• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.5
• /
• pp.18-27
• /
• 2006

Rapid increase of the amount of music data demands for a new method that allows efficient similarity retrieval of music genre using audio features in music databases. To build this similarity retrieval, an indexing techniques that support audio features as a time-series pattern and data mining technologies are needed. In this paper, we address the development of a system that retrieves similar genre music based on the indexing techniques. We first propose the structure of content-based music genre retrieval system based on the time-series pattern index file and data mining technologies. In addition, we implement the time-series pattern index file using audio features and present performance analysis of the time-series pattern index file for similar genre retrieval. The experiments are performed on real data to verify the performance of the proposed method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.377-380
• /
• 2011

음악은 인류의 대표적인 예술로서 오랜 세월동안 사랑을 받아왔다. 그 오래된 세월만큼이나 인류가 만들어온 음악의 수는 방대하다. 방대한 음악이 IT기술의 발달과 인터넷의 확산을 통하여 온라인 음악시장을 형성하였고 음악은 디지털 음원으로 관리되게 되었다. 이러한 디지털 음원을 효과적으로 검색하기 위한 방법은 많이 연구되었다. 그리고 검색을 도와줄 대량의 디지털 음원 자료들을 저장하고 관리하는 기법에 관한 연구가 필요하다. 본 논문에서는 대용량 자료를 처리하는 기술로 관심 받고 있는 하둡을 통하여 이 문제를 연구하였다. 하둡의 맵리듀스, HDFS 그리고 HBase를 이용하여 음악 내용기반검색을 설계하였다. 본 시스템은 음악 검색 시스템을 관리하고 유지하는데 있어서 컴퓨팅자원을 절약함으로써 비용을 절감 효과를 얻을 수 있다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.5
• /
• pp.637-644
• /
• 2011

Being digitalized, the music can be easily purchased and delivered to the users. However, there is still some difficulty to find the music which fits to someone's taste using traditional music information search based on musician, genre, tittle, album title and so on. In order to reduce the difficulty, the contents-based or the emotion-based music retrieval has been proposed and developed. In this paper, we propose new method to determine the importance of MPEG-7 low-level audio descriptors which are multi-dimensional vectors for the emotion-based music retrieval. We measured the mutual similarities of musics which represent a pair of emotions expressed by opposite meaning in terms of each multi-dimensional descriptor. Then rough approximation, and inter- and intra similarity ratio from the similarity relation are used for determining the importance of a descriptor, respectively. The set of weights based on the importance decides the aggregated similarity measure, by which emotion-based music retrieval can be achieved. The proposed method shows better result than previous method in terms of the average number of satisfactory musics in the experiment emotion-based retrieval based on content-based search.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1210-1216
• /
• 2003

Traditional indexing mechanism are based on the song's metadata such as the title and the composer and so on. However, these system have a major limitation that users have to know the metadata of the songs they want to retrieve. In order to solve these limitation, we proposed a rhythm extraction system that allows users to retrieve music information efficiently from a large music database using the rhythm that is defined as the parts of the music.

• The KIPS Transactions:PartD
• /
• v.11D no.3
• /
• pp.495-508
• /
• 2004

Recently, in content-based music information retrieval systems, to enhance the response time of retrieving music data from large music database, some researches have adopted the indexing mechanism that extracts and indexes the representative melodies. The representative melody of music data must stand for the music itself and have strong possibility to use as users' input queries. However, since the previous researches have not considered the musical composition forms, they are not able to correctly catch the contrast, repetition and variation of motif in musical forms. In this paper, we use an index automatically constructed from representative melodies such like first melody, climax melodies and similarly repeated theme melodies. At first, we expand the clustering algorithm in order to extract similarly repeated theme melodies based on the musical composition forms. If the first melody and climax melodies are not included into the representative melodies of music by the clustering algorithm, we add them into representative melodies. We implemented a prototype system and did experiments on comparison the representative melody index with other melody indexes. Since, we are able to construct the representative melody index with the lower storage by 34％ than whole melody index, the response time can be decreased. Also, since we include first melody and climax melody which have the strong possibility to use as users' input query into representative melodies, we are able to get the more correct results against the various users' input queries than theme melody index with the cost of storage overhead of 20％.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.732-735
• /
• 2010

본 연구에서는 음악 데이터 베이스에서 노래의 특정 구간과 가장 유사한 구간을 검색하는 시스템을 제안한다. 제안된 시스템에서는 음악을 다차원 시계열 데이터로 간주하고, 음악의 조성 차이 및 템포(tempo) 차이를 고려한 음악의 유사도 계산 방법을 사용한다. 유사도 계산의 전처리 단계에서 조성 차이를 보정하고, 비트(beat)를 검출하며, 추출된 크로마그램(chromagram)을 검출된 비트와 동기화 하여 평균한다. 이후, 동적 시간 왜곡(DTW; dynamic time warping)을 사용하여 두 구간사이의 유사도를 계산한 후 계산된 유사도 순서로 정렬된 검색 결과를 출력한다. 사용자는 제안된 시스템을 사용하여 선택 구간 유사도 검색과 자동 유사 검색 결과로 도출된 구간 쌍을 검토하여 유사 구간을 보다 쉽게 찾을 수 있다.

