• 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.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.16 no.1
• /
• pp.23-27
• /
• 2005

Background and Objectives : Voice disorders can cause problems in patients with benign vocal cord lesions emotionally, physically, economically and functionally. Neither subjective nor objective voice examinations can evaluate such factors adequately. The Voice Handicap Index (VHI) subjectively evaluates voice disorders in terms of physical, functional, emotional factors and measures the patient's perception of the impact of voice disorder. The purpose of this study is to evaluate the usefulness of VHI in the patients with benign vocal cord lesions. Materials and Method : The authors evaluated 37 patients who experienced laryngeal microsurgery for benign vocal cord lesions from september 2003 to August 2004. The VHI was used to measure the postoperative changes of the patient's perception and acoustic analysis and aerodynamic tests were also done. Statistical analysis was done using paired t-test and Pearson's correlation. Results : The VHI scores showed statistically significant reductions postoperatively. In acoustic analysis, jitter and shimmer had statistically significant reductions after surgery but noise-to-harmonics ratio did not. A statistically significant change in the average MFR and MPT perioperatively was found. The relationship between VHI and acoustic, aerodynamic analysis attained statistical significance. Conclusion : The VHI is a useful assessment tool to monitor the patient's self-perception of voice change after the surgery of benign vocal cord lesions. The VHI measurement, when combined with acoustic and aerodynamic analyses, will be helpful in comparing functional outcomes after voice surgery.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.5
• /
• pp.13-20
• /
• 2008

Although digital hearing aid algorithms have been developed to compensate hearing loss and to help hearing impaired people to communicate with others, digital hearing aid user still complain about difficulty of hearing the speech. The reason could be the quality of speech through digital hearing aid is insufficient to understand the speech caused by feedback, residual noise and etc. And another thing is masking effect among formants that makes sound quality low. In this study, we measured the masking characteristics of normal listeners and hearing impaired listeners having presbyacusis to confirm masking effect in speech itself. The experiment is composed of 5 tests; pure tone test, speech reception threshold (SRT) test, word recognition score (WRS) test, puretone masking test and speech masking test. In speech masking test, there are 25 speeches in each speech set. And log likelihood ratio (LLR) is introduced to evaluate the distortion of each speech objectively. As a result, the speech perception became lower by increasing the quantity of formant enhancement. And each enhanced speech in a speech set has statistically similar LLR, however speech perception is not. It means that acoustic masking effect rather than distortion influences speech perception. In actuality, according to the result of frequency analysis of the speech that people can not answer correctly, level difference between first formant and second formant is about 35dB, and it is similar to result of pure tone masking test(normal hearing subject:36.36dB, hearing impaired subject:32.86dB). Characteristics of masking effect is not similar between normal listeners and hearing impaired listeners. So it is required to check the characteristics of masking effect before wearing a hearing aid and to apply this characteristics to fitting.

• Journal of agricultural medicine and community health
• /
• v.25 no.1
• /
• pp.1-9
• /
• 2000

A public perception survey of environmental health due to small-scale industries was conducted in Sudong Myun, Namyangju City, Kyungki Do, recently being changed to industrialized rural community. This survey had the purpose to ascertain public interest, to identify public needs, and to assess participation for environmental health programs of rural community. The results of survey were as follows: 1. The rate of the respondents with factory worker 19.4% and half(53.1%) of respondents had lived nearby the factory. 2. Some respondents were not favor their neighboring factories(30.1%) and have discussed about its environmental problems in community meeting(14.4%) especially in neighborhood adjacent factories. 3. The respondents have perceived that: (1) major problems were water contamination, air pollution, nasty odor, dust, and noise (2) health problems were more serious in employees than in other residents (3) the employers were responsible for environmental problems (4) the health service should provided by public health center channel and participated by the residents (5) most important service for workers was improvement of working conditions. We hope the community environmental and/or occupational health delivery system for the employees and residents will be developed true public health center channel in a rural community on the basis of this result.

• Korean Security Journal
• /
• no.42
• /
• pp.309-334
• /
• 2015

Now it is a proper time to discuss on the issue of crisis negotiation more in-depth. Thus far, studies on crisis negotiations have been mere manual style guidelines of "what to do". More substantial and rigorous theoretical propositions and empirical studies await for the future development of crisis negotiation field. This article contributes to the theoretical enrichment of the study of crisis negotiation field. Conventionally, two problems of misperceptions are raised in crisis negotiation. For instance, even though two parties used the same word, there can appear a substantial difference. Even worse, in many cases parties of negotiation send misinformation intentionally or unintentionally. This noise of communication can cause a serious misperception for parties of crisis negotiation including police officers, perpetrators, and hostages. However, this issue has not yet discussed in the field of crisis negotiation in Korea. This paper pointed out such important but not yet focused issue. It first discusses about the problem of perception and misperception. Next, it presents the negative impacts of such perception and misperception in crisis negotiation communication. Finally, it suggests the policy implications.

