• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4E
• /
• pp.146-155
• /
• 2002

We present a new technique for achieving source separation when given only a single charmel recording. The main idea is based on exploiting the inherent time structure of sound sources by learning a priori sets of time-domain basis functions that encode the sources in a statistically efficient manner. We derive a learning algorithm using a maximum likelihood approach given the observed single charmel data and sets of basis functions. For each time point we infer the source parameters and their contribution factors. This inference is possible due to the prior knowledge of the basis functions and the associated coefficient densities. A flexible model for density estimation allows accurate modeling of the observation, and our experimental results exhibit a high level of separation performance for simulated mixtures as well as real environment recordings employing mixtures of two different sources. We show separation results of two music signals as well as the separation of two voice signals.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.3
• /
• pp.473-479
• /
• 2008

Generally, HDDs are widely used as data storage device in office, home and mobile machineries. So, it is used for various applications or tasks, such as file copy, file download, music and movie play etc., in various environment. In spite of this kind of varieties in tasks and environment in which HDDs perform, most commercial HDDs hardly control its operations adaptively to these varieties. Thus, it is preferred to optimize the performance and energy consumption of HDDs according to the task and/or the environment. So, this paper proposes a new fuzzy inference algorithm which adaptively controls HDDs operations and may also easily be implemented as the firmware of HDDs and run in the restricted environment such as embedded systems.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.34-35
• /
• 2013

본 논문에서는 오디오 피크 검출을 적용한 TV 방송 프로그램내 배경음악 식별 알고리즘을 제안한다. 제안한 알고리즘은 음악 핑거프린트 추출 및 전송부, 음악구간 검출부, 음악 핑거프린트는 고속 매칭 및 정보전송부 세 부분으로 구성되어 있다. 음악 핑거프린트 추출 및 전송부에서는 음악 원음 오디오 데이터를 퓨리에 변환하여 스펙트럼 계수를 추출한다. 추출된 스펙트럼의 성분 중에서 일정한 문턱값 이상의 에너지를 가지는 값을 피크로 검출하고 검출된 피크를 이용하이 핑거프린트를 생성하고 데이터 베이스화한다. 음악구간 검출부에서는 입력된 방송 프로그램 오디오 데이터에 GMM(Gaussian Mixture Model)을 적용하여 음악과 음악 외 오디오 데이터를 분류한다. 음악 핑거프린트 고속 매칭 및 정보전송부에서는 음악구간이라고 인식된 쿼리 오디오 데이터를 음악 핑거프린트 추출 및 전송부와 동일한 과정을 통해 핑거프린트를 생성하고 데이터 베이스화된 음악 원음의 핑거프린트들과 비교하여 가장 유사한 음원의 정보를 TV의 화면에 자막으로 보여준다.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.1E
• /
• pp.21-27
• /
• 2005

Environmental mismatch has been one of important issues discussed in matched field processing for underwater source detection problem. To overcome this mismatch many algorithms professing robustness have been suggested. Feature extraction method (FEM) [Seong and Byun, IEEE Journal of Oceanic Engineering, 27(3), 642-652 (2002)] is one of robust matched field processing algorithms, which is based on the eigenvector estimation. Excluding eigenvectors of replica covariance matrix corresponding to large eigenvalues and forming an incoherent subspace of the replica field, the processor is formulated similarly to MUSIC algorithm. In this paper, by using the ocean experimental data, processing results of FEM and MVDR with white noise constraint (WNC) are presented for two levels of multi-tone source. Analysis of eigen-space of CSDM and FEM performance are also presented.

