• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.2
• /
• pp.129-136
• /
• 2020

Recognizing finger movements have been used as a intuitive way of human-computer interaction. In this study, we implement an wearable device for finger motion recognition and evaluate the accuracy of several ML (Machine learning) techniques. Not only HMM (Hidden markov model) and DTW (Dynamic time warping) techniques that have been traditionally used as time series data analysis, but also NN (Neural network) technique are applied to compare and analyze the accuracy of each technique. In order to minimize the computational requirement, we also apply the pre-processing to each ML techniques. Our extensive evaluations demonstrate that the NN-based gesture recognition system achieves 99.1% recognition accuracy while the HMM and DTW achieve 96.6% and 95.9% recognition accuracy, respectively.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.10
• /
• pp.1000-1004
• /
• 2010

A large number of current language processing systems use a part-of-speech tagger for preprocessing. Most language processing systems required a tagger with the highest possible accuracy. Specially, the use of domain-specific advantages has become a hot issue in machine translation community to improve the translation quality. This paper addresses a method for customizing an HMM or LHMM based English tagger from general domain to specific domain. The proposed method is to semi-automatically customize the output and transition probabilities of HMM or LHMM using domain-specific raw corpus. Through the experiments customizing to Patent domain, our LHMM tagger adapted by the proposed method shows the word tagging accuracy of 98.87% and the sentence tagging accuracy of 78.5%. Also, compared with the general tagger, our tagger improved the word tagging accuracy of 2.24% (ERR: 66.4%) and the sentence tagging accuracy of 41.0% (ERR: 65.6%).

• 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 Korea Institute of Information and Communication Engineering
• /
• v.11 no.8
• /
• pp.1596-1603
• /
• 2007

In this paper, we experimented by three kind of method for feature parameter, training method and recognition algorithm of most suitable for speech recognition system and considered. We decided speech recognition system of most suitable through two kind of experiment after we make speech recognizer. First, we did an experiment about three kind of feature parameter to evaluate recognition performance of it in speech recognizer using existent MFCC and MFCC new feature parameter that change characteristic space using PCA and ICA. Second, we experimented recognition performance or HMM, SVM and RVM by studying data number. By an experiment until now, feature parameter by ICA showed performance improvement of average 1.5% than MFCC by high linear discrimination from characteristic space. RVM showed performance improvement of maximum 3.25% than HMM in an experiment by decrease of studying data. As such result, effective method for speech recognition system to propose in this paper derives feature parameters using ICA and un recognition using RVM.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.151-160
• /
• 2023

The Hadith is the second source of Islamic jurisprudence after Qur'an. Both sources are indispensable for muslims to practice Islam. All Ahadith are collected and are written. But most books of Hadith contain Ahadith that can be weak or rejected. So, quite a long time, scholars of Hadith have defined laws, rules and principles of Hadith to know the correct Hadith (Sahih) from the fair (Hassen) and weak (Dhaif). Unfortunately, the application of these rules, laws and principles is done manually by the specialists or students until now. The work presented in this paper is part of the automatic treatment of Hadith, and more specifically, it aims to automatically process the chain of narrators (Hadith Isnad) to find its different components and affect for each component its own tag using a statistical method: the Hidden Markov Models (HMM). This method is a power abstraction for times series data and a robust tool for representing probability distributions over sequences of observations. In this paper, we describe an important tool in the Hadith isnad processing: A chunker with HMM. The role of this tool is to decompose the chain of narrators (Isnad) and determine the tag of each part of Isnad (POI). First, we have compiled a tagset containing 13 tags. Then, we have used these tags to manually conceive a corpus of 100 chains of narrators from "Sahih Alboukhari" and we have extracted a lexicon from this corpus. This lexicon is a set of XML documents based on HPSG features and it contains the information of 134 narrators. After that, we have designed and implemented an analyzer based on HMM that permit to assign for each part of Isnad its proper tag and for each narrator its features. The system was tested on 2661 not duplicated Isnad from "Sahih Alboukhari". The obtained result achieved F-scores of 93%.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.1
• /
• pp.56-61
• /
• 2010

