• ETRI Journal
• /
• v.29 no.3
• /
• pp.292-299
• /
• 2007

In this paper, we present a speech recognition system using a throat microphone. The use of this kind of microphone minimizes the impact of environmental noise. Due to the absence of high frequencies and the partial loss of formant frequencies, previous systems using throat microphones have shown a lower recognition rate than systems which use standard microphones. To develop a high performance automatic speech recognition (ASR) system using only a throat microphone, we propose two methods. First, based on Korean phonological feature theory and a detailed throat signal analysis, we show that it is possible to develop an ASR system using only a throat microphone, and propose conditions of the feature extraction algorithm. Second, we optimize the zero-crossing with peak amplitude (ZCPA) algorithm to guarantee the high performance of the ASR system using only a throat microphone. For ZCPA optimization, we propose an intensification of the formant frequencies and a selection of cochlear filters. Experimental results show that this system yields a performance improvement of about 4% and a reduction in time complexity of 25% when compared to the performance of a standard ZCPA algorithm on throat microphone signals.

• Journal of Digital Convergence
• /
• v.10 no.6
• /
• pp.219-224
• /
• 2012

In the communication mobile terminal, Vocabulary recognition system has low recognition rates, because this problems are due to phoneme feature extract from inaccurate vocabulary. Therefore they are not recognize the phoneme and similar phoneme misunderstanding error. To solve this problem, this paper propose the system model, which based on the two step process. First, input phoneme is represent by number which measure the distance of phonemes through phoneme likelihood process. next step is recognize the result through the reliability measure. By this process, we minimize the phoneme misunderstanding error caused by inaccurate vocabulary and perform error correction rate for error provrd vocabulary using phoneme likelihood and reliability. System performance comparison as a result of recognition improve represent 2.7% by method using error pattern learning and semantic pattern.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.21 no.3
• /
• pp.55-59
• /
• 1984

This paper describes a method of Hangout recognition using 2 - D digital filtering. The 170 patterns classified by the positions of the initial sound (consonant), middle sound (vowel) and terminal sound (consonant) of the 1,659 characters were established and models formed by using 2 - D digital filtering for each patterns were obtained. Based on these models we proposed an algorithm that can recognize KOREAN combinational characters by separating patterns from them with superpostion principles. As a result of simulation, 100% of recognition rate is obtained in the case of the print letter.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.13 no.2
• /
• pp.11-19
• /
• 1993

It is very essential to get the accurate classification of defects in primary pressure vessel weld for the safety of nuclear power plant. The signal analysis using the digital signal processing and pattern recognition is performed to classify UT defects extracting feature vector from ultrasonic signals. The minimum distance classifier and the maximum likelihood classifier based on statistics were applied in this experiment to discriminate ultrasonics data obtained form both the training specimens (slit, hole) and the testing specimens(crack, slag). The classification rate was measured using pattern classifier. Results of this study show the promise in solving the many flaw classification problems that exist today.

• Journal of Internet Computing and Services
• /
• v.4 no.3
• /
• pp.9-14
• /
• 2003

The method of vocal tract normalization is a successful method for improving the accuracy of inter-speaker normalization. In this paper, we present an intra-speaker warping factor estimation based on pitch alteration utterance. The feature space distributions of untransformed speech from the pitch alteration utterance of intra-speaker would vary due to the acoustic differences of speech produced by glottis and vocal tract. The variation of utterance is two types: frequency and amplitude variation. The vocal tract normalization is frequency normalization among inter-speaker normalization methods. Therefore, we have to consider amplitude variation, and it may be possible to determine the amplitude warping factor by calculating the inverse ratio of input to reference pitch. k, the recognition results, the error rate is reduced from 0.4% to 2.3% for digit and word decoding.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.208-212
• /
• 1998

