• Journal of information and communication convergence engineering
• /
• 제9권2호
• /
• pp.161-165
• /
• 2011

Recently, According to increasing interest to original sound Karaoke instrument, MIDI type karaoke manufacturer attempt to make more cheap method instead of original recoding method. Separating technique for singing voice from music accompaniment is very useful in such equipment. We propose a system to separate singing voice from music accompaniment for stereo recordings. Our system consists of three stages. The first stage is a spectral change detector. The second stage classifies an input into vocal and non vocal portions by using GMM classifier. The last stage is a selective frequency separation stage. The results of removed by listening test from the results for computer based extraction simulation, spectrogram results show separation task successfully. Listening test with extracted MR from proposed system show vocal separating and removal task successfully.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2013년도 제48차 하계학술발표논문집 21권2호
• /
• pp.379-380
• /
• 2013

본 논문은 중국전통문화 오행문무(五行文武)와 인터랙티브 미디어 아트 개념을 결합한다. 중국 전통악기 고금(古琴, Gu Qui)을 레이저 다이오드와 빛감지센서를 이용하여 현을 하드웨어적으로 구현하고, VVVV를 활용하여 센서 인식, 음향재생, 프로젝션 화면 영상 시각화에 해당하는 소프트웨어를 구현한다.

• Journal of information and communication convergence engineering
• /
• 제2권4호
• /
• pp.233-236
• /
• 2004

This paper shows the easy way to composite a music for non-musicians. Namely, only select a chord and put it to special program which called "the chord composition program", and then the composition program creates the rest chords. After doing this process, non-musicians overwrite their own melodies in accordance with created chords. Finally, they can perform their own music with the sound of master-keyboard and other sound sources by using the band-in-a-box program.x program.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2012년도 제46차 하계학술발표논문집 20권2호
• /
• pp.1-2
• /
• 2012

본 논문에서는 GPU 컴퓨팅 환경에서 물리적 모델링 기반의 음 합성 알고리즘을 수행하는 경우에 GPU의 개수에 따른 성능 및 에너지 효율의 변화를 분석한다. 실험결과, 6개의 GPU를 사용하였을 때 가장 좋은 성능을 보였으며, 1개의 GPU에서 가장 높은 에너지 효율을 보였다.

• 한국통신학회논문지
• /
• 제39A권5호
• /
• pp.244-250
• /
• 2014

The Most Serious Engine Faults Are Those That Occur Within The Engine. Traditional Engine Fault Diagnosis Is Highly Dependent On The Engineer'S Technical Skills And Has A High Failure Rate. Neural Networks And Support Vector Machine Were Proposed For Use In A Diagnosis Model. In This Paper, Noisy Sound From Faulty Engines Was Represented By The Mel Frequency Cepstrum Coefficients, Zero Crossing Rate, Mean Square And Fundamental Frequency Features, Are Used In The Hidden Markov Model For Diagnosis. Our Experimental Results Indicate That The Proposed Method Performs The Diagnosis With A High Accuracy Rate Of About 98% For All Eight Fault Types.

• 대한안전경영과학회지
• /
• 제22권2호
• /
• pp.15-21
• /
• 2020

Industrial facilities need design to predict and reduce noise from design to prevent and reduce noise. The purpose of this study is to predict worker's environment and evaluate safety by analyzing noise inside underground blower room and air compressor room with fluid machinery in waste facility. This waste incineration facility was analyzed based on the ground floor, ground floor blower chamber, and air compressor chamber. The results of SPL(Sound Pressure Level) analysis at 1.5m away, which are frequently used to measure the SPL as a noise source, are as follows. SPL of basement level: 46.80[dB], SPL of ground layer: 48.57[dB]. As a result, it was expected that the noise level would be considerably lower than the 8 hours 50[dB] noise exposure per day.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2012년도 춘계학술발표대회
• /
• pp.950-952
• /
• 2012

음원 위치추정 시스템은 일반적으로 여러 개의 마이크에서 수집된 음원의 시간 간격을 이용해 음원의 위치를 추정하는 방식을 적용한다. 본 논문에서는 감시카메라에 적합한 4개의 마이크로폰을 이용한 음원 위치추정 시스템에서 마이크로폰에 수신된 음원의 도착순서를 이용해 음원의 위치를 추정하는 알고리즘을 제안하였다. 제안한 알고리즘을 시뮬레이션 프로그램을 통해 검증한 결과, 음원 추정각도의 오차는 $2^{\circ}{\sim}11.25^{\circ}$로 확인되었으며, 이는 실제각도의 오차범위인 $0^{\circ}{\sim}22.5^{\circ}$ 내에 해당하기 때문에 추정각도의 오차가 최대로 발생하더라도 음원이 발생한 위치를 파악 할 수 있음을 의미한다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제67차 동계학술대회논문집 31권1호
• /
• pp.241-242
• /
• 2023

본 논문에서는 딥러닝 소리 인식을 이용하여 실내에서 발생할 수 있는 다양한 소리를 시각적인 정보로 제공해주는 스마트허브 시스템을 제안한다. 인공지능 모델은 2D-CNN 구조를 활용하여 학습을 진행하였고, 스마트허브 하드웨어는 라즈베리파이를 이용하여 구현하였다. 제안된 시스템은 청각장애인을 위해 설계된 다양한 청각 정보를 시각 정보로 전달하는 다양한 제품을 하나로 대체할 수 있을 뿐만 아니라, 설치 및 운반이 간편하여 누구나 사용하기 쉬워서 활용도가 높을 것으로 기대된다.

• 감성과학
• /
• 제4권1호
• /
• pp.43-51
• /
• 2001

When consumer evaluates a product, every aspec of the product affects the evaluation. Human uses at least five sensory organs for the evaluation. Multi-sensory or multi-modal design tries to add auditory and olfactory factors to the traditional visual-centered design. For the multi-modal design, it is essential to understand relationships between combined sensory stimuli and human sensibility. Information between simple sensory stimulus and human sensibility is pre-requisite to combine multi-modal stimuli. This study investigated human sensibility against 8 colors and 30 sounds, presented independently. The combined stimuli of color and sound were made based on the sensibility generated by each stimulus. Human sensibility generated by the combined stimuli of color and sound were made based on the sensibility generated by each stimulus. Human sensibility generated by the combined stimuli was investigated with 20 female subjects. For combined stimuli that generated the same kind of sensibility respectively, generated sensibility was same but strength was diminished. For combined stimuli that generated the different sensibilities respectively, subjects showed neutral sensibility or no special sensibilities. Sensibilities to the same stimuli also showed difference depending on personal background of the subjects.

• 제어로봇시스템학회논문지
• /
• 제15권12호
• /
• pp.1203-1208
• /
• 2009

Green IT based u-City means that u-City having Green IT concept. If we adopt the situation awareness or not, the processing of Green IT may be reduced. For example, if we recognize a lot of speech sound on CCTV in u-City environment, it takes a lot of processing time and cost. However, if we want recognize emergency sound on CCTV, it takes a few reduced processing cost. So, for detecting emergency state dynamically through CCTV, we propose our advanced speech recognition system. For the purpose of that, we adopt HMM (Hidden Markov Model) for feature extraction. Also, we adopt Wiener filter technique for noise elimination in many information coming from on CCTV in u-City environment.