• 한국정보통신설비학회:학술대회논문집
• /
• 2004.08a
• /
• pp.81-85
• /
• 2004

내용기반 질의법 (Content-based Query Method)은 멀티미디어 데이터가 가지고 있는 고유의 특성을 검색의 단서로 하여 질의하는 방법이다. 따라서 이러한 내용 기반의 디지털 오디오 콘텐츠 시스템은 유저가 데이터베이스 내에서 찾고자 하는 오디오 관련 정보의 질의 방법으로써 그 노래의 멜로디 정보를 입력함으로써 이루어지게 된다. 본 논문에서는 가수명이나 노래 제목, 혹은 가사의 일부 등 기존의 음악 검색에 필수적인 텍스트 정보인 키워드를 전혀 모르는 상태에서, 휴대폰이나 컴퓨터의 마이크를 통해 자신이 기억하고 있는 노래의 일부분을 흥얼거리는 것만으로, 각종 오디오 정보를 손쉽게 찾아주는 내용기반 질의법을 이용한 디지털오디오 검색시스템 (MuseFinder)을 소개한다. 또한 실제 유저의 편이성을 고려한 GUI에 기초한 고성능의 검색시스템을 구현하는데 있어 주요 이슈와 고려사항에 대해서 살펴보고 그 해결 방법을 제안한다.

• Journal of KIISE:Databases
• /
• v.34 no.4
• /
• pp.283-303
• /
• 2007

Recently, the study of efficient way to store and retrieve enormous music data is becoming the one of important issues in the multimedia database. Most general method of MIR (Music Information Retrieval) includes a text-based approach using text information to search a desired music. However, if users did not remember the keyword about the music, it can not give them correct answers. Moreover, since these types of systems are implemented only for exact matching between the query and music data, it can not mine any information on similar music data. Thus, these systems are inappropriate to achieve similarity matching of music data. In order to solve the problem, we propose an Efficient Query-By-Humming System (EQBHS) with a content-based indexing method that efficiently retrieve and store music when a user inquires with his incorrect humming. For the purpose of accelerating query processing in EQBHS, we design indices for significant melodies, which are 1) frequent melodies occurring many times in a single music, on the assumption that users are to hum what they can easily remember and 2) melodies partitioned by rests. In addition, we propose an error tolerated mapping method from a note to a character to make searching efficient, and the frequent melody extraction algorithm. We verified the assumption for frequent melodies by making up questions and compared the performance of the proposed EQBHS with N-gram by executing various experiments with a number of music data.

• The KIPS Transactions:PartD
• /
• v.10D no.3
• /
• pp.547-558
• /
• 2003

From the viewpoint of that music melody has the similar features to time-series data, music melody is transformed to a time-series data with normalization and corrections and the similarity between melodies is defined as the Euclidean distance between the transformed time-series data. Then, based the similarity between melodies of a music object, melodies are clustered and the representative of each cluster is extracted as one of theme melodies for the music. To construct the theme melody index, a theme melody is represented as a point of the multidimensional metric space of M-tree. For retrieval of user's query melody, the query melody is also transformed into a time-series data by the same way of indexing phase. To retrieve the similar melodies to the query melody given by user from the theme melody index the range query search algorithm is used. By the implementation of the prototype system using the proposed theme melody index we show the effectiveness of the proposed methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.1 s.307
• /
• pp.85-90
• /
• 2006

In this paper, we propose the content-based music information retrieval system with improved retrieval speed and stable performance while maintaining resonable retrieval accuracy In order to solve the in-stable system problem multi-feature clustering (MFC) is used to setup robust music DB. In addition, the music retrieval speed was improved by using the Superclass concept. Effectiveness of the system with SuperClass and without SuperClass is compared in terms of retrieval speed, accuracy and retrieval precision. It is demonstrated that the use of WC and Superclass substantially improves music retrieval speed up to $20\%\~40\%$ while maintaining almost equal retrieval accuracy.