• The KIPS Transactions:PartB
• /
• v.9B no.6
• /
• pp.765-774
• /
• 2002

The purpose of this paper is a design and implementation for korean character and pen-gesture recognition system in multimedia terminal, PDA and etc, which demand both a fast process and a high recognition rate. To recognize writing-types which are written by various users, the korean character recognition system uses a database which is based on the characteristic information of korean and the stroke information Which composes a phoneme, etc. In addition. it has a fast speed by the phoneme segmentation which uses the successive process or the backtracking process. The pen-gesture recognition system is performed by a matching process between the classification features extracted from an input pen-gesture and the classification features of 15 pen-gestures types defined in the gesture model. The classification feature is using the insensitive stroke information. i.e., the positional relation between two strokes. the crossing number, the direction transition, the direction vector, the number of direction code. and the distance ratio between starting and ending point in each stroke. In the experiment, we acquired a high recognition rate and a fart speed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.7
• /
• pp.618-627
• /
• 1990

In this paper a new algorithm for separation of contacting subpattern and connective feature extraction of strokes is proposed. This algorithm is able to classification of the type of contacting parts, connective feature extreaction of strokes, separate the phoneme of contacting parts between strokes, classify the character types by feature classification of connecting parts and analysis of connecting attribute. Also, shape normalize into formal patterns and decide on the input pattern from position value of bending feature of this normalized shape and make an recognition experiment by neural network using BEP learining algorithm. This algorithm represents the good achievement ratio by separation of phoneme, classification of character type, connective feature extraction of stroke and recognition experiment.

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.6
• /
• pp.323-329
• /
• 2010

The edit distance problem is finding the minimum number of edit operations to transform a string into another one. It is one of the important problems in algorithm research and there are some algorithms that compute an optimal edit distance for the one-dimensional languages such as the English alphabet. However, there are a few researches to find the edit distance for the more complicated language such as the Korean or Chinese alphabet. In this paper, we define the measure of the edit distance for the Korean alphabet with the phoneme classification system to improve the previous edit distance algorithm and present an algorithm for the edit distance problem for the Korean alphabet.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.18-21
• /
• 2003

In general it has been considered to be the difficult problem that we divide continuous speech into short interval with having identical phoneme quality. In this paper we used Gaussian Mixture Model (GMM) related to probability density to divide speech into phonemes, an initial, medial, and final sound. From them we peformed continuous speech recognition. Decision boundary of phonemes is determined by algorithm with maximum frequency in a short interval. Recognition process is performed by Continuous Hidden Markov Model(CHMM), and we compared it with another phoneme divided by eye-measurement. For the experiments result we confirmed that the method we presented is relatively superior in auto-segmentation in korean speech.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1
• /
• pp.31-39
• /
• 1995

In this paper, we have constructed phoneme discriminant filters [PDF] according to the linear discriminant function. These discriminant filters do not follow the heuristic rules by the experts but the mathematical methods in iterative learning. Proposed system. is based on the piecewise linear classifier and error correction learning method. The segmentation of speech and the classification of phoneme are carried out simutaneously by the PDF. Because each of them operates independently, some speech intervals may have multiple outputs. Therefore, we introduce the unified coefficients by the output unification process. But sometimes the output has a region which shows no response, or insensitive. So we propose time windows and median filters to remove such problems. We have trained this system with the 549 monosyllables uttered 3 times by 3 male speakers. After we detect the endpoint of speech signal using threshold value and zero crossing rate, the vowels and consonants are separated by the PDF, and then selected phoneme passes through the following PDF. Finally this system unifies the outputs for competitive region or insensitive area using time window and median filter.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.6-9
• /
• 2003

In this paper, we studied on the difference of speaker adaptation according to the phoneme classification for Korean Speech recognition. In order to study of speech adaptation according to the weight of difference of phoneme as recognition unit, we used SCHMM as recognition system. And Speaker adaptation method used in this paper was MAPE(Maximum A Posteriori Probability Estimation), Linear Spectral Estimation. In order to evaluate the performance of these methods, we used 10 Korean isolated numbers as the experimental data. It is possible for the first and the second methods to be carried out unsupervised learning and used in on-line system. And the first method was shown performance improvement over the second method, and hybrid adaptation showed the better recognition results than those which performed each method. And the result of Speaker adaptation using the variable weight according to the phoneme had better than the result using fixed weight.

• Speech Sciences
• /
• v.9 no.4
• /
• pp.265-274
• /
• 2002

In this paper we propose an automatic segmentation system that outputs the time alignment information of phoneme boundary using Viterbi search with HMM (Hidden Markov Model) and corrects these results by an UVS (unvoiced/voiced/silence) classification algorithm. We selecte a set of 39 monophones and a set of 647 extended phones for HMM models. For the UVS classification we use the feature parameters such as ZCR (Zero Crossing Rate), log energy, spectral distribution. The result of forced alignment using the extended phone set is 11% better than that of the monophone set. The UVS classification algorithm shows high performance to correct the segmentation results.

• Speech Sciences
• /
• v.3
• /
• pp.148-155
• /
• 1998

As an application of dimensional analysis in the theory of chaos and fractals, we studied and estimated the information dimension for various phonemes. By constructing phase-space vectors from the time-series speech signals, we calculated the natural measure and the Shannon's information from the trajectories. The information dimension was finally obtained as the slope of the plot of the information versus space division order. The information dimension showed that it is so sensitive to the waveform and time delay. By averaging over frames for various phonemes, we found the information dimension ranges from 1.2 to 1.4.

• The Journal of the Acoustical Society of Korea
• /
• v.12 no.1E
• /
• pp.71-77
• /
• 1993

패턴매칭 기법에 근거한 음성 인식 시스템은 크게 clustering 과정과 labeling 과정으로 구성된다. 본 논문에서는 Kohonen의 featrue map 알고리즘과 LVQ2 알고리즘을 각각 clusterer와 labeler로 하는 음소인식 시스템을 구성한다. 구성된 인식시스템의 성능을 향상시키기 위해서 수정된 LVQ2알고리즘(MLVQ2)을 제안한다. MLVQ2는 selective learning, LVQ2, perturbed LVQ2 그리고 기존의 LVQ2의 4단계 학습과정으로 구성된다. 제안된 음소 인식 알고리즘의 성능을 평가하기 위하여 LVQ2와 MLVQ2를 각각 사용하여 6가지의 한국어 음소군에 대한 feature map을 만든다. 음소인식 실험결과, LVQ2와 MLVQ2를 사용하는 경우 각각 60.5%와 65.4%의 인식률을 얻을 수 있었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.5
• /
• pp.1026-1035
• /
• 1997

In this paper, we studied for phoneme recognition using GPFN and PNN as a kind of RBFN. The structure of RBFN is similar to a feedforward networks but different from choosing of activation function, reference vector and learnign algorithm in a hidden layer. Expecially sigmoid function in PNN is replaced by one category included exponential function. And total calculation performance is high, because PNN performs pattern classification with out learning. In phonemerecognition experiment with 5 vowel and 12 consant, recognition rates of GPFN and PNN as a kind of RBFN reflected statistic characteristic of speech are higher than ones of MLP in case of using test data and quantizied data by VQ and LVQ.