以GEP有效分類數位音樂

Digital Music Classification Using Genetic Expression Programming

劉伯恆(Bo-Heng Liu)

指導教授 ： 劉俞志

元智大學/資訊學院/資訊管理學系/碩士(2008年)

https://doi.org/10.6838/YZU.2008.00057

摘要

過去，已有許多學者試圖提出解決音樂分類問題的方法，但基於音樂檔案的組成要素複雜，且音樂曲風種類的分類準則由人的知覺定出，無特定的量化規則可循，使音樂檔案的分類問題更加困難。本研究提出以基因表示規劃(Genetic Expression Programming)為基礎，以Midi音樂檔案各項特徵之統計資訊作分類，建立音樂內容(context-based)的曲風分類規則，其成果可應用於各類之音樂分類及推薦系統。

關鍵字

音樂曲風分類 ； 基因表示規劃 ； 音樂推薦 ； 數位音樂

並列摘要

There have been many algorithm proposed to solve music classification problems. The composition of music context is complicated, and the music genre is defined by musical perception. Lacking of qualifications to determinate music genres makes music classification more difficult. In this paper, method based on genetic expression programming to classify Midi music files was proposed. This method uses statistical information of Midi file features to classify Midi music genres, and builds models and classification rules. The result can be use for music recommendation or classification systems.

並列關鍵字

Music Genre Classification ； Genetic Expression Programming ； Music Rcommendation ； Midi

參考文獻

[1]B., Thom and D., Watson “A machine learning approach to musical style recognition RB Dannenberg,” Proceedings of International Computer Music Conference, pp.344-347, 1997.

[2]C., McKay and I., Fujinaga, “Automatic genre classification using large high-level musical feature sets,” 5th International Conference on Music Information Retrieval , 2004.

[5]F.F, Kuo and M.K., Shan, “A Personalized Music Filtering System Based on Melody Style Classification,” Proceedings of IEEE International Conference on Data Mining, pp. 649-652, 2002.

[6]F.F, Kuo, M.K, Shan and M.F, Chen “Music Style Mining and Classification by Melody,” Proceedings of IEEE International Conference on Multimedia and Expo, pp.91-100, 2002.

[7]Ferreira, C., Gene Expression Programming: A New Adaptive Algorithm for Solving Problems. Complex Systems, Vol. 13, No. 2: pp. 87-129, 2001.