This paper describes optimization methods of acoustic models in HMM-based continuous speech recognition. Most of the conventional speech recognition systems use the same number of Gaussian mixture components for each HMM state. However, since the number of data samples available for each state is different from each other, it is possible to reduce the overall number of model parameters and the computational cost at the decoding step by optimizing the number of Gaussian mixture components. In this study, we introduced the Gaussian mixture weight term at the merging stage of Gaussian components in the minimum description length (MDL) based acoustic modeling optimization. Experimental results showed that the proposed method can obtain better ASR accuracy than the previous optimization method which does not consider the Gaussian mixture weight term.

• MALSORI
• /
• no.62
• /
• pp.97-112
• /
• 2007

The speech recognizer in general operates in noisy acoustical environments. Many research works have been done to cope with the acoustical variations. Among them, the multiple-HMM model approach seems to be quite effective compared with the conventional methods. In this paper, we consider a multiple-model approach combined with the model compensation method and investigate the necessary number of the HMM model sets through noisy speech recognition experiments. By using the data-driven Jacobian adaptation for the model compensation, the multiple-model approach with only a few model sets for each noise type could achieve comparable results with the re-training method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.739-741
• /
• 2004

얼굴인식 기술 분야에 있어서 Haar-like feature를 이용한 얼굴 검출 알고리즘은 많은 관련 알고리즘 중에 매우 빠른 트레이닝 시간과 처리속도 향상의 장점을 가지고 있다 그러므로 특히 동영상에서의 얼굴 검출에서 유용하게 쓰일 수 있다. 이러한 방법으로 검출된 얼괄 데이터는 HMM(Hidden Markov Model)알고리즘을 이용하여 이미 트레이닝된 얼굴 데이터베이스와의 비교를 통해 얼굴인식에 있어서 가장 확률이 높은 사람을 본인의 얼굴로 인증하는 신원 확인 시스템을 구현할 수 있게 된다. 신원 확인 시스템에 있어서 얼굴 검출 율이나 신원 확인 성공률은 모두 학습 과정에 의해 결정되기 때문에 얼마나 많은 학습을 효율적으로 하느냐에 따라 성능이 좌우된다. 이러한 시스템은 카메라에 얼굴을 보여주는 것만으로 신원 확인이 가능하기 때문에 번거로운 신원 확인 과정을 거쳐야 하는 다른 시스템 구조에 비해 매우 편리한 기능을 제공할 수 있다.

• Phonetics and Speech Sciences
• /
• v.4 no.3
• /
• pp.111-117
• /
• 2012

In this paper, we compare the performance of several speaker adaptation methods for a HMM-based Korean speech synthesis system with small amounts of adaptation data. According to objective and subjective evaluations, a hybrid method of constrained structural maximum a posteriori linear regression (CSMAPLR) and maximum a posteriori (MAP) adaptation shows better performance than other methods, when only five minutes of adaptation data are available for the target speaker. During the objective evaluation, we find that the duration models are insufficiently adapted to the target speaker as the spectral envelope and pitch models. To alleviate the problem, we propose the duration rectification method and the duration interpolation method. Both the objective and subjective evaluations reveal that the incorporation of the proposed two methods into the conventional speaker adaptation method is effective in improving the performance of the duration model adaptation.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.77-80
• /
• 2000

In this paper, the speaker-recognition process based on both DTW and discrete HMM was performed using the method to evaluate state-dependent parameter weighting from training data so as the personal audio-characteristics are to be well reflected. In the suggested method below, we found the optimal state sequence using the Viterbi algorithm. The optimal path could be evaluated after comparing the sequence of base pattern which already have, with that of the other patterns. After that the frame of which the pattern was matched with the base pattern in the same state are to be found so that the reference pattern can be gained by weighting on the numbers of matched frames.