• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2006년도 춘계 학술대회 발표논문집
• /
• pp.143-146
• /
• 2006

Music is now digitally produced and distributed via internet and we face a huge amount of music day by day. A music summarization technology has been studied in order to help people concentrate on the most impressive section of the song andone can skim a song as listening the climax(chorus, refrain) only. Recent studies try to find the climax section using various methods such as finding diagonal line segment or kernel based segmentation. All these methods fail to capture the inherent structure of music due to polyphonic and noisy nature of music. In this paper, after applying moving average filter to time domain of MFCC/chroma feature, we achieved a remarkable result to capture the music structure.

• 한국컴퓨터정보학회논문지
• /
• 제22권1호
• /
• pp.9-14
• /
• 2017

In this paper, we propose that the contrast features of octave spectrum can be used to show spectral contrast features of some music clips. It shows the relative spectral distribution rather than average spectrum. From the experiment, it can be seen the method of spectral contrast features has a good performance in classification of music styles. Another comparative experiment shows that the method of spectral contrast features can better distinguish different music styles than the method of MFCC features that commonly used previously in the classification system of music styles.

• 한국멀티미디어학회논문지
• /
• 제23권6호
• /
• pp.765-771
• /
• 2020

To enable AI(artificial intelligence) to realize visual emotions, it attempts to create music centered on color, an element that causes emotions in paintings. Traditional image-based music production studies have a limitation in playing notes that are unrelated to the picture because of the absence of musical elements. In this paper, we propose a new algorithm to set the group of music through the average color of the picture, and to produce music after adding diatonic code progression and deleting sound using median value. And the results obtained through the proposed algorithm were analyzed.

• International Journal of Contents
• /
• 제10권4호
• /
• pp.11-17
• /
• 2014

The influence of acquisition environment on music score images captured by a camera has not yet been seriously examined. All existing Optical Music Recognition (OMR) systems attempt to recognize music score images captured by a scanner under ideal conditions. Therefore, when such systems process images under the influence of distortion, different viewpoints or suboptimal illumination effects, the performance, in terms of recognition accuracy and processing time, is unacceptable for deployment in practice. In this paper, a novel, lightweight but effective approach for dealing with the issues caused by camera based music scores is proposed. Based on the staff line information, musical rules, run length code, and projection, all regions of interest are determined. Templates created from inverse filter are then used to recognize the music symbols. Therefore, all fragmentation and deformation problems, as well as missed recognition, can be overcome using the developed method. The system was evaluated on a dataset consisting of real images captured by a smartphone. The achieved recognition rate and processing time were relatively competitive with state of the art works. In addition, the system was designed to be lightweight compared with the other approaches, which mostly adopted machine learning algorithms, to allow further deployment on portable devices with limited computing resources.

• 융합정보논문지
• /
• 제11권9호
• /
• pp.214-220
• /
• 2021

스마트폰이 빠르게 보급되면서 음악을 생활 속의 배경음악처럼 항상 모든 곳에서 듣는 것이 일반화되어 개인의 상황과 조건에 맞는 추천을 할 수 있는 음악 데이터베이스를 필요하다. 본 논문에서는 소셜 미디어를 통한 음악추천 모델을 제안한다. 소셜 미디어의 데이터를 사용하여 음악 데이터베이스를 작성하고 기존의 음원 제공 플랫폼이 주로 사용하는 협업필터링과는 다른 방식으로 음악을 분류한다. 웹크롤링으로 음악 제목이 해시 태그로 달린 게시글을 찾아 해당 글에 함께 달린 다른 해시 태그들을 수집하고 분류하여 실제 청취자의 음악에 관한 의견을 데이터베이스에 사용한다. 소셜 미디어를 작성할 때의 감정, 상황, 시간대, 날씨 등 많은 조건이 해시 태그에는 포함되어 있으므로 다양한 사람의 의견이 집단지성으로 반영된 소셜 미디어 기반 데이터베이스를 구축할 수 있다.

