• Proceedings of the KSPS conference
• /
• 2006.11a
• /
• pp.142-145
• /
• 2006

Discrimination between speech and music is important in many multimedia applications. Previously we proposed a new parameter for speech/music discrimination, the mean of minimum cepstral distances (MMCD), and it outperformed the conventional parameters. One weakness of it is that its performance depends on range of candidate frames to compute the minimum cepstral distance, which requires the optimal selection of the range experimentally. In this paper, to alleviate the problem, we propose a multi-dimensional MMCD parameter which consists of multiple MMCDs with different ranges of candidate frames. Experimental results show that the multi-dimensional MMCD parameter yields an error rate reduction of 22.5% compared with the optimally chosen one-dimensional MMCD parameter.

• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.10
• /
• pp.399-406
• /
• 2021

With the steady growth of the content industry, the need for research that automatically recommending content suitable for individual tastes is increasing. In order to improve the accuracy of automatic content recommendation, it is needed to fuse existing recommendation techniques using users' preference history for contents along with recommendation techniques using content metadata or features extracted from the content itself. In this work, we propose a new graph-based music recommendation method which learns an LSTM-based classification model to automatically extract appropriate tagging words from sound data and apply the extracted tagging words together with the users' preferred music lists and music metadata to graph-based music recommendation. Experimental results show that the proposed method outperforms existing recommendation methods in terms of the recommendation accuracy.

• Journal of information and communication convergence engineering
• /
• v.3 no.3
• /
• pp.119-121
• /
• 2005

This paper aims to estimate the delay time of multiple signals in a multi-path environment. It also seeks to carry out a comparative analysis with the existing delay time under the proposed algorithm to develop a new algorithm that applies the space average method in a MUSIC algorithm. Unlike the existing delay time estimation algorithm, the developed algorithm was able to estimate the delay time in 5ns low. Therefore, the algorithm proposed in this paper improved the existing delay time estimated algorithm.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.24 no.1
• /
• pp.64-72
• /
• 2013

Blind equalization is a technique that equalizes the received signals without the training sequence. Because of the absence of training sequence, we can increase the bandwidth efficiency due to the blind equalization system. And we must use the blind equalization for removing the ISI in mobile satellite communication receiver. ISI occurs due to mobility of users in mobile satellite communications. Blind equalization is suitable for the mobile satellite communication channels. In this blind equalization, it's very important to improve BER performance to apply the mobile satellite communication system. In this paper, we propose the blind beamforming equalization system using the beamforming, MUSIC algorithm and coordinate change method. We were confirmed by the simulation that the proposed system improves the BER performance.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1578-1581
• /
• 2002

In this paper, the accuracy of the direction-of-arrival (DOA) estimation of signal impinged on the uniform linear array (ULA) is investigated. The conventional beamformer and Capon’s beamformer categorized in beamformaing techniques as well as MUSIC (MUlti-pie Signal Classification) and ESPRIT (Estimation of Signal Invariance Techniques) categorized in subspace- based methods are employed to estimate the DOAs. From the simulation result under uncorrelated environment, MUSIC can prominently distinguish the DOAs while the beamforming techniques cannot demonstrate the DOAs as clear as MUSIC does. Moreover, Uni-tary ESPRIT is employed to estimate the DOAs under uncorrelated signal conditions. By means of Uni-tary ESPRIT, the estimation has more accuracy with the computational-time reduction. In addition, it incorporates forward-backward averaging; thus Unitary ES-PRIT can overcome the problem of the coherent signal condition.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.3E
• /
• pp.101-109
• /
• 2003

A multi-mode harmonic transform coding (MMHTC) for speech and music signals is proposed. Its structure is organized as a linear prediction model with an input of harmonic and transform-based excitation. The proposed coder also utilizes harmonic prediction and an improved quantizer of excitation signal. To efficiently quantize the excitation of music signals, the modulated lapped transform(MLT) is introduced. In other words, the coder combines both the time domain (linear prediction) and the frequency domain technique to achieve the best perceptual quality. The proposed coder showed better speech quality than that of the 8 kbps QCELP coder at a bit-rate of 4 kbps.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.300-300
• /
• 2012

A database is an organized collection of data, today typically in digital form. The data are typically organized to model relevant aspects of reality, in a way that supports processes requiring this information. A good database is designed for a specific use and is constructed with the possibility of growth. In this project, we collect music education data of the East Asia and try to build a database that can share the primary data based on this collection. Hence we can provide opportunity to study about Korea modern music and culture in a broader perspective. In this paper, we explore the database construction methodology for implementing on this project and we see over about data entry and management.

• Proceedings of the KIEE Conference
• /
• 1992.07a
• /
• pp.427-430
• /
• 1992

In this paper, we proposed an algorithm for the musical note recognition. Firstly, a given bit-mapped music score image is converted to a set of individual note pattern images via vertical projection. Then, the pitch of a note is determinal by comparison in the note-head position with the reference five-lines. Also, the length of a note is found via leader clustering with a set of normalized note patterns. Finally, a datafile to play the music is obtained using the pitch and length of musical notes. Experimental results with a simple musical score image show that the proposed scheme is performed well.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.306-309
• /
• 2000

We developed an electronic music glove (EMG) system that could play musical scores in real time processing. The EMG system interfaces with the signal coming from the controller to the sound card in the computer. The computer, according to the status of the finger and foot switches, generates the signals to the speaker systems using the application C++ program by making use of MIDI message. The EMG systems can control up to several octave notes and duration of sound, and several musical performance expressions such as chorus, reverberation, rhythm, and volume. Finally, our EMG could play the performance of simple music depending on the choice of any kind of musical instruments in the sound card in computer systems.