• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.271-278
• /
• 2004

In this paper, we propose a content-based audio genre classification algorithm that automatically classifies the query audio into five genres such as Classic, Hiphop, Jazz, Rock, Speech using digital sign processing approach. From the 20 seconds query audio file, the audio signal is segmented into 23ms frame with non-overlapped hamming window and 54 dimensional feature vectors, including Spectral Centroid, Rolloff, Flux, LPC, MFCC, is extracted from each query audio. For the classification algorithm, k-NN, Gaussian, GMM classifier is used. In order to choose optimum features from the 54 dimension feature vectors, SFS(Sequential Forward Selection) method is applied to draw 10 dimension optimum features and these are used for the genre classification algorithm. From the experimental result, we can verify the superior performance of the proposed method that provides near 90% success rate for the genre classification which means 10%∼20% improvements over the previous methods. For the case of actual user system environment, feature vector is extracted from the random interval of the query audio and it shows overall 80% success rate except extreme cases of beginning and ending portion of the query audio file.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1487-1494
• /
• 2011

In this paper, a novel genre classification algorithm is proposed for music recommendation system. Especially, to improve the classification accuracy, the band-pass filter for octave-based spectral contrast (OSC) feature is designed considering the psycho-acoustic model and actual frequency range of musical instruments. The GTZAN database including 10 genres was used for 10-fold cross validation experiments. The proposed multiple-octave based OSC produces better accuracy by 2.26% compared with the conventional OSC. The combined feature vector based on the proposed OSC and mel-frequency cepstral coefficient (MFCC) gives even better accuracy.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09b
• /
• pp.114-117
• /
• 2003

본 논문에서는 사용자가 음악을 직접 선곡하지 않고 락, 트로트, 댄스, 힙합, 발라드 등 5가지의 장르 중 사용자가 선호하는 음악의 장르를 추천하는 시스템을 구현하였다. 실시간으로 연주되는 음악에서 Bass Drum 신호를 추출ㆍ분석하여, 기본적으로 한 마디에 소요되는 시간, 주법, 진폭 등 세가지 파라메터를 이용하여 5가지 장르로 분류하였다 선택 곡 수와 들은 시간으로 퍼지 추론을 통해 각 장르에 대한 사용자 만족도를 평가한다. 평가된 만족도에 의해 사용자가 선호하는 장르의 음악을 제공하는 시스템을 제안한다.

• The Journal of the Acoustical Society of Korea
• /
• v.33 no.1
• /
• pp.81-86
• /
• 2014

This paper presents a study on the effectiveness of using the spectral and the temporal octave-band order statistics for musical genre classification. In order to represent the relative disposition of the harmonic and non-harmonic components, we utilize the octave-band order statistics of power spectral distribution. Experiments on the widely used two music datasets were performed; the results show that the octave-band order statistics improve genre classification accuracy by 2.61 % for one dataset and 8.9 % for another dataset compared with the mel-frequency cepstral coefficients and the octave-band spectral contrast. Experimental results show that the octave-band order statistics are promising for musical genre classification.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.53-54
• /
• 2018

본 논문에서는 스펙트로그램을 이용하여 딥 러닝 기반으로 오디오 장르와 품질의 다중 정보를 동시에 분류하는 기술을 제안한다. 기존 딥 러닝 기반의 오디오 정보 인식 기술은 각각의 정보 인식을 목표로 독립 네트워크를 설계하고, 여러 정보를 동시에 인식하기 위하여 각각에 특화된 여러 네트워크를 사용한다. 이러한 문제점을 보완하기 위해 본 논문에서는 디지털 오디오의 대표 특성인 스펙트로그램을 기반으로 범용성이 있는 특성을 추출하고, 단일 네트워크로 학습시켜 장르 및 품질을 동시에 분류하는 다중 분류 기술을 제안한다. 제안하는 방법으로 단일 분류 성능과 유사한 다중 분류 성능을 얻을 수 있다.

• Journal of KIISE:Software and Applications
• /
• v.35 no.11
• /
• pp.692-700
• /
• 2008

In some previous works on musical genre classification, human experts specify segments of a song for extracting musical features. Although this approach might contribute to performance enhancement, it requires manual intervention and thus can not be easily applied to new incoming songs. To extract musical features without the manual intervention, most of recent researches on music genre classification extract features from a pre-determined part of a song (for example, 30 seconds after initial 30 seconds), which may cause loss of accuracy. In this paper, in order to alleviate the accuracy problem, we propose a new method, which extracts features from representative segments (or main theme part) identified by structure analysis of music piece. The proposed method detects segments with repeated melody in a song and selects representative ones among them by considering their positions and energies. Experimental results show that the proposed method significantly improve the accuracy compared to the approach using a pre-determined part.

• Journal of Information Technology and Architecture
• /
• v.9 no.4
• /
• pp.413-422
• /
• 2012

Many researchers have been studied to reveal human natural language to let machine understand its meaning by text based, page rank based or more. Particularly, it has been considered that URL and HTML Tag information in web documents are attracting people' attention again to analyze huge amount of web document automatically. In this paper, we propose a STW (Semantic Term Weight) approach based on syntactic and linguistic structure of web documents in order to classify what genres are. For the evaluation, we analyzed more than 1,000 documents from 20-Genre-collection corpus for training the documents based on SVM algorithm. Afterwards, we tested KI-04 corpus to evaluate performance of our proposed method. This paper measured their accuracy by classifying them into an experiment using STW and one without u sing STW. As the results, the proposed STW based approach showed approximately 10.2% which Is higher than one without use of STW.

• Journal of Korea Game Society
• /
• v.10 no.5
• /
• pp.39-49
• /
• 2010

The fundamental characteristic that digital games have is interactivity. Digital games need to be systematically categorized so that similarities and differences can be identified and analyzed. Research in the past, however, has not established common criteria for categorizing digital games. This paper resolves that gap by identifying the fundamental characteristic of games, interactivity, and develops a conceptual framework consisting of primary and corresponding participants, and controlling characters. Through an empirical analysis on some digital games, this study shows that the framework could be comprehensive covering all of interactivity during the game. Future research topics are presented based on this framework.

• Proceedings of the Korea Contents Association Conference
• /
• 2019.05a
• /
• pp.57-58
• /
• 2019

SF&액션 장르 애니메이션 주제가 가사를 메시지의 유형에 따라 분류하고 Song form 별 가사의 역할과 내포된 활동성 표현 포함 비율의 서열을 생성했다. 3가지 세부 장르의 주제, 소재, 캐릭터 유형, 주제가의 유의미한 상관성을 도출하고 장르의 영향력 안에서 자유로울 수 없는 주제가의 제한적 창작형태를 확인하였다.

• Journal of Korea Multimedia Society
• /
• v.10 no.7
• /
• pp.817-826
• /
• 2007

The existing a music genre classification research used signal feature of the part which gets 20 seconds interval of the random or the $40%{\sim}45%$ after in the music. This paper propose it to increase the accuracy of existing research to classify music genre using climax part in the music. Generally the music is divided to three parts; introduction, progress and climax. And the climax is the part which the music emphasizes and expresses the feature of the music best. So, we can get efficient result if the climax is used, when the music classify. We can get the climax in the music finding the tempo and node which uses FFT and the maximum waveform from each node. In this paper, we did a genre classification experiment which uses existing research method and proposing method. The existing method expressed 47% accuracy. And proposing method expressed 56% accuracy which is improved than existing method.