• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.5
• /
• pp.528-533
• /
• 2010

Currently the telephone service using Internet grows and the recent introduction of a smart phone is expected to accelerate the trend. In particular, considering the domestic situation that the wireless broadband (WiBro) system deployed over the nation, the telephone service over WiBro can be a solution toward its fast expansion. Unlike telephone service over a conventional telephone network or mobile network, however, internet telephone cannot guarantee it service quality, which can be severer in a wireless environment such as a WiBro network. Therefore, a more strict and systematic management for controlling the quality of internet telephone service over WiBro in a more efficient way. As the first step to establish the management system, this paper proposes a scheme to manage the quality of internet telephone service over WiBro and introduces a software developed for the purpose. The developed software is installed on a user terminal and facilitates efficient service quality management by measuring the quality of internet telephone service over WiBro in terms of VoIP metric, network metric, and wireless metric.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.810-818
• /
• 2010

This paper presents a new framework for integrating untranscribed spoken content into the acoustic training of an automatic speech recognition system. Untranscribed spoken content plays a very important role for under-resourced languages because the production of manually transcribed speech databases still represents a very expensive and time-consuming task. We proposed two new methods as part of the training framework. The first method focuses on combining initial acoustic models using a data-driven metric. The second method proposes an improved acoustic training procedure based on unsupervised transcriptions, in which word endings were modified by broad phonetic classes. The training framework was applied to baseline acoustic models using untranscribed spoken content from parliamentary debates. We include three types of acoustic models in the evaluation: baseline, reference content, and framework content models. The best overall result of 18.02% word error rate was achieved with the third type. This result demonstrates statistically significant improvement over the baseline and reference acoustic models.

• Journal of Software Engineering Society
• /
• v.25 no.3
• /
• pp.59-62
• /
• 2012

We propose a novel metric for quantitatively comparing different clustered results generated from software clustering algorithms. A quantitative evaluation of software clustering helps understanding of architectural changes of software. The concept of split, which has been used for analysis of genetic characters in bio-informatics, is applied in the analysis of software architecture.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.130-133
• /
• 2020

Smart pig farm which is based on IoT has been widely adopted by many pig farmers. In order to achieve optimal control of smart pig farm, the relation between environmental conditions and performance metric should be characterized. In this study, the relation between multiple environmental conditions including temperature, humidity and various performance metrics, which are daily gain, feed intake, and MSY, is analyzed based on data obtained from 55 real pig farm. Especially, based on preprocessing of data, various regression based machine learning algorithms are considered. Through performance evaluation, we show that the performance can be predicted with high precision, which can improve the efficiency of management.

• The KIPS Transactions:PartD
• /
• v.9D no.5
• /
• pp.897-902
• /
• 2002

Because of rapid evolution of software technique, numerous software professionals have been concerned with component based development methodologies. However, it is hard to find out a systematic technique for the selection of COTS (Commercial Off The Shelf) component in consumer position. Up to date, the major of component quality evaluation is object-oriented metric based evaluation methodology. But this paper present four step process and evaluation criteria based on MCDM (Multiple Criteria Decision Making) technique for optimal COTS component selection in consumer position. We considered funtionality, efficiency, usability based on IS0/IEC 9126 for Quality measurement and executed practical analysis about commercial EJB component in internet. This paper show that the proposed selection technique is applicable to optimal COTS component selection.

• The KIPS Transactions:PartD
• /
• v.10D no.5
• /
• pp.821-828
• /
• 2003

Package software should have the feature that enables purchasers to discriminate a product suitable for them among a number of software belonging to the similar kind of product. Purchaser's ability to choose a package software depends on whether they can judge that a package software conforms to the relevant standard through an objective quality test process and method or not. There are the standards that can be applicable to the quality evaluation of package software, such as and . This study developed a system with which purchasers can effectively select a package software suitable for their needs, building quality test process for package software and developing test metric and application method.

• Convergence Security Journal
• /
• v.14 no.4
• /
• pp.55-60
• /
• 2014

In this study, we propose a cryptographic module quality evaluation system referenced by ISO/IEC 9000 quality system with Quality, Quality Factor, Quality Subfactor, Metric. Practical application process encryption algorithm based on the encryption algorithm to encrypt the pros and cons valuation of diagnosis, point selection algorithm, analysis, and quality items(quality factor), eliciting constraints derived, such as the cryptographic module design quality evaluation system is set to step 5. The five steps are examples of field-based diagnostic tool for cryptographic operations, the most essential work to be done in order to derive one will work. 2-Factor encryption module for connection between indicator items(quality factor) to identify and ensure the quality of the item the constraints of the environment are two kinds of cryptographic operations. This study is an encryption module and a practical field application system, it presents the standardized model. We have to meet the rapid changes in information technology. The environment, development and the encryption algorithm applied to model a wide variety of on-site development encryption will be able to expect the efficiency.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.176-182
• /
• 2021

This paper evaluates and compares the performance of the Deep Nerual Network (DNN)-based speech enhancement models according to various loss functions. We used a complex network that can consider the phase information of speech as a baseline model. As the loss function, we consider two types of basic loss functions; the Mean Squared Error (MSE) and the Scale-Invariant Source-to-Noise Ratio (SI-SNR), and two types of perceptual-based loss functions, including the Perceptual Metric for Speech Quality Evaluation (PMSQE) and the Log Mel Spectra (LMS). The performance comparison was performed through objective evaluation and listening tests with outputs obtained using various combinations of the loss functions. Test results show that when a perceptual-based loss function was combined with MSE or SI-SNR, the overall performance is improved, and the perceptual-based loss functions, even exhibiting lower objective scores showed better performance in the listening test.

• Phonetics and Speech Sciences
• /
• v.1 no.3
• /
• pp.73-85
• /
• 2009

This paper introduces the technique of synthesizing and evaluating human utterances with exaggerated or atypical prosody. Prosody exaggeration can be implemented by manipulating either the fundamental frequency (F0) contour, the segmental durations, or the intensity contour of an utterance. Of these three prosodic elements, two or more can be exaggerated at the same time. The algorithms of synthesis and evaluation were suggested. Learner utterances exaggerated in each of the three prosodic features were evaluated with respect to their original native versions in terms of the differences in their F0 contours, the segmental durations, and the intensity contours. The measure of differences was the Euclidean distance metric between the matching points in their F0 and intensity contours. The measure was calculated after the exaggerated learner utterances were aligned by the segments and rendered identical to their native version in terms of their segmental durations. For the evaluation of the segmental durations, no prior modifications were made in durations and the same measure was used. The results from the pilot experiment suggest the viability of this measure in the evaluation of learner utterances with atypical prosody with respect to their native versions.

• The KIPS Transactions:PartD
• /
• v.11D no.3
• /
• pp.659-670
• /
• 2004

It is possible to implement high quality system which coincided with embedded system purchaser's requirements by quality test. The concrete quality test system applicable within our country for embedded software was not constructed yet. Recently, various embedded systems are developed, but they have many problems such as recall by defect. In this paper, we developed evaluation modules and quality test fables which can implement duality test based on ISO/IEC 12119 for embedded software evaluation.