and Expanded Hidden Markov model (eHMM) technique are applied to pre-processed OES data to detect endpoint.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2
• /
• pp.145-152
• /
• 2003

In this paper, assuming that the score of speech utterance is the product of HMM log likelihood and HMM weight, we propose a new method that HMM weights are adapted iteratively like the general MCE training. The proposed method adjusts HMM weights for better performance using delta coefficient defined in terms of misclassification measure. Therefore, the parameter estimation and the Viterbi algorithms of conventional 1:.um can be easily applied to the proposed model by constraining the sum of HMM weights to the number of HMMs in an HMM set. Comparing with the general segmental MCE training approach, computing time decreases by reducing the number of parameters to estimate and avoiding gradient calculation through the optimal state sequence. To evaluate the performance of HMM-based speech recognizer by weighting HMM likelihood, we perform Korean isolated digit recognition experiments. The experimental results show better performance than the MCE algorithm with state weighting.