• 한국컴퓨터정보학회논문지
• /
• 제24권6호
• /
• pp.81-88
• /
• 2019

Based on the theory of planned behavior and the theory of legal deterrence, this study takes consumers' willingness to pay for digital music as the research object, investigates the consumers who have digital music consumption channels and behaviors, and discusses the willingness of consumers to pay for digital music and its influencing factors. The study attempts to achieve the following research purposes: First, explore the influencing factors of willingness to pay for digital music using domestic and foreign literature research and related content analysis. Second, we want to examine the effect of Attitude, Collective Specifications, Quality Sensitivity and Music affinity on willingness to pay. Third, Legal deterrence and resource availability tries to verify whether there is a moderating effect between Attitude, Collective Specifications, Quality Sensitivity and Music affinity and willingness to pay. The research data was collected in 2019 between April 6th to May 8th. Questionnaires were randomly distributed in fixed places, mainly in Hubei Province, China. A total of 393 questionnaires were selected for data analysis. Based on the previous theoretical review and empirical analysis, the study draws the following conclusions: Firstly, attitude, collective specifications, quality sensitivity and music affinity have an impact on the willingness to pay. Second, Legal deterrence has a regulatory effect on the relationship among quality sensitivity, musical affinity and the willingness to pay. Last the resource availability has a significant impact on the willingness to pay. It also has a regulatory effect on the relationship among quality sensitivity, music affinity and the willingness to pay.

• ETRI Journal
• /
• 제46권4호
• /
• pp.697-707
• /
• 2024

Music identification is widely regarded as a solved problem for music searching in quiet environments, but its performance tends to degrade in TV broadcast audio owing to the presence of dialogue or sound effects. In addition, constructing an accurate dataset for measuring the performance of background music monitoring in TV broadcast audio is challenging. We propose a framework for monitoring background music by automatic identification and introduce a background music cue sheet. The framework comprises three main components: music identification, music-speech separation, and music detection. In addition, we introduce the Cue-K-Drama dataset, which includes reference songs, audio tracks from 60 episodes of five Korean TV drama series, and corresponding cue sheets that provide the start and end timestamps of background music. Experimental results on the constructed and existing datasets demonstrate that the proposed framework, which incorporates music identification with music-speech separation and music detection, effectively enhances TV broadcast audio monitoring.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2013년도 제47차 동계학술대회논문집 21권1호
• /
• pp.271-272
• /
• 2013

The music with the times, evolved from analogous tape music to digital music. New authoring tools, interfaces, and applications make us to produce high quality music using cheap equipments. Inspired by this concept, we design an classical chinese style-instrument with the audio-visual interactive function. It enables a user to compose music and to see a vivid picture at the same time.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2007년도 한국컴퓨터종합학술대회논문집 Vol.34 No.1 (C)
• /
• pp.252-257
• /
• 2007

MusicXML은 다양한 전자악보 형식들이 음악을 악보로 표현하는데 있어 지니는 한계를 잘 극복하면서 응용성, 확장성 및 공개성 등의 장점으로 인해 현재 전자악보의 표준으로 가장 적합한 것으로 평가되고 있는 악보 형식이다. 그러나 MusicXML은 XML을 기반으로 한 텍스트 데이터이기 때문에 이러한 악보 형식을 실제 악보로 변환하거나 연주하는 것은 물론 실제 악보 내용을 기반으로 한 악보 검색이 용이하도록 적절한 데이터 구조로 표현하는 것이 필요하다. 본 논문에서는 MusicXML 악보에 대하여 다차원 속성 정보를 가진 데이터의 표현에 용이한 k-d 트리 기반 데이터 구조로 표현하는 방법을 제안한다. 논문은 또한 악보에 대한 k-d 트리 구조를 보다 다양한 응용에 활용할 수 있도록 k-d 트리를 확장하여 구조화하는 방법을 제시한다. 본 논문에서 제안한 방법은 특히 내용을 기반으로 한 악보 정보 검색에 유용하게 이용될 수 있다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 하계학술대회
• /
• pp.23-25
• /
• 2021

This paper describes an approach of composing music with multiple AI composers. This approach enriches more the creativity space of artificial intelligence music composition than using only one composer. This paper presents a simple example with 2 different deep learning composers working together for composing one music. For the experiment, the two composers adopt the same deep learning architecture of an LSTM model trained with different data. The output of a composer is a sequence of notes. Each composer alternatively appends its output to the resulting music which is input to both the composers. Experiments compare different music generated by the proposed multiple composer approach with the traditional one composer approach.