音樂什錦歌由多首現存的歌剪輯而成。無論是選定合適相接的歌曲、或是無縫地將歌曲接合,都是很困難的挑戰,使得手動製作什錦歌非常耗時與費神。此篇論文提出一個人化什錦歌製作系統。與目前僅僅低階的音訊特徵的研究不同在於,在製作什錦歌時,此系統考慮歌曲結構以及樂曲段落,來挑選什錦歌中的歌曲片段,以及尋找可能的樂曲接點。受音樂骰子遊戲所啟發,此篇論文將什錦歌製作視為音訊版的骰子遊戲。一但使用者完成分析音樂選集中的歌曲特性,此系統便能依據音樂片段之間的轉換機率來製作出形形色色的什錦歌。靈活的設計使此系統能根據使用者指定的的條件來產生什錦歌,例如什錦歌的結構、或是欲使用在什錦歌中的歌曲。初步的主觀評論證明此系統之設計能有效地選出可替換且互相可連接的音樂片段;此外,實驗也顯示與前人研究比起來,使用者較偏好保留樂句完整性之什錦歌。
A musical medley is a piece of music that is composed of parts of existing pieces. Manually creating medley is time consuming since finding out proper clips to be put in succession and seamlessly connect them are both difficult tasks. In this work, we propose a framework for creating personalized music medley from users' music ollection.Unlike existing similar researches where only low-level features are used to select candidate clips and locate possible transition points among clips, we take song structure and song phrasing into account during medley creation. Inspired by the musical dice game, we treat the medley generation process as an audio version musical dice game. That is, once the analysis on the songs of user collection has been done, the system is able to generate various medleys with different probabilities. This flexibility brings us the ability to create medleys according to the user specified conditions, such as the medley structure or a number of must-use clips. The preliminary subjective evaluations show that the proposed system is effective in selecting interchangeable and connectable clips. Besides, connecting the clips at phrase boundaries acquired more user preference than previous works did.