• 방송공학회논문지
• /
• 제23권3호
• /
• pp.421-430
• /
• 2018

많은 음성인식 시스템들은 MFCC와 HMM등의 분류 기법을 사용하여 사람의 음성을 인식한다. 그러나 이러한 음성인식 시스템은 단일 음성신호를 인식하는 것을 목적으로 설계되어, 인간과 기계사이의 일대일 음성 인식에는 적합하나, 애완동물 소리와 실내 소리같은 음성보다 다양하고 넓은 주파수의 소리 군으로 중첩된 음향 속에서 설정된 소리를 인식하기에는 제한이 있다. 중첩된 소리들의 주파수는 사람의 목소리보다 높은 최대 20 kHz까지 넓은 주파수 범위로 구성된다. 본 논문에서는 광역 사운드 스펙트로그램과 DNN에 기반한 케라스 시?셜 모델 기법을 활용하여 인지 주파수 범위를 넓게 확대하는 새로운 인식방법을 제안한다. 광역 사운드 스펙트로그램이 본 논문에서 설계된 특징 추출 및 분류 시스템과 같이 넓은 주파수 범위의 다양한 소리를 분석하고 실험하도록 채택되었다. 소리 인식률을 개선하기 위하여, 케라스 시?셜 모델이 사운드 스펙트로그램에 의하여 생성되어 추출된 특징을 사용하여 패턴인식을 수행하기 위한 방법으로 채용되었다. 제안된 특징 추출 및 분류 시스템이 광역 사운드 스펙트로그램과 케라스 시?셜 모델을 채용하여 애완동물 소리와 실내 소리같은 다양한 주파수들로 구성되어 중첩된 음향 속에서 설정된 소리를 우수하게 분류하는 것을 확인하였다. 그리고 중첩된 소리의 크기에 비례하여 인식에 미치는 특성과 영향을 단계별로 비교 분석하였다.

• 한국실내디자인학회논문집
• /
• 제21권6호
• /
• pp.243-251
• /
• 2012

Theatricals have been with human's history for a long time. And It is also receiving a lot of love in modern times. The stage is recognized another space of time by spectators during the play and the production actualize fictional world by using all destination things on the stage. Therefore, the design of the stage has symbolism and the production needs semiological. The Elements expressed through the stage is composed of stage equipment, costume, lighting, stage effects and the production needs light, sound and costume designers, a stage manager, grips an advertising director for the play. The study analysis on symbolic image on the view of semigical with focused on "Vishnvovvi sad" of Anton Chekhov. The details of the study are symbolism of stage effect and costume, lighting, stage equipment. Furthermore, The study analyze way to symbolic Express korean characteristics and This research is an excellent source for students who are studying the semilogical analysis of stage.

• 전기학회논문지
• /
• 제58권3호
• /
• pp.645-654
• /
• 2009

In this study, we present an efficient ambulatory speech audiometric system to detect one's hearing problems at an earlier stage as possible without his or her visit to the audiometric testing facility such in a hospital or a clinic. To estimate a person's hearing threshold level in terms of speech sound response in his or her local environment, a digital assistant(PDA) device is used to generate the speech sound with implementing audiometric Graphic User Interface(GUI) system. Furthermore, a supra-aural earphone is used to measure a subject's hearing threshold level in terms of speech sound by the compensating the transducer's gain by adopting speech sound calibration system.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2000년도 춘계학술대회논문집
• /
• pp.151-156
• /
• 2000

The sound insulation performance of walls and floors for air-borne and structure-borne sounds in an apartment building is an important environmental factor which should be contemplated at the intial design stage for their thorough control. Recent increasing residents' demands for quality living spaces strongly urge the development of more accurate and efficient measurement and evaluation methods for the control of air-borne and structure-borne sound insulation. However, steel-structured apartment buildings, recently emerged as new building structures in the market, have not been thoroughly examined. The present work carried out an extensive survey for steel-structured apartment buildings, in an attempt to provide useful design data, and their sound insulation performances were compared with those of R.C. apartment buildings.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 1998년도 창립기념 춘계학술대회 논문집
• /
• pp.241-248
• /
• 1998

A Systematic approach to estimate an interior noise level for a railway passenger car has been proposed. The prediction is based on the sound power values obtained from measured sound pressure lever, when a high speed train runs at 300km/hr. Then, the exterior sound pressure value is calculated by using the BEM code. After that, an interior sound lever is estimated, considering the transmission loss of body structures and absorption effect inside of the train. In this application, the estimated noise level is between 66 dBA and 74 dBA. The proposed approach could be useful for rough estimation of a noise level inside a passenger car at the design stage, a]though the method has some limitation to be implement for a general situation.

