• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06d
• /
• pp.153-155
• /
• 2011

최근 음악 검색 연구에서 일반적으로 사용되는 방법은 키워드 중심의 텍스트 기반 검색방식, 음원의 특징 정보나 허밍 질의 처리 등을 이용하는 내용기반 검색 방식 등이 있다. 그러나 이러한 검색 방식은 단순히 원하는 음악을 질의에 따라 검색해 주며 인간의 감성을 고려하지 못하고 있다. 따라서 본 논문에서는 질의에 의한 검색뿐만 아니라 질의한 음원과 감성정도가 같은 음원을 추천하는 인간 감성 기반 음악 검색 및 추천 시스템을 제안한다. 인간 감성 기반 음악 검색 및 추천 시스템은 크게 2가지 요소로 구성된다. 첫 번째는 사용자가 질의한 질의어를 분석하는 감성기반 검색추론엔진과 두 번째는 음원의 특징 정보 및 감성 정보를 가지고 있는 음원 감성 정보 데이터베이스로 구성된다. 사용자의 감성에 따라 음악을 검색하고 추천한다는 것은 향후 음반 산업에 큰 발전에 기여할 것으로 기대한다.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.6
• /
• pp.488-496
• /
• 2004

This paper describes a music information retrieval system which uses humming as the key for retrieval Humming is an easy way for the user to input a melody. However, there are several problems with humming that degrade the retrieval of information. One problem is a human factor. Sometimes people do not sing accurately, especially if they are inexperienced or unaccompanied. Another problem arises from signal processing. Therefore, a music information retrieval method should be sufficiently robust to surmount various humming errors and signal processing problems. A retrieval system has to extract pitch from the user's humming. However pitch extraction is not perfect. It often captures half or double pitches. even if the extraction algorithms take the continuity of the pitch into account. Considering these problems. we propose a system that takes multiple pitch candidates into account. In addition to the frequencies of the pitch candidates. the confidence measures obtained from their powers are taken into consideration as well. We also propose the use of an algorithm with three dimensions that is an extension of the conventional DP algorithm, so that multiple pitch candidates can be treated. Moreover in the proposed algorithm. DP paths are changed dynamically to take deltaPitches and IOIratios of input and reference notes into account in order to treat notes being split or unified. We carried out an evaluation experiment to compare the proposed system with a conventional system. From the experiment. the proposed method gave better retrieval performance than the conventional system.

• Journal of Korea Multimedia Society
• /
• v.15 no.1
• /
• pp.18-31
• /
• 2012

This paper proposes a matching engine of query-by-singing/humming (QbSH) system which retrieves the most similar music information by comparing the input data with the extracted feature information from polyphonic music like MP3. The feature sequences transcribed from polyphonic music may have many errors. So, to reduce the influence of errors and improve the performance, the chroma-scale representation, compensation and asymmetric DTW (Dynamic Time Warping) are adopted in the matching engine. The performance of various distance metrics are also investigated in this paper. In our experiment, the proposed QbSH system achieves MRR (Mean Reciprocal Rank) of 0.718 for 1000 singing/humming queries when searching from a database of 450 polyphonic musics.

• The KIPS Transactions:PartA
• /
• v.10A no.6
• /
• pp.737-748
• /
• 2003

With the popularity of digital music contents, querying and retrieving music contents efficiently from database has become essential. In this paper, we propose a Fast Melody Finder (FMF) that can retrieve melodies fast and efficiently from music database using frequently queried tunes. This scheme is based on the observation that users have a tendency to memorize and query a small number of melody segments, and indexing such segments enables fast retrieval. To handle those tunes, FMF transcribes all the acoustic and common music notational inputs into a specific string such as UDR and LSR. We have implemented a prototype system and showed on its performance through various experiments.

• Journal of the Korean Society for information Management
• /
• v.23 no.2
• /
• pp.5-19
• /
• 2006

The purpose of this study is to observe and analyze information searching behaviors of various user groups in different access modes for designing user-centered query interface of content-based Music Information Retrieval System(MIRS). Two expert groups and two non-expert groups were recruited for this research. The data gathering techniques employed in this study were in-depth interviewing, participant observation, searching task experiments, think-aloud protocols, and post-search surveys. Expert users, especially majoring in music theory, preferred to input exact notes one by one using the devices such as keyboard and musical score. On the other hand, non-expert users preferred to input melodic contours by humming.