• MALSORI
• /
• no.44
• /
• pp.73-82
• /
• 2002

Channel distortion degrades the performance of speech recognizer in telephone environment. It mainly results from the bandwidth limitation and variation of transmission channel. Variation of channel characteristics is usually represented as baseline shift in the cepstrum domain. Thus undesirable effect of the channel variation can be removed by subtracting the mean from the cepstrum. In this paper, to improve the recognition performance of Korea connected digit telephone speech, channel compensation methods such as CMN (Cepstral Mean Normalization), RTCN (Real Time Cepatral Normalization), MCMN (Modified CMN) and MRTCN (Modified RTCN) are applied to the static MFCC. Both MCMN and MRTCN are obtained from the CMN and RTCN, respectively, using variance normalization in the cepstrum domain. Using HTK v3.1 system, recognition experiments are performed for Korean connected digit telephone speech database released by SITEC (Speech Information Technology & Industry Promotion Center). Experiments have shown that MRTCN gives the best result with recognition rate of 90.11% for connected digit. This corresponds to the performance improvement over MFCC alone by 1.72%, i.e, error reduction rate of 14.82%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.3
• /
• pp.115-127
• /
• 2006

The purpose of this paper is evaluation of various normalization methods and fusion algorithms in addition to pattern classification algorithms for multi-biometric systems. Experiments are performed using various normalization functions, fusion algorithms and pattern classification algorithms based on Biometric Scores Set-Releasel(BSSR1) provided by NIST. The performance results are presented by Half Total Error Rate (WTER). This study gives base data for the study on performance enhancement of multiple-biometric system by showing performance results using single database and metrics.

• Journal of Environmental Health Sciences
• /
• v.43 no.5
• /
• pp.412-421
• /
• 2017

Objectives: To establish a system for integrated risk assessment of EDCs in Korea, infrastructure for providing toxicity data of ecological media should be established. Some systems provide soil ecotoxicity databases along with aquatic ecotoxicity information, but a well-structured ecotoxicity database system is still lacking. Methods: Aquatic and soil ecotoxicological information were collected by a toxicologist based on a human readable data (HRD) format for collecting ecotoxicity data that we provided. Among these data, anomalies were removed according to database normalization theory. Also, the data were cleaned and encoded to establish a machine-readable data (MRD) ecotoxicity database system. Results: We have developed a multi-purpose ecotoxicity database model focusing on EDCs, ecological species, and toxic effects. Also, we have constructed a web-based data searching system to retrieve, extract, and download data with greater availability. Conclusions: The results of our study will contribute to decision-making as a tool for efficient ecological risk assessment of EDCs in Korea.

• Journal of Korea Multimedia Society
• /
• v.22 no.9
• /
• pp.1036-1045
• /
• 2019

Relational databases have a notion of normalization, in which the model for storing data is standardized according to the organization's business processes or data operations. However, the graph database is relatively early in this standardization and has a high degree of freedom in modeling. Therefore various models can be created with the same data, depending on the database designers. The essences of the graph database are two aspects. First, the graph database allows accessing relationships between the objects semantically. Second, it makes relationships between entities as important as individual data. Thus increasing the degree of freedom in modeling and providing the modeling developers with a more creative system. This paper introduces different graph models with test data. It compares the query performances by the results of response speeds to the query executions per graph model to find out how the efficiency of each model can be maximized.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.1
• /
• pp.8-14
• /
• 2002

In this paper, we realized a real-time text-independent speaker recognition system using gaussian mixture model, and applied frame level likelihood normalization method which shows its effects in verification system. The system has three parts as front-end, training, recognition. In front-end part, cepstral mean normalization and silence removal method were applied to consider speaker's speaking variations. In training, gaussian mixture model was used for speaker's acoustic feature modeling, and maximum likelihood estimation was used for GMM parameter optimization. In recognition, likelihood score was calculated with speaker models and test data at frame level. As test sentences, we used text-independent sentences. ETRI 445 and KLE 452 database were used for training and test, and cepstrum coefficient and regressive coefficient were used as feature parameters. The experiment results show that the frame-level likelihood method's recognition result is higher than conventional method's, independently the number of registered speakers.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.663-667
• /
• 1999

In this paper, we review the conventional speaker verification algorithm and present the text-dependent speaker verification system for application over telephone lines and its result of experiments. We apply blind-segmentation algorithm which segments speech into sub-word unit without linguistic information to the speaker verification system for training speaker model effectively with limited enrollment data. And the World-mode] that is created from PBW DB for score normalization is used. The experiments are presented in implemented system using database, which were constructed to simulate field test, and are shown 3.3% EER.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.9 no.2
• /
• pp.80-86
• /
• 2000

Although polishing process take 30-50% of whole process of manufacturing die and mold it has not been fully automat-ed yet. Considering current trend of manufacturing it is necessary to study on polishing automation. To accomplish automation reliable database must be developed. For developing it polishing mechanism should be defined and a general empirical formula that can be applied widely should be created. In this paper it is found that polishing process must be separated into 2 process such as removing cusp and getting fine surface process and the polishing parameter which is com-posed of major machining parameters and normalization of data can be applied efficiently in making reliable database.

• Journal of Korean Library and Information Science Society
• /
• v.36 no.2
• /
• pp.327-348
• /
• 2005

The purpose of this study is to emphasize the importance of index definition and to prepare the basis of optimal index in bibliographic retrieval system. For the purpose, this research studied a index extraction theory on index tag definition and index normalization from the bibliographic marc database and analyzed a retrieval utilization rate of extracted index. In this experiment, we divided index between text-type and code-type about the generated 29,219,853 indexes from 2,200,488 bibliographic records and analyzed utilization rate by the comparison of index-type and index term of web logs. According to the result, the text-type indexes such as title, author, publication, subject are showed high utilization rate while the code-type indexes were showed low utilization rate. So this study suggests that the unused index is removed from index definition to optimize index.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.4
• /
• pp.23-27
• /
• 2009

In this paper, we propose an effective compression method for electrocardiogram (ECG) signals. 1-D ECG signals are reconstructed to 2-D ECG data by period and complexity sorting schemes with image compression techniques to increase inter and intra-beat correlation. The proposed method added block division and mean-period normalization techniques on top of conventional 2-D data ECG compression methods. JPEG 2000 is chosen for compression of 2-D ECG data. Standard MIT-BIH arrhythmia database is used for evaluation and experiment. The results show that the proposed method outperforms compared to the most recent literature especially in case of high compression rate.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.1
• /
• pp.119-127
• /
• 2018

The formal data used in the business is managed in a table form without normalization due to lack of understanding and application of data modeling. If the balance of the database design is destroyed, it affects the speed of response to the data query, and the data obesity becomes high. In this paper, it is investigated how data obesity improved through database design through optimized data modeling. The data query path was clearly visualized by square design through data modeling based on the relationship between object (data) and object, from the radial and task - oriented isolation design where data obesity is excessive. In terms of data obesity, the obesity degree of the current research support database was 57.2%, but it was 16.2% in the new research support database, and the data obesity degree was reducd by 40.5%. In addition, by minimizing redundancy of data, the database has been improved to ensure the accuracy and integrity of the data.