電子舞曲（EDM）是一種主要由電子樂器組成的流派，旨在推動舞蹈衝動。唱片騎士（DJ）是EDM歌曲中的關鍵角色之一，他們以選擇合適的EDM歌曲的能力而聞名。 DJ可以透過歌曲能量強度變化、相對的調性和類似的風格的歌曲來保持跳舞的氣氛。然而，由於需要知識和經驗，執行這樣的任務是非常具有挑戰性的。僱用一個DJ一般來說是很昂貴的，尤其是從長遠來看。作為人類，DJ的工作時間也是有限的，因為他們不能連續工作而不休息。隨著神經網絡和音樂分類的最新進展，我們可以開發一種每個人都可以輕鬆使用的自動選歌。我們提出了一種自動選歌的方法，根據能量強度的逐漸變化、相對的調性和相似的歌曲來選擇EDM歌曲。根據台灣15位專業DJ對400首EDM歌曲的評價，所提出的系統所選擇的歌曲被證實能夠滿足聽眾的要求，以平均意見分數（MOS）作為衡量標準。

Electronic Dance Music (EDM) is a genre mainly composed of electronic instruments designed to drive dancing urges. A disc jockey (DJ), one of the critical actors in the EDM song, is known for their ability to choose suitable EDM songs. DJs can maintain a dancing atmosphere by choosing the song with good energy level change, similar keys, and similar style. However, performing such tasks is very challenging due to the knowledge and experience needed. Hiring a DJ generally is expensive, especially in the long run. As humans, DJs also have limited work hours as they cannot work continuously without taking a break. With the recent advancement in neural network and music classification, we can develop an automatic song selection that everyone can use easily. We propose an automatic song selection by selecting an EDM song according to the gradual change of energy level, similar key, and similar song. Based on evaluations from 15 professional DJs in Taiwan using 400 EDM songs, the selected song from the proposed system were confirmed to be able to satisfy the audience, with mean opinion score (MOS) as the metric.

[1] M. I. Key, “Harmonic Mixing Guide,” https://mixedinkey.com/harmonic-mixing-guide/, Jun. 2021.

[2] J. W. Cannon and A. E. Greasley, “Exploring relationships between electronic dance music event
participation and well-being,” Music & Science, vol. 4, Jan. 2021.

[3] Á. M. Bjartmarz, “Electronic dance music (edm): brief introduction of edm production,” Ph.D. dissertation, Iceland Academy of the Arts, 2017.

[4] A. Redfield and M. T. Savard, “Electronic dance music events as modern-day ritual,” International Journal of Transpersonal Studies, vol. 36, pp. 52–66, Sep. 2017.

[5] M. J. Butler, Unlocking the groove: Rhythm, meter, and musical design in electronic dance music. Indiana University Press, 2006.

[6] B. Attias, A. Gavanas, and H. Rietveld, DJ culture in the mix: power, technology, and social change in electronic dance music. Bloomsbury Publishing USA, 2013.

[7] E. Mazierska, T. Rigg, and L. Gillon, The Evolution of Electronic Dance Music. Bloomsbury Publishing USA, 2022.

[8] E. Lustig and I. Tan, “All about that bass: Audio filters on basslines determine groove and liking in electronic dance music,” Psychology of Music, vol. 48, no. 6, pp. 861–875, 2020.

[9] R. Brøvig Hanssen, B. Sandvik, J. M. Aareskjold Drecker, and A. Danielsen, “A grid in flux: Sound and timing in electronic dance music,” Music Theory Spectrum, vol. 44, no. 1, pp. 1–16, 2022.

[10] T. Souvaliotis, “Learning edm the ”schooling” of electronic dance musicians,” Ph.D. dissertation, University of Sydney, Jan. 2022.

[11] L. Grogan, “Electronic Music Is the World’s Third Most Popular Genre,” https://mixmag.net/read/electronic-music-third-popular-genre-news/, May 2019.

[12] N. Thompson, “Hey dj, don’t stop the music: Institutional work and record pooling practices in the united states music industry,” Business History, vol. 60, no. 5, pp. 677–698, 2018.

[13] V. S. Ferreira, “Being a dj is not just pressing the play: the pedagogization of a new dream job,” Educação & Realidade, vol. 42, pp. 473–494, 2017.

[14] J. W. Smith, “The functions of continuous processes in contemporary electronic dance music,” Music Theory Online, vol. 27, no. 2, 2021.

[15] H. Wi, K. Hyun, J. Lee, and W. Lee, “The effect of djs’ social network on music popularity,” in ICMC, 2016.

[16] F. Broughton and B. Brewster, How to DJ Right: the art and science of playing records. Grove Press, 2007.

[17] J. Steventon, DJing for dummies. John Wiley & Sons, 2014.