• Journal of KSNVE
• /
• v.11 no.3
• /
• pp.461-470
• /
• 2001

A friction-type clutch system sometimes generates spick-slip vibration during engagement, which disturbs smooth start of a car and makes a passenger uncomfortable. In this study, the spick-slip vibration in four types of friction couples was investigated at two different engagement conditions respectively of which the amount of slip time and clutch travel was varied. Results are found as follows. First, the vibration increased at the condition of small engine torque and large torque fluctuations due to higher harmonics of engine speed. Second, the friction couple without a pre-damper has advantages of reducing the vibration. This study also suggested an evaluation method of vehicle vibration in the view point of human perception by using the frequency weighting of ISO2631-1.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.6
• /
• pp.1125-1132
• /
• 2012

The researches on driver assistance systems that can prevent an accident have been actively performed due to social issues of traffic accidents with development of vehicle industry in recent. It is required for researchers to develope systems which assist driver's perception and judgment when considering that over 70% of traffic accidents occur by drivers' carelessness and 75% of the total accidents occur at the speed of less 29km per hour. In this paper, we implemented a front and rear vehicle monitoring system that monitors distance from a vehicle to obstacles in real-time at the low-speed or back-ward driving. The proposed system consists of ultrasonic sensors of high angle and wide angle of beam spread, ATmega128, and DSP processor.

• Journal of the Korean Society of Food Culture
• /
• v.20 no.4
• /
• pp.438-445
• /
• 2005

This research examines how various dimensions of physical environments influence patrons' psychological responses(especially emotional responses) in the restaurant service setting, and how these emotional responses, in turn, influence patrons' attitude formation. The result of empirical research indicates that restaurant physical environments have a significant effect patrons' emotional responses, and that these psychological experiences serve as critical mediators in the restaurant physical environments-store attitudes relationship. However, the effects of restaurant physical environments on patrons' psychological responses varied with the dimensions of physical environments. First, the effect of cleanliness on emotional responses was most significant, especially on negative emotion, out of 4 dimension of restaurant physical environment. Second, ambient conditions are the most important predictor on customers' positive emotion, and in turn, positive emotion has the most significant effects on customers' attitude formation of restaurant. Therefore, the result suggests that restaurants should manage(or, improve) their ambient conditions(e.g. background music, scents, ventilation, noise etc.) for efficiently maximizing customers' positive attitude. The implications of this study are discussed, and ideas for future work suggested.

• MALSORI
• /
• no.53
• /
• pp.1-16
• /
• 2005

This experimental study aims to test the hypothesis that the occurrence of English sentence-final stop release is, at least, partly predictable by examining its phonetic context. 10 native(5 male and 5 female) speakers of American English recorded, in a sound-proof booth, sentences excerpted from novels and the natural documents on the World Wide Web. Based on the waveforms and spectrograms of the recorded sentences, judgements of the release of a sentence-final stop were made. If the aperiodic energy of a given final stop lasted more than .015 second, it was considered to be "released." The result reveals that English sentence-final stops tend to be released when they are 1) velar consonants, 2) preceeded by tense vowels, and 3) coda consonants of content words. The phonetic environment in which final stops are often released can be characterized by the articulatory comfortableness and the need for release burst noise, without which the final stops may not be correctly perceived. By examining the release of English final stops, it is concluded that the phonological events, which had been considered to occur rather "randomly," in fact, reflect the universal tendency of human speech: to minimize the speakers' and hearers' effort.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1043-1064
• /
• 2020

A kind of Subjective Imaging Effect Assessment (SIEA) method and its applications on intelligent imaging terminal design in engineering site are presented. First, some visual assessment indices are used to characterize the imaging effect: the image brightness, the image brightness uniformity, the color image contrast, the image edge blur, the image color difference, the image saturation, the image noise, and the integrated imaging effect index. A linear weighted function is employed to carry out the SIEA computation and the Analytic Hierarchy Process (AHP) technique is used to estimate its weights. Second, a SIEA software is developed. It can play images after the settings of assessment index or assessment reaction time, etc. Third, two cases are used to illustrate the application effects of proposed method: the image enhancement system design for surveillance camera and the imaging environment perception system design for intelligent lighting terminal. A Prior Sequential Stimulus (PSS) experiment is proposed to improve the evaluation stability of SIEA method. Many experiment results have shown the proposed method can realize a stable system design or parameters setting for the intelligent imaging terminal in engineering site.