• KIEAE Journal
• /
• 제2권1호
• /
• pp.41-48
• /
• 2002

This study aims to investigate and evaluate the room acoustic designs of a multi purpose gymnasiums which do not use adjustable treatments in order to change the acoustical characteristics. Considering the main uses of gymnasium and auditorium, experiments were carried out using both nondirectional speakers on the stage and loudspeaker installed on the ceiling. The result from the study are as follows; Measured RT under unoccupied condition was a little longer than the expected value, therefore, in the case of occupied condition RT would be close to the optimum value. However, parameters that evaluate intelligibility and speech transmission property appeared to be low and have large differences depending on the measuring points, therefore, more effective sound reflecting surfaces and sound reinforcement systems should be considered.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.20-27
• /
• 2020

Sound event detection in real-world environments suffers from the interference of non-stationary and time-varying noise. This paper presents an adaptive noise reduction method for sound event detection based on non-negative matrix factorization (NMF). In this paper, we proposed a deep learning model that integrates Convolution Neural Network (CNN) with Non-Negative Matrix Factorization (NMF). To improve the separation quality of the NMF, it includes noise update technique that learns and adapts the characteristics of the current noise in real time. The noise update technique analyzes the sparsity and activity of the noise bias at the present time and decides the update training based on the noise candidate group obtained every frame in the previous noise reduction stage. Noise bias ranks selected as candidates for update training are updated in real time with discrimination NMF training. This NMF was applied to CNN and Hidden Markov Model(HMM) to achieve improvement for performance of sound event detection. Since CNN has a more obvious performance improvement effect, it can be widely used in sound source based CNN algorithm.

• 한국소음진동공학회논문집
• /
• 제26권3호
• /
• pp.340-349
• /
• 2016

A coupled room system consists of adjacent rooms and apertures where the sound energy is exchanged between the two rooms. Acoustically, a coupled room system shows a non-exponential decay profile. Most of the related researches have been to analyze the acoustic properties of two-room coupled system so far whereas three-room coupled system were seldom studied. In this regard, this paper aims to analyse the distribution of sound pressure level, sound decay curve of three-room coupled system and sound energy flow between them by using the acoustic diffusion model and to further verify them through experiments. Firstly, the sound pressure level distribution and mean sound pressure level in the steady-state condition are analyzed at various frequencies and source locations. Good agreements are observed in both experiments and analysis results. Secondly, two double slope effect quantifiers of sound attenuation, LDT/EDT and LDT/T10 are compared at various frequencies and for different source locations. The result indicates that LDT/T10, less affected by the early reflection patterns than LDT/EDT, is more suitable to the analysis and experiments of a multi-slope sound decay curve. Lastly, the sound energy flow in each room is analyzed based on the acoustic diffusion model. After the early decay stage, the sound energy is observed to flow from the room with a long reverberation time to the room with a short one.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2008년도 춘계학술대회논문집
• /
• pp.25-28
• /
• 2008

This study investigates the effect of geometrical shape of concert halls, with variation in the shape and location of diffusers. The acoustical characteristics both in the audience area and on the stage 1:50 scale models of shoebox and fan-shaped halls. It was found that the front side walls affect sound diffusion. The 1:50 scale model based on the Boston Symphony Hall was used for monaural impulse response measurements for calculation of RT, EDT, C80, G and ST1. In addition, calculating the numbers and amplitudes of reflection rays were applied to quantify diffusion phenomena.

• 디지털콘텐츠학회 논문지
• /
• 제9권2호
• /
• pp.203-211
• /
• 2008

입체음 재생을 위한 하드웨어 및 소프트웨어 기술발전에 의해 입체음과 입체영상을 적용한 3D 가상 공간은 보다 증강된 입체감 및 생동감을 제공할 수 있다. 그러나 영세한 지역 영상콘텐츠 전문제작자들과 일반인들이 입체음을 구현하기 위해서는 고가의 입체음향 엔진구입, 전문 인력 투입 및 고급 프로그래밍을 작성해야 하는 어려움이 있다. 그러므로 입체음 기술의 저비용 활용을 위해서 단순하면서도 효율적인 입체음 재생 인터페이스 개발이 필요하다. 이를 활용하게 되면 영상 제작전문가들이 손쉽게 입체음 재생기술을 콘텐츠 제작물에 추가할 수 있다. 본 논문은 입체음 재생 인터페이스 개발을 위한 기초연구 단계로서 다음 내용을 설계하고 구현한다. 먼저 PC 기반 시스템에서 모노음을 입체음향으로 재생하는 주요한 모듈을 구현한다. 두 번째로 3D 영상과 입체음을 연동하는 모듈을 개발한다. 본 논문에서 구현된 모듈은 청취자가 가상공간 상에서 이동함에 따라 음원의 위치 및 서라운드 효과를 인지할 수 있도록 한다. 추후 본 연구는 사운드와 이동객체의 동기화 및 HRTF 구현을 추진하여 보다 완벽한 입체음향 재생 인터페이스를 완성 할 예정이다.