[18] B. Burger and P. Toiviainen, “Embodiment in electronic dance music: Effects of musical content and structure on body movement,” Musicae Scientiae, vol. 24, no. 2, pp. 186–205, 2020.

[19] R. T. Solberg and A. R. Jensenius, “Group behaviour and interpersonal synchronization to electronic dance music,” Musicae Scientiae, vol. 23, no. 1, pp. 111–134, 2019.

[20] B. Brewster and F. Broughton, Last Night a DJ Saved My Life: The History of the Disc Jockey. Grove Press, 2014.

[21] G. Bernardes, M. Davies, and C. Guedes, “A perceptually-motivated harmonic compatibility method for music mixing,” Sep. 2017.

[22] B. Portal, “Beatport: 16 Years in Numbers.” https://www.beatportal.com/news/beatport-16-years-in-numbers/, Jan. 2020.

[23] P. Álvarez, F. Z. Soria, and S. Baldassarri, “Mobile music recommendations for runners based on location and emotions: The dj-running system,” Pervasive and Mobile Computing, vol. 67, p. 101242, 2020.

[24] L. Veire and T. Bie, “From raw audio to a seamless mix: creating an automated dj system for drum and bass,” EURASIP Journal on Audio, Speech, and Music Processing, vol. 2018, Sep. 2018.

[25] A. Kim, S. Park, J. Park, J. W. Ha, T. Kwon, and J. Nam, “Automatic dj mix generation using highlight detection,” Proc. ISMIR, late-breaking demo paper, 2017.

[26] H. Y. Lin, Y. T. Lin, and M. C. Tien, “Music paste: Concatenating music clips based on chroma and rhythm features.” Jan. 2009, pp. 213–218.

[27] T. Hirai, H. Doi, and S. Morishima, “Musicmixer: Computer-aided dj system based on an automatic song mixing,” in Proceedings of the 12th International Conference on Advances in Computer Entertainment Technology, ser. ACE ’15. New York, NY, USA: Association for Computing Machinery, 2015.

[28] D. Ayata, Y. Yaslan, and M. E. Kamasak, “Emotion based music recommendation system using wearable physiological sensors,” IEEE Transactions on Consumer Electronics, vol. 64, no. 2, pp. 196–203, 2018.

[29] H. C. Chen and A. L. P. Chen, “A music recommendation system based on music data grouping and user interests,” in Proceedings of the Tenth International Conference on Information and Knowledge Management, ser. CIKM ’01. New York, NY, USA: Association for Computing Machinery, 2001, p. 231–238.

[30] M. I. Key, “Sorting Your Playlists by Energy Level,” https://mixedinkey.com/harmonic-mixing-guide/sorting-playlists-by-energy-level/, May 2021.

[31] E. Gómez, “Tonal description of polyphonic audio for music content processing,” INFORMS Journal on Computing, vol. 18, pp. 294–304, Aug. 2006.

[32] J. Mehta, D. Gandhi, G. Thakur, and P. Kanani, “Music genre classification using transfer learning on log-based mel spectrogram,” in 2021 5th International Conference on Computing Methodologies and Communication (ICCMC), pp. 1101–1107, 2021.

[33] A. A. S. Gunawan, A. P. Iman, and D. Suhartono, “Automatic music generator using recurrent neural network,” International Journal of Computational Intelligence Systems, vol. 13, no. 1, p. 645–654, 2020.

[34] R. Pascanu, C. Gulcehre, K. Cho, and Y. Bengio, “How to construct deep recurrent neural networks,” in Proceedings of the Second International Conference on Learning Representations (ICLR 2014), 2014.

[35] K. Choi, G. Fazekas, M. Sandler, and K. Cho, “A comparison of audio signal preprocessing methods for deep neural networks on music tagging,” in 2018 26th European Signal Processing Conference (EUSIPCO). IEEE, 2018, pp. 1870–1874.

[36] C. Weiß, H. Schreiber, and M. Müller, “Local key estimation in music recordings: A case study across songs, versions, and annotators,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, pp. 2919–2932, 2020.

[37] F. Korzeniowski and G. Widmer, “Genre-agnostic key classification with convolutional neural networks,” in Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR 2018, Paris, France, September 23-27, 2018, E. Gómez, X. H. 0001, E. Humphrey, and E. Benetos, Eds., 2018, pp. 264–270.

[38] A. Faraldo, S. Jorda, and P. Herrera, “A multi-profile method for key estimation in edm,” in Audio Engineering Society Conference: 2017 AES International Conference on Semantic Audio. Audio Engineering Society, 2017.

[39] D. Whitehead, “How to Craft a Good DJ Set,” https://rolandcorp.com.au/blog/how-to-craft-a-good-dj-set, Sep. 2017.

[40] P. Morse, “How DJs Always Know What Song to Play Next,” https://www.digitaldjtips.com/2021/04/how-djs-always-know-what-song-to-play-next-without-ever-panicking/, Apr. 2021.