著者

北 研二 肖 清梅

雑誌

研究報告音楽情報科学(MUS)

巻号頁・発行日

vol.2011, no.4, pp.1-6, 2011-05-06

---

楽曲検索では,ノイズ等による楽曲の劣化や,検索質問曲の演奏開始位置が不明であることから,一般に膨大な検索空間を探索する必要がある.多くの楽曲検索システムでは,楽曲の音響的・知覚的な特性に基づくオーディオ指紋 (audio fingerprint) を特徴量として用いているが,本稿では,オーディオ指紋に適した高速検索手法を提案する.また,8,740 曲の楽曲データベースを用いた評価実験を行い,提案手法の有効性を示す.In music information retrieval, a huge search space has to be explored because a query audio clip can start at any position of any music in the database, and also a query is often corrupted by highly significant noise and distortion. Audio fingerprints have attracted much attention recently in music information retrieval, because they provide compact representation of the perceptually relevant parts of audio signals. In this paper, we propose an extremingly fast method for exploring a huge hamming space that is suitable for audio fingerprinting systems. The effectiveness of the proposed method has been confirmed by evaluation experiments using a database of 8,740 songs.