• The Journal of the Acoustical Society of Korea
• /
• v.41 no.6
• /
• pp.655-661
• /
• 2022

Since speech impairment is prevalent in patients with Parkinson's disease (PD), speech recognition systems suitable for these patients are needed. In this paper, we propose a speech recognition system that effectively recognizes the speech of patients with PD. The speech recognition system is firstly pre-trained with the Globalformer using the speech data from healthy people, and then fine-tuned using relatively small amount of speech data from the patient with PD. For this analysis, we used the speech dataset of healthy people built by AI hub and that of patients with PD collected at Inha University Hospital. As a result of the experiment, the proposed speech recognition system recognized the speech of patients with PD with Character Error Rate (CER) of 22.15 %, which was a better result compared to other methods.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.3
• /
• pp.64-72
• /
• 1997

In this paper, study and experiments are performed for finding recognition unit fit which can be used in large vocabulary recognition system. Specifically, a phoneme that is currently used as recognition unit and a syllable in which Korean is well characterized are selected. From comparisons of recognition experiments, the study is performed whether a syllable can be considered as recognition unit of Korean recognition system. For report of an objective result of the comparison experiment, we collected speech data of a male speaker and processed them by hand-segmentation for phoneme boundary and labeling to construct speech database. And for training and recognition based on HMM, we used HTK (HMM Tool Kit) 2.0 of commercial tool from Entropic Co. to experiment in same condition. We applied two HMM model topologies, 3 emitting state of 5 state and 6 emitting state of 8 state, in Continuous HMM on training of each recognition unit. We also used 3 sets of PBW (Phonetically Balanced Words) and 1 set of POW(Phonetically Optimized Words) for training and another 1 set of PBW for recognition, that is "Speaker Dependent Medium Vocabulary Size Recognition." Experiments result reports that recognition rate is 95.65% in phoneme unit, 94.41% in syllable unit and decoding time of recognition in syllable unit is faster by 25% than in phoneme.

• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.3-8
• /
• 2023

The Fourth Industrial Revolution is bringing about great changes in many industrial fields, and among them, active research is being conducted on convergence technology using artificial intelligence. Among them, the demand is increasing day by day in the field of object recognition using artificial intelligence and digital transformation using recognition results. In this paper, we proposed an optimal learning model construction method to accurately recognize letters, symbols, and lines in images and save the recognition results as files in a standardized format so that they can be used in simulations. In order to recognize letters, symbols, and lines in images, the characteristics of each recognition target were analyzed and the optimal recognition technique was selected. Next, a method to build an optimal learning model was proposed to improve the recognition rate for each recognition target. The recognition results were confirmed by setting different order and weights for character, symbol, and line recognition, and a plan for recognition post-processing was also prepared. The final recognition results were saved in a standardized format that can be used for various processing such as simulation. The excellent performance of building the optimal learning model proposed in this paper was confirmed through experiments.

• Journal of Korean Home Economics Education Association
• /
• v.22 no.2
• /
• pp.31-43
• /
• 2010

We investigated the extent of recognition and the rate of class practice on the contents relevant to the environmental education in the units of 'Clothing Life' of the 7th 'Technology-Home Economics' curriculum in Korean middle school teachers. Two hundred sixty teachers, who had taught the units of 'Clothing Life' and responded to the questionnaires by mail from December 2007 to January 2008, were enrolled and each item in the questionnaires was analyzed in this study. Most teachers recognized the serious environmental issues in their residential area resulting in a harmful influence on their lives. Also they exhibited increased practice will such as joining to the environmental organizations and showed high practice of the environmental preservation. They commented relatively high rate of class practice on the contents relevant to the environmental education and enhanced practice of the environmental preservation in all units of 'Clothing Life' of the 7th 'Technology-Home Economics' curriculum except the units of 'Clothing Skill and Dress Clothes' and 'Simple Clothes Making'. Moreover, teachers with higher age and longer teaching career had the higher level of recognition and the greater rate of class practice on the environmental education compared to those without. Teachers should try to raise the students' recognition and practice will on the environmental issues in the class of 'Clothing Life' of the 7th 'Technology-Home Economics' curriculum in Korean middle school.

• Korean Journal of Health Education and Promotion
• /
• v.16 no.2
• /
• pp.19-40
• /
• 1999

In order to ascertain the attitudes of residents to their health and the National Health Promotion Law, surveyors interviewed 1,220 subjects, 1% of men and women in Kyungsan city, who were twenty-year-old or more. The major findings are as follows: Men and women were 48.2% and 51.8%, respectively. The recognition rate of enacting and enforcing this law is 59.2% of men and 51.3% of women. With regard to the behavioral attitude to the health in the distinction of sex and age, current smokers are 31.2% of the interviewees, 61.6% of the men and 3.3% of the women. Current drinkers are 35.1%, 59.5% of the men and 12.3% of the women, but on the other hand there is little significance in the distinction of age. The acknowledgement proportion of enacting and enforcing this law is 59.2% of male and 51.3% of female. In terms of the recognition rate of the contents according to the general characteristics of interviewees, it appears that the indication of a warning expression on a packing paper of cigarette case and a liquor bottle is 92.4% and also the designation of a smoking free area in public facilities is 94.8%. Prohibition of cigarette-sale to the teenagers who are under 19, is 96.0%. Considering these facts, the recognition rate is high. On the contrary, 48.8% is accounted for encouraging a medical check-up before marriage which is in a low position. As a result of multiple behavior as a independent educational level, marital significant variables. In case of having undergone a periodic medical examination the recognition rate was high whereas frequent exercise led to the low recognition rate. Concerning the details of the undertaking in accordance with each factor of general characteristics, the greater part of them have been appraised successfully whether it is recognized or not. On the other side, no effect got answered about the result of the undertaking subjects to general and peculiar behavior attitude towards health was in effect or not. A great majority approved of more reinforcement of legal regulation about smoking and drinking regardless of whether they perceived the details of the law of promotion of National Health Promotion Law or not. Additionally there was significant difference in reinforcing legal regulation of smoking and drinking in compliance with the attitude of the substance of this law. With regard to education, public relations and evaluation about national health through public health centers by our government, the younger and the higher in education they are, the more deficient they feel. First of all, those who were aware of the enforcement of this law as well as plenty of scarcity answered that better service of disease prevention had to be expanded than ever. In consideration of the above-stated results, the education to public health and the business of public relations should be reinforced and a practical campaign for health life should also spread out for the purpose of encouraging to practise healthy life-style.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.3
• /
• pp.344-355
• /
• 2002

