一般而言,一個內容式音樂檢索(CBMR, Content-based Music Retrieval) 系統是藉由使用者輸入的一串資訊(歌聲、樂曲),經由比對資料庫中的MIDI而找出使用者想找的歌曲。歌曲的比對須要大量的計算能力,然在單機版的系統下其計算能力是有限的,因此本論文以分散式平行處理的方法加速CBMR的系統。分散式平行處理下的CBMR提供了比單機版更快的速度,更穩定的回應和可擴展式的運算能力。在異質性平台下,我們在不同的作業系統、不同的硬體設備下實作了一個平行版的分散式音樂檢索系統。另本文亦把現行熱門的雲端運算做一整理介紹,並對分散式音樂檢索在雲端運算下的可行性做出討論。
In general, a CBMR (Content-based Music Retrieval) system requires heavy computation in order to retrieve an intended song specified by the acoustic input of the user. The heavy computation is primarily spent on similarity comparison, and the computation time is proportional to the number of songs in the database. The goal of this research is to speed up the similarity comparison via parallel processing, such that the user can obtain the comparison results in a reasonable amount of time. Our parallel version of CBMR system not only has a faster response time, but also has a better recognition rate. The implementation is based on heterogeneous platforms with different operating systems and hardware configurations, and a satisfying improvement has been shown in the performance result. Moreover, cloud computing is also introduced in this study and the feasibility of the CBMR in cloud computing is also discussed.