This paper suggests the method to recognize the various defect patterns of cold mill strip using binary decision tree constructed by genetic algorithm automatically. In case of classifying the complex the complex patterns with high similarity like the defect patterns of cold mill strip, the selection of the optimal feature set and the structure of recognizer is important for high recognition rate. In this paper genetic algorithm is used to select a subset of the suitable features at each node in binary decision tree. The feature subset of maximum fitness is chosen and the patterns are classified into two classes by linear decision function. After this process is repeated at each node until all the patterns are classified respectively into individual classes. In this way , binary decision tree classifier is constructed automatically. After construction binary decision tree, the final recognizer is accomplished by the learning process of neural network using a set of standard p tterns at each node. In this paper, binary decision tree classifier is applied to recognition of the defect patterns of cold mill strip and the experimental results are given to show the usefulness of the proposed scheme.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.1958-1962
• /
• 2005

A driver's emotion is a very important factor of safe driving. This paper classified a driver's emotion into 3 major emotions, can be occur when driving a car: Surprise, Joy, Tired. And It evaluated the classifier using Hidden Markov Models, which have observation sequence as bio-signals. It used the 2-D emotional plane to classfiy a human's general emotion state. The 2-D emotional plane has 2 axes of pleasure-displeasure and arsual-relaxztion. The used bio-signals are Galvanic Skin Response(GSR) and Heart Rate Variability(HRV), which are easy to acquire and reliable. We classified several moving pictures into 3 major emotions to evaluate our HMM system. As a result of driving simulations for each emotional situations, we can get recognition rates of 67% for surprise, 58% for joy and 52% for tired.

• Journal of Korean Academy of Nursing Administration
• /
• v.16 no.3
• /
• pp.306-313
• /
• 2010

Purpose: This study was conducted to examine the factors associated with work related injuries of nurses in small and medium sized hospitals. Method: A cross-sectional survey was conducted with nurses in eight hospitals from October 2007 to January 2008. A questionnaire was designed to collect information on nurses' work related injuries, and individual and job related characteristics. The response rate was 65.1%. Data from 294 nurses were analyzed. Multiple logistic regression analysis was performed to determine factors associated with work related injuries. Result: Of the 294 nurses, 19.1% (n=56) responded as having at least one injury during their job performance. The logistic regression analysis revealed that the significant factors influencing work related injuries were job satisfaction, stress recognition, and hospital's location. Nurses with a higher job satisfaction were less likely to experience work related injuries (OR=0.58). Nurses with a higher stress recognition (OR=2.57) and those working at hospitals in metropolitan cities (OR=3.28) were more likely to experience work related injuries. Conclusions: The result of this study indicated that a substantial proportion of nurses in small and medium sized hospitals had experienced injuries related to nursing job. Interventions to prevent work related injuries among nurses should take into account the job satisfaction, stress recognition, and hospital characteristics.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.7B
• /
• pp.1361-1369
• /
• 1999

A hit-miss transform(HMT) using modified synthetic structuring elements(SEs) for distortion-invariant recognition of multiple objects is proposed. A fundamental problem in an HMT is the determination of the optimal SE needed to improve the false alarm rate, and detect distorted objects with various shapes. The proposed synthetic methods of SE provide good solutions against this problem. One is the multistage synthesis of each true class SE using only set theory, and the other is the multistage synthesis of each true class and false class SE using set theory and SDF(synthetic discriminant function) synthesis method. Simulation results show the proposed methods can be used for the recognition of distorted intraclass objects and the discrimination of similar interclass objects.

• MALSORI
• /
• no.65
• /
• pp.93-103
• /
• 2008

In this paper, we propose a method for optimizing a multiple pronunciation dictionary used for modeling pronunciation variations of non-native speech. The proposed method removes some confusable pronunciation variants in the dictionary, resulting in a reduced dictionary size and less decoding time for automatic speech recognition (ASR). To this end, a confusability measure is first defined based on the Levenshtein distance between two different pronunciation variants. Then, the number of phonemes for each pronunciation variant is incorporated into the confusability measure to compensate for ASR errors due to words of a shorter length. We investigate the effect of the proposed method on ASR performance, where Korean is selected as the target language and Korean utterances spoken by Chinese native speakers are considered as non-native speech. It is shown from the experiments that an ASR system using the multiple pronunciation dictionary optimized by the proposed method can provide a relative average word error rate reduction of 6.25%, with 11.67% less ASR decoding time, as compared with that using a multiple pronunciation dictionary without the optimization.