Having a variety of good characteristics against other pattern recognition techniques, Multilayer Perceptron (MLP) has been used in wide applications. But, it is known that Error Backpropagation (EBP) algorithm which MLP uses in learning has a defect that requires relatively long leaning time. Because learning data in pattern recognition contain abundant redundancies, in order to increase learning speed it is very effective to use online-based teaming methods, which update parameters of MLP pattern by pattern. Typical online EBP algorithm applies fixed learning rate for each update of parameters. Though a large amount of speedup with online EBP can be obtained by choosing an appropriate fixed rate, fixing the rate leads to the problem that the algorithm cannot respond effectively to different leaning phases as the phases change and the learning pattern areas vary. To solve this problem, this paper defines learning as three phases and proposes a Instant Learning by Varying Rate and Skipping (ILVRS) method to reflect only necessary patterns when learning phases change. The basic concept of ILVRS is as follows. To discriminate and use necessary patterns which change as learning proceeds, (1) ILVRS uses a variable learning rate which is an error calculated from each pattern and is suppressed within a proper range, and (2) ILVRS bypasses unnecessary patterns in loaming phases. In this paper, an experimentation is conducted for speaker verification as an application of pattern recognition, and the results are presented to verify the performance of ILVRS.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1183-1186
• /
• 2004

In the steel production line, the molten metal of a furnace is transformed into billet and then moves to the heating furnace of the hot rolling mill. This paper describes about the realtime billet characters recognition system in the steel production line. Normally, the billets are mixed at yard so that their identifications are very difficult and very important processing. The character recognition algorithm used in this paper is base on the subspace method by K-L transformation. With this method, we need no special feature extraction steps, which are usually error prone. So the gray character images are directly used as input vectors of the classifier. To train the classifier, we have extracted eigen vectors of each character used in the billet numbers, which consists of 10 arabia numbers and 26 alphabet aharacters, which are gathered from billet images of the production line. We have developed billet characters recognition system using this algorithm and tested this system in the steel production line during the 8-days. The recognition rate of our system in the field test has turned out to be 94.1% (98.6% if the corrupted characters are excluded). In the results, we confirmed that our recognition system has a good performance in the poor environments and ill-conditioned marking system like as steel production plant.

• The Journal of the Acoustical Society of Korea
• /
• v.33 no.4
• /
• pp.268-272
• /
• 2014

This paper presents a method for speech recognition using multi-section vector-quantization (MSVQ) and time-delay recurrent neural network (TDTNN). The MSVQ generates the codebook with normalized uniform sections of voice signal, and the TDRNN performs the speech recognition using the MSVQ codebook. The TDRNN is a time-delay recurrent neural network classifier with two different representations of dynamic context: the time-delayed input nodes represent local dynamic context, while the recursive nodes are able to represent long-term dynamic context of voice signal. The cepstral PLP coefficients were used as speech features. In the speech recognition experiments, the MSVQ/TDRNN speech recognizer shows 97.9 % word recognition rate for speaker independent recognition.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.5 no.2
• /
• pp.77-85
• /
• 2009

In this paper, we propose data format for smell, taste, touch with speech and vision which can be transmitted and implement a floral scent detection and recognition system. We provide representation method of data of smell, taste, and touch. Also, proposed floral scent recognition system consists of three module such as floral scent acquisition module using Metal Oxide Semiconductor (MOS) sensor array, entropy-based floral scent detection module, and floral scent recognition module using correlation coefficients. The proposed system calculates correlation coefficients of the individual sensor between feature vector(16 sensors) from floral scent input point until the stable region and 12 types of reference models. Then, this system selects the floral scent with the maximum similarity to the calculated average of individual correlation coefficients. To evaluate the floral scent recognition system using correlation coefficients, we implemented an individual floral scent recognition system using K-NN with PCA and LDA that are generally used in conventional electronic noses. In the experimental results, the proposed system performs approximately 95.7% average recognition rate.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.1
• /
• pp.160-164
• /
• 2005

The process of recognizing a vehicle involves detection of the vehicle, recognition of the vehicle model, and identification of the vehicle. The process of vehicle identification involves identification of the vehicle itself, such as by recognition of the license plate on the vehicle. In this paper the method involves the use of a beam splitter to divide incident rays into two directions, a transmitted beam and a reflected beam of different light intensities, and synthesizing two captured images using CCD devices from each beam, thus producing fluctuation-free images of a wide dynamic range even when the subject is moving. A prototype license plate recognition system was also developed using the experimental sensing device. The system achieved a 98.7% recognition rate on 466 images of moving vehicles, which demonstrates its effectiveness as a license plate recognition system.