• Structural Monitoring and Maintenance
• /
• v.1 no.2
• /
• pp.159-171
• /
• 2014

Real-time near and far-field monitoring of concrete structural components gives enough information on the time and condition at which damage occurs, thereby facilitating damage detection while in the same time evaluate the cause of the damage. This paper experimentally investigates an integrated monitoring technique for near and far-field damage detection in concrete structures based on simultaneous use of electromechanical admittance technique in combination with guided wave propagation. The proposed sensing system does not measure the electromechanical admittance itself but detect time variations in output voltages of the response signal obtained across the electrodes of piezoelectric transducers bonded on surfaces of concrete structures. The damage identification is based on the spectral estimation MUSIC algorithm. Experimental results show the efficiency and performance of the proposed measuring technique.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.228-231
• /
• 1999

3차원 공간상의 표적의 위치는 방위각, 고각, 거리의 세가지요소로 나타내어 질 수 있다. 이 논문에서는 등각적 선배열 센서로 이루어진 3개의 부분센서배열을 이용한 3차원 표적의 위치추정 알고리듬을 제안하였다. 원거리 표적의 방위각 추정 알고리듬으로 근거리 표적의 방위각을 추정하면 추정된 방위각은 실제 근거리 표적의 방위각과 고각과 거리의 비선형 대수적 관계식으로 주어진다. 제안한 알고리듬은 3개의 부분센서배열에서 각각 표적을 원거리에 있다고 가정하고 원거리입체각을 추정하여 위의 대수적 관계식을 얻은 후 이들 관계식을 연립하여 실제 근거리 표적의 위치를 추정하였다. 다중표적의 경우 각각의 부분센서배열에서 추정한 원거리입체각이 어떤 표적에 대한 추정치인지 연관시켜주는 알고리듬이 필요하다. 이 논문에서는 추정한 원거리입체각의 모든 조합으로부터 3차원 MUSIC 스펙트럼값을 비교하여 그 중 표적의 개수만큼을 선별하여 다중표적의 위치를 추정하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.3E
• /
• pp.91-97
• /
• 2004

In this paper, we propose a classification system of TV program scenes based on audio information. The system classifies the video scene into six categories of commercials, basketball games, football games, news reports, weather forecasts and music videos. Two type of audio feature set are extracted from each audio frame-timbral features and coefficient domain features which result in 58-dimensional feature vector. In order to reduce the computational complexity of the system, 58-dimensional feature set is further optimized to yield l0-dimensional features through Sequential Forward Selection (SFS) method. This down-sized feature set is finally used to train and classify the given TV program scenes using κ -NN, Gaussian pattern matching algorithm. The classification result of 91.6% reported here shows the promising performance of the video scene classification based on the audio information. Finally, the system stability problem corresponding to different query length is investigated.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.3-6
• /
• 1988

The UCERSS algorithm is an extended MUSIC which is used to estimate incident angles of multiple wide band signals. The purpose of this paper is to extend the UCERSS in order to estimate the direction of arrivals of multiple wide band signals in multipath environment. The modifications of the UCERSS result in the wide band spatial smoothing and the UNSS approaches. Computer simulation results indicate that the performances of the UNSS are superior to those of the UCERSS and the wide band spatial smoothing method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.220-223
• /
• 2015

기존의 제품에서는 음악을 들으며 운동하는 과정에서 음악속도에 맞게 운동을 하는 방법을 사용하였다. 사용자가 운동중에 직접 음악 재생을 조절하는 방법은 좀 더 격한 음악을 재생하고자 했을 때 음악을 검색중 사용자의 운동의 흐름이 끊어지는 경우가 빈번하게 발생한다. 그러나 사용자의 걸음 속도를 이용해 음악 재생속도를 더 빠르게 한다면 효율적인 운동이 될 것이다. 본 논문에서는 신발의 깔창에 장착된 1개 이상의 압전센서를 활용하여 아두이노에서 걸음 수를 수집하고 수집된 압전센서 데이터를 이용하여 걸음 수를 이용한 걸음 속도의 측정 과정을 안드로이드 스마트폰에서 처리한다. 이렇게 측정된 걸음 속도를 통해 안드로이드 스마트폰에서 음악 재생 속도를 결정하여 사용자에게 쾌적한 운동 환경을 제공하는 것을 목적으로 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.184-185
• /
• 2018

Face Song Player, which is a system that recognizes the facial expression of an individual and plays music that is appropriate for such person, is presented. It studies information on the facial contour lines and extracts an average, and acquires the facial shape information. MUCT DB was used as the DB for learning. For the recognition of facial expression, an algorithm was designed by using the differences in the characteristics of each of the expressions on the basis of expressionless images.