Abstract
The impact of music on the many dimensions of human life can be partly attributed to its linguistic component – the lyrics. In hopes of helping songwriters reach their full potential, researchers have implemented advanced artificial intelligence (AI) technology to automatically generate song lyrics. These efforts, however, were met with challenges that accompany the distinctive qualities of song lyrics, such as word repetition, structural pattens, and line breaks; all of which are dependent on the music genre. Seeing as most previous research either focuses on a given approach or genre, or performs the task without consideration of lyric variation among genres, this study attempts to address the gap by exploring and comparing the capabilities of three promising methods, specifically Markov chains, long short-term memory (LSTM), and gated recurrent units (GRU), in algorithmically generating lyrics for six selected music genres, namely rock, pop, country, hip-hop, electronic dance music (EDM), and rhythm and blues (R&B). Our findings show that LSTM scored better in the average readability index in overall, however, GRU produced the overall highest Rhyme Density score.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Montagu, J.: How music and instruments began: A brief overview of the origin and entire development of music, from its earliest stages. Front. Sociol. 2, 8 (2017)
Levinowitz, L.M.: The importance of music in early childhood. General Music Today 12(1), 4–7 (1998)
North, A.C., Hargreaves, D.J., O’Neill, S.A.: The importance of music to adolescents. Br. J. Psychol. 70(2), 255–272 (2000)
Cohen, A., Bailey, B., Nilsson, T.: The importance of music to seniors. Psychomusicol. J. Res. Music Cogn. 18(1–2), 89–102 (2002)
Barradas, G.T., Sakka, L.S.: When words matter: a cross-cultural perspective on lyrics and their relationship to musical emotions. Psychol. Music 50(2), 650–669 (2022)
Astor, P.: The poetry of rock: song lyrics are not poems but the words still matter; another look at Richard Goldstein’s collection of rock lyrics. Pop. Music 29(1), 143–148 (2010)
Russell, E.: 25 pop songs with social messages. In: PopCrush (2015). https://popcrush.com/pop-songs-social-messages. Accessed 11 Aug 2022
Pudaruth, S., Amourdon, S., Anseline, J.: Automated generation of song lyrics using CFGs. In: 2014 Seventh International Conference on Contemporary Computing (IC3), pp. 613–616. IEEE, Noida, India (2014)
Gill, H., Lee, D.T., Marwell, N.: Deep learning in musical lyric generation: an LSTM- based approach. Yale Undergrad. Res. J. 1(1), 1–7 (2020)
Barbieri, G., Pachet, F., Roy, P., Esposti, M. D.: Markov constraints for generating lyrics with style. In: Proceedings of the 20th European Conference on Artificial Intelligence (ECAI 2012), pp. 115–120. IOS Press, Amsterdam, Netherlands (2012)
Fernandez, A.C.T., Tarnate, K.J.M., Devaraj, M.: Deep rapping: character level neural models for automated rap lyrics composition. Int. J. Innov. Technol. Explor. Eng. (IJITEE) 8(2S), 306–311 (2018)
Lowder, J.: The 10 most popular music genres. In: Audio Captain (2021). https://audiocaptain.com/most-popular-music-genres. Accessed 11 Aug 2022
Clark, B.: The top 10 genres in the music industry. In: Musician Wave (2021). https://www.musicianwave.com/top-music-genres. Accessed 11 Aug 2022
Settles, B.: Computational creativity tools for songwriters. In: Proceedings of the NAACL HLT 2010 Second Workshop on Computational Approaches to Linguistic Creativity, pp. 49–57. Association for Computational Linguistics, Los Angeles, California, USA (2010)
Al-Anzi, F.S., AbuZeina, D.: A survey of Markov chain models in linguistics applications. In: Computer Science and Information Technology (CS & IT) Conference Proceedings, vol. 6, no. 13, pp. 53–62. AIRCC Publishing Corporation, Chennai, Tamil Nadu, India (2016)
Brownlee, J.: A gentle introduction to long short-term memory networks by the experts. In: Machine Learning Mastery (2017). https://machinelearningmastery.com/gentleintroduction-long-short-term-memory-networks-experts. Accessed 11 Aug 2022
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Rathore, A.S.: LSTM — Introduction in simple words. In: Medium (2020). https://medium.com/nerd-for-tech/lstm-introduction-in-simple-words-fe544a45f1e7. Accessed 11 Aug 2022
Cho, K., et al.: Learning phrase representations using RNN encoder–decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734. Association for Computational Linguistics, Doha, Qatar (2014)
Shen, G., Tan, Q., Zhang, H., Zeng, P., Xu, J.: Deep learning with gated recurrent unit networks for financial sequence predictions. Proc. Comput. Sci. 131, 895–903 (2018)
Saxena, S.: Introduction to gated recurrent unit (GRU). In: Analytics Vidhya (2021). https://www.analyticsvidhya.com/blog/2021/03/introduction-to-gated-recurrent-unit-gru. Accessed 11 Aug 2022
Banga, S.S.: Readability index in Python (NLP). In: GeeksforGeeks (2021). https://www.geeksforgeeks.org/readability-index-pythonnlp. Accessed 11 Aug 2022
Hirjee, H., Brown, D.G.: Using automated rhyme detection to characterize rhyming style in rap music. Empir. Musicol. Rev. 5(4), 121–145 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Tee, T.H., Bei Yeap, B.Q., Gan, K.H., Tan, T.P. (2022). Learning to Automatically Generating Genre-Specific Song Lyrics: A Comparative Study. In: Villazón-Terrazas, B., Ortiz-Rodriguez, F., Tiwari, S., Sicilia, MA., Martín-Moncunill, D. (eds) Knowledge Graphs and Semantic Web . KGSWC 2022. Communications in Computer and Information Science, vol 1686. Springer, Cham. https://doi.org/10.1007/978-3-031-21422-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-21422-6_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-21421-9
Online ISBN: 978-3-031-21422-6
eBook Packages: Computer ScienceComputer Science (R0)