A Music Retrieval System which Estimates Characteristics of Data based on Users' Sensibility.

Accession number;02A0233733
Title;A Music Retrieval System which Estimates Characteristics of Data based on Users' Sensibility.
Author; MIURA MANAMI (Iwate Prefectural Univ., Faculty of Software & Info. Sci., JPN) MITSUISHI TAKASHI (Iwate Prefectural Univ., Faculty of Software & Info. Sci., JPN) SASAKI JUN (Iwate Prefectural Univ., Faculty of Software & Info. Sci., JPN) FUNYU YUTAKA (Iwate Prefectural Univ., Faculty of Software & Info. Sci., JPN)
Journal Title;Joho Shori Gakkai Kenkyu Hokoku
Journal Code:Z0031B
ISSN:0919-6072
VOL.2002;NO.3(DBS-126);PAGE.129-136(2002)
Figure&Table&Reference;FIG.4, TBL.2, REF.11
Pub. Country;Japan
Language;Japanese
Abstract;We propose a music retrieval system which could estimate individual characteristics of music data based on users' sensibility. It estimates each user's interest (user model) from the history; which data he/she had accessed, estimates a characteristc of music data (music title model) from history; by which users it had been accessed, and create indices in emotional words from estimated characteristics semi-automatically. However it is difficult to create indices expressing individual characteristics of music data, this system could create more appropriate indices and we could retrieve target data efficiently from music database. In order to show the effectiveness of our system, we perform a simple experiment. (author abst.)