• The Journal of the Acoustical Society of Korea
• /
• v.43 no.2
• /
• pp.200-206
• /
• 2024

Computing music similarity is an indispensable component in developing music search service. This paper proposes a relevance weight of each chromagram vector for cover song identification in computing a music similarity function in order to boost identification accuracy. We derive a music similarity function using the relevance weight based on the probabilistic relevance model, where higher relevance weights are assigned to less frequently-occurring discriminant chromagram vectors while lower weights to more frequently-occurring ones. Experimental results performed on two cover music datasets show that the proposed music similarity improves the cover song identification performance.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.518-524
• /
• 2018

The cover song refers to live recordings or reproduced albums. This paper studies two-dimensional Fourier transform as a feature-dimension reduction method to search cover song fast. The two-dimensional Fourier transform is conducive in feature-dimension reduction for cover song search due to musical-key invariance. This paper extends the previous work, which only utilize the magnitude of the Fourier transform, by introducing an invariant from phase based on the assumption that adjacent frames have the same musical-key change. We compare the cover song retrieval accuracy of the Fourier-transform based methods over two datasets. The experimental results show that the addition of the invariant from phase improves the cover song retrieval accuracy over the previous magnitude-only method.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.6
• /
• pp.436-441
• /
• 2017

Computing music similarity is indispensable in constructing music retrieval system. This paper focuses on the cover song search among various music-retrieval tasks. We investigate the cover song search method based on the chroma n-gram to reduce storage for feature DB and enhance search accuracy. Specifically we propose t-tab n-gram, n-gram selection method, and n-gram set comparison method. Experiments on the widely used music dataset confirmed that the proposed method improves cover song search accuracy as well as reduces feature storage.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.3
• /
• pp.314-319
• /
• 2019

Computing chromagram similarity is indispensable in constructing cover song identification system. This paper proposes a code-based chromagram similarity to reduce the computational and the storage costs for cover song identification. By learning a song-specific codebook, a chromagram sequence is converted into a code sequence, which results in the reduction of the feature storage cost. We build a lookup table over the learned codebooks to compute chromagram similarity efficiently. Experiments on two music datasets were performed to compare the proposed code-based similarity with the conventional one in terms of cover song search accuracy, feature storage, and computational cost.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.6
• /
• pp.662-667
• /
• 2022

Computing music similarity is an indispensable component in developing music search service. This paper focuses on learning a music similarity function in order to boost cover song identification performance. By using the probabilistic linear discriminant analysis, we construct a latent music space where the distances between cover song pairs reduces while the distances between the non-cover song pairs increases. We derive a music similarity function by testing hypothesis, whether two songs share the same latent variable or not, using the probabilistic models with the assumption that observed music features are generated from the learned latent music space. Experimental results performed on two cover music datasets show that the proposed music similarity improves the cover song identification performance.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.8
• /
• pp.766-771
• /
• 2002

In this study, we have developed a 3-dimensional diagnostic ultrasonic sector probe using a convex type ultrasonic probe with 128 active elements. The probe was made to operate at the center frequency of 4.5㎒ with the bandwidth of 66%. The driving part was designed to rotate the axis of the convex probe by means of a step motor equipped with reduction gears and spur gears attached to the motor so that the probe could enable us to acquire a series of 2-dimensional images to construct a 3-dimensional image. Acoustic cover of the probe was made of polymers to have the same radius of rotation as that of the convex probe. The controllability of the rotation angle and the structural stability of the probe were confirmed through experimental 3-dimensional images obtained using the developed 3-dimensional sector probe.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.345-348
• /
• 2002

본 연구에서는 128개의 능동소자로 구성된 convex형 초음파 탐촉자를 회전시켜 3차원 입체영상을 구현 할 수 있도록 하는 구동부를 설계 및 제작하여, 3차원 입체 영상 진단용 초음파 섹터 트랜스듀서를 개발하였다. 탐촉자는 중심주파수 4.5Mhz, 대역폭 $66\%$로 제작되었으며, 구동부는 탐촉자의 축을 스텝모터와 평기어를 이용해 회전시킴으로써 3차원 입체영상을 획득할 수 있게 고안하였다. 그리고 피부와 유사한 고분자재료를 사용하여 탐촉자의 회전반경과 동일하게 음향커버를 설계 및 제작하였다. 제작된 초음파 섹터 트랜스듀서는 정밀한 각도 제어 및 구조적 안정성이 확보되었음을 확인 할 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.412-421
• /
• 2023

Ultrasound brain stimulation is spot-lighted by its capability of inducing brain cell activation in a localized deep brain region and ultimately treating impaired brain function while the efficiency and directivity of neural modulation are highly dependent on types of stimulus waveforms. Therefore, to optimize the types of stimulation parameters, we propose a cell-cultivable ultrasonic transducer having a series stack of a spin-coated polymer piezoelectric element (Poly-vinylidene fluoride-trifluorethylene, PVDF-TrFE) and a parylene insulating layer enhancing output acoustic pressure on a glass-coverslip which is commonly used in culturing cells. Due to the uniformity and high accuracy of stimulus waveform, tens of neuronal cell responses located on the transducer surface can be recorded simultaneously with fluorescence microscopy. By averaging the cell response traces from tens of cells, small changes to the low intensity ultrasound stimulations can be identified. In addition, the reduction of stimulus distortions made by standing wave generated from reflections between the transducers and other strong reflectors can be achieved by placing acoustic absorbers. Through the proposed ultrasound transducer, we could successfully observe the calcium responses induced by low-intensity ultrasound stimulation of 6 MHz, 0.2 MPa in astrocytes cultured on the transducer surface.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.8
• /
• pp.22-25
• /
• 2000

In this paper, we examine the characteristic of samulnori by the sound analysis techniques. Four instruments of samulnori are constituted with the dual principle of the negative and positive (the male and female) which mean the harmony of each instruments high and low sounds. These sounds are covered the audible whole sounds. Since the fundamental frequencies of jing and janggu sounds are similar to the fundamental frequencies of male and female speech respectively, we feel the affection when we hear the sounds of jing and janggu. Additionally, since human feels the sound not only by ears, but also by the vibration to the skin, the put jing and janggu have the remarkable characteristic of the vibration.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37B no.9
• /
• pp.778-786
• /
• 2012

Sensors that are used on wireless sensor networks can be divided into two types: directional sensors, such as PIR, image, and electromagnetic sensors; and non-directional sensors, such as seismic, acoustic and magnetic sensors. In order to guarantee the line-of-sight of a directional sensor, the installation location of the sensor must be higher than ground level. Among non-directional sensors, seismic sensors should be installed on the ground in order to ensure the maximal performance. As a result, seismic sensors may have network connectivity problems due to communication failure. In this paper, we propose a 3D node deployment method to maximize the coverage and the network connectivity considering the sensor-specific properties. The proposed method is for non-directional sensors to be placed on the ground, while the directional sensor is installed above the ground, using trees or poles, to maximize the coverage. As a result, through the topology that the detection data from non-directional sensors are transmitted to the directional sensor, we can maximize the network connectivity. Simulation results show that our strategy improves sensor coverage and network connectivity.