基於高階模糊派翠網路之國語卡拉OK歌詞自動校準系統

在數位家庭娛樂中，卡拉OK是一個能夠讓大人、小孩、不分任何年齡同樂的休閒活動之一，只需跟著歌詞就可以唱出一首歌曲，這簡單且有趣的優點讓卡拉OK逐漸盛行，但在傳統的卡拉OK系統中，還是利用最原始的方式來製作卡拉OK歌曲，這需要花費大量人力來一句句的同步化音樂與歌詞，相當沒有效率，讓卡拉OK歌曲的製作成本居高不下，也讓家庭式歌唱機器的價格難以被一般家庭所接受。近年來資訊科技日新月異不斷地進步，在數位音樂研究盛行的同時，我們為促使這整個過程更有效率，利用C#程式語言來做自動化程式的編寫，其中使用音樂分割技術中最知名的調性音樂生成理論(A Generative Theory of Tonal Music)來對國語流行音樂作分析，讓音樂自動分割成一句句的音樂樂句，再利用模糊技術的高階模糊派翠網路 (High-Level Fuzzy Petri Net)來判斷，對國語流行音樂以及歌詞分析，並完成音樂切割及卡拉OK歌詞校準，最後我們利用50首國語流行音樂實驗可以證明，此系統可以提供一個良好的精準度，藉此以自動化歌詞校正系統來提升卡拉OK製作，更能幫助使用者簡單的自製卡拉OK音樂，也可以讓家庭式卡拉OK更為方便、更加普及；本研究的結果可以使用在家庭娛樂或其他相關領域之中。

關鍵字

高階模糊派翠網路；家庭娛樂；音樂系統；卡拉OK

並列摘要

In the home entertainment system, a very important leisure facility in the modern life is karaoke, which is a popular activity, enjoyed by the elderly and the young people. With karaoke systems and microphones, users can sing along with lyrics based on recordings of pop songs that have the singer’s voice removed. While a lot of karaoke software or apparatuses display lyrics automatically, they traditionally require the lyrics to be input manually, and need to be synchronized step-by-step with the tonal music, which requires a significant amount of time. 　　With advances in computer technology, music albums have gradually been replaced by digital music purchased on-line. Nowadays digital music researches suggest that automatically calibrating karaoke lyrics may be possible. First, musical phrase segmentation is required. One of the most famous musical phrase segmentation theories is a generative theory of tonal music, and we use C# programming language to implement and design the karaoke system. The system can automatically segment music phrases and according to a high-level fuzzy Petri net to analyze and calibrate pop songs with lyrics, and then an automatic calibration system for Chinese karaoke lyrics is complete. Finally, 50 Chinese pop songs are used to test, and the experimental results show that the final precision is better. As a result, we propose a practical system to enhance the convenience of karaoke, and the result of this study may be used in the fields of home entertainment or other relevant systems.

並列關鍵字

Home entertainment ； Music ； Karaoke ； High-level fuzzy Petri net

參考文獻

[25] V. R. L. Shen, Y. S. Chang and T. T. Y. Juang, "Supervised and unsupervised learning by using Petri nets," IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans, vol. 40, no. 2, pp. 363-375, 2010.

[1] A. Klapuri, “Sound onset detection by applying psychoacoustic knowledge,” Processing of IEEE International Conference on Acoustics, Speech and Signal, Phoenix, pp. 115-118, 1999.

[2] A. Klapuri, A.J. Eronen, and J.T. Astola, “Analysis of the meter of acoustic musical signals,” IEEE Transaction on Audio, Speech, and Language Processing, vol.14, no.1, pp.342-355, 2006.

[3] B.W. Frankland and A.J. Cohen, “Parsing of melody: quantiﬁcation and testing of the local grouping rules of Lerdahl and Jackendoff’s a generative theory of tonal music,” Music Perception, vol. 21, no. 4, pp. 499-543, 2004.

[5] D. L. Baggi, “An IEEE standard for symbolic music,” IEEE Computer, pp.100-102, 2005.

國際替代計量

基於高階模糊派翠網路之國語卡拉OK歌詞自動校準系統

未授權

主題瀏覽