説明
type:text
We have developed a music retrieval system that takes a humming query and finds similar audio intervals (segments) in a musical audio database. This system enables a user to retrieve a segment of a musical audio signal desired just by singing its melody. In this paper, we propose a method to compress the music database through similarity analysis. The distance of chroma vectors is used as a similariity measeure.The aim of this compressin is to reduce the retrieval time. Practical experiments was conducted by actually using 115 musical audios in the RWC popular music database. We report that the compression ratio is about 45%.
収録刊行物
-
- 埼玉大学紀要. 工学部 第1編 第1部 論文集 = The Science and Engineering Reports of Saitama University
-
埼玉大学紀要. 工学部 第1編 第1部 論文集 = The Science and Engineering Reports of Saitama University 38 22-26, 2005
埼玉大学工学部
- Tweet
キーワード
詳細情報 詳細情報について
-
- CRID
- 1390572174766936320
-
- NII論文ID
- 120006387908
-
- ISSN
- 18804446
-
- Web Site
- http://id.nii.ac.jp/1586/00016073/
-
- 本文言語コード
- ja
-
- 資料種別
- departmental bulletin paper
-
- データソース種別
-
- JaLC
- IRDB
- CiNii Articles
