Ultra High Speed Audio Fingerprint Detection and Search

2014 Fiscal Year Final Research Report

• Project/Area Number: 24300016
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Computer system/Network
• Research Institution: Japan Advanced Institute of Science and Technology
• Principal Investigator: INOGUCHI Yasushi 北陸先端科学技術大学院大学, 情報社会基盤研究センター, 教授 (90293406)
• Co-Investigator(Kenkyū-buntansha): FUKUSHI Masaru 山口大学, 理工学研究科, 准教授 (50345659)
• Co-Investigator(Renkei-kenkyūsha): KANEKO Mineo 北陸先端科学技術大学院大学, 情報科学研究科, 教授 (00185935) ; SATOU Yukinori 北陸先端科学技術大学院大学, 情報社会基盤研究センター, 助教 (30452113)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: リコンフィギャラブル / FPGA / 電子指紋 / 音楽検索 / データベース / ハッシュ / Staged LSH / インターネット

Outline of Final Research Achievements

This research addresses ultra-high speed audio fingerprint detection from mp3 files that traded through the internet. Hardware supported audio fingerprint detection algorithms that mostly uses only addition and subtraction has been proposed as HiFP 2.0. Concerning searching, the Staged-LSH method that is hierarchical hash-based algorithm was proposed. This algorithm takes advantage physical hierarchical structure such as Flip-Flops and Block RAM in FPGA and off-chip D-RAM.
Network on Chip, fault avoidance, and hierarchical interconnection are also investigated.

Free Research Field

並列処理