1. bookVolume 10 (2018): Issue 2 (December 2018)
Journal Details
First Published
30 May 2014
Publication timeframe
2 times per year
access type Open Access

Connecting the Last.fm Dataset to LyricWiki and MusicBrainz. Lyrics-based experiments in genre classification

Published Online: 31 Dec 2018
Volume & Issue: Volume 10 (2018) - Issue 2 (December 2018)
Page range: 158 - 182
Received: 07 Sep 2018
Journal Details
First Published
30 May 2014
Publication timeframe
2 times per year

Music information retrieval has lately become an important field of information retrieval, because by profound analysis of music pieces important information can be collected: genre labels, mood prediction, artist identification, just to name a few. The lack of large-scale music datasets containing audio features and metadata has lead to the construction and publication of the Million Song Dataset (MSD) and its satellite datasets. Nonetheless, mainly because of licensing limitations, no freely available lyrics datasets have been published for research.

In this paper we describe the construction of an English lyrics dataset based on the Last.fm Dataset, connected to LyricWiki’s database and MusicBrainz’s encyclopedia. To avoid copyright issues, only the URLs to the lyrics are stored in the database. In order to demonstrate the eligibility of the compiled dataset, in the second part of the paper we present genre classification experiments with lyrics-based features, including bagof-n-grams, as well as higher-level features such as rhyme-based and statistical text features. We obtained results similar to the experimental outcomes presented in other works, showing that more sophisticated textual features can improve genre classification performance, and indicating the superiority of the binary weighting scheme compared to tf–idf.


MSC 2010

[1] C. Apté, F. Damerau, and S. M. Weiss. Toward language independent automated learning of text categorization models. In Proceedings of the 17th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 23–30, Dublin, Ireland, 1994. Springer-Verlag. ⇒17110.1007/978-1-4471-2099-5_3Search in Google Scholar

[2] J. Atherton and B. Kaneshiro. I said it first: Topological analysis of lyrical influence networks. In ISMIR, pages 654–660, 2016. ⇒162Search in Google Scholar

[3] T. Bertin-Mahieux, D. P. W. Ellis, B. Whitman,and P. Lamere. The million song dataset. In A. Klapuri and C. Leider, editors, ISMIR, pages 591–596. University of Miami, 2011. ⇒159, 160Search in Google Scholar

[4] M. Besson, F. Faita, I. Peretz, A.-M. Bonnel, and J. Requin. Singing in the brain: Independence of lyrics and tunes. Psychological Science, 9(6):494–498, 1998. ⇒160, 169Search in Google Scholar

[5] C. M. Bishop. Pattern recognition and machine learning. Springer, 2006. ⇒174Search in Google Scholar

[6] M. J. T. Carneiro. Towards the discovery of temporal patterns in music listening using Last.fm profiles. Master’s thesis, Faculdade de Engenharia da Universidade do Porto, 2011. ⇒170Search in Google Scholar

[7] O. Chapelle, B. Schölkopf, and A. Zien. Semi-Supervised Learning. The MIT Press, 2006. ⇒17810.7551/mitpress/9780262033589.001.0001Search in Google Scholar

[8] K. Choi, Gy. Fazekas, M. Sandler, and K. Cho. Convolutional recurrent neural networks for music classification. In ICASSP, pages 2392–2396. IEEE, 2017. ⇒16110.1109/ICASSP.2017.7952585Search in Google Scholar

[9] K. Choi, J. H. Lee, X. Hu, and J. S. Downie. Music subject classification based on lyrics and user interpretations. In Proceedings of the 79th ASIS&T Annual Meeting: Creating Knowledge, Enhancing Lives through Information & Technology. American Society for Information Science, 2016. ⇒161Search in Google Scholar

[10] H. Corona and M. P. O’Mahony. An exploration of mood classification in the million songs dataset. In 12th Sound and Music Computing Conference,Ireland, 2015. Music Technology Research Group, Department of Computer Science, Maynooth University. ⇒161Search in Google Scholar

[11] D. R. Cox. The regression analysis of binary sequences. Journal of the Royal Statistical Society. Series B (Methodological), 2(2):215–242, 1958. ⇒17410.1111/j.2517-6161.1958.tb00292.xSearch in Google Scholar

[12] S. Dieleman, P. Brakel, and B. Schrauwen. Audio-based music classification with a pretrained convolutional network. In ISMIR, pages 669–674, 2011. ⇒161Search in Google Scholar

[13] S. Dieleman and B. Schrauwen. Multiscale approaches to music audio feature learning. In ISMIR, pages 116–121, 2013. ⇒161Search in Google Scholar

[14] S. Dieleman and B. Schrauwen. End-to-end learning for music audio. In ICASSP, pages 6964–6968. IEEE, 2014. ⇒16110.1109/ICASSP.2014.6854950Search in Google Scholar

[15] D. P. W. Ellis. Extracting information from music audio. Communications of the ACM, 49(8):32–37, 2006. ⇒16010.1145/1145287.1145310Search in Google Scholar

[16] R. J. Ellis, Z. Xing, J. Fang, and Y. Wang. Quantifying lexical novelty in song lyrics. In ISMIR, pages 694–700, 2015. ⇒162Search in Google Scholar

[17] M. Fell and C. Sporleder. Lyrics-based analysis and classification of music. In J. Hajic and J. Tsujii, editors, COLING, pages 620–631. ACL, 2014. ⇒ 159, 161, 170, 172, 174Search in Google Scholar

[18] J. Fürnkranz. A study using n-gram features for text categorization, 1998. ⇒171Search in Google Scholar

[19] W. H. Gomaa and A. A. Fahmy. A survey of text similarity approaches. International Journal of Computer Applications, 68(13):13–18, April 2013. ⇒17210.5120/11638-7118Search in Google Scholar

[20] S. Gupta. Music data analysis: A state-of-the-art survey. arXiv preprint arXiv:1411.5014, 2014. ⇒160Search in Google Scholar

[21] P. Hamel and D. Eck. Learning features from music audio with deep belief networks. In ISMIR, volume 10, pages 339–344, 2010. ⇒161Search in Google Scholar

[22] H. Hirjee and D. G. Brown. Using automated rhyme detection to characterize rhyming style in rap music. Empirical Musicology Review, 5(4), 2010. ⇒172, 17810.18061/1811/48548Search in Google Scholar

[23] D. Jurafsky and J. H. Martin. Speech and language processing. 2017. 3rd edition draft. ⇒177Search in Google Scholar

[24] A. Kiss. Classification of hungarian folk music from Transylvania with convolutional neural networks. Master’s thesis, Faculty of Mathematics and Computer Science,Babeş–Bolyai University, Romania, 2018. ⇒161Search in Google Scholar

[25] P. Knees and M. Schedl. Music Similarity and Retrieval. Springer, Berlin–Heidelberg, 2016. ⇒16010.1007/978-3-662-49722-7Search in Google Scholar

[26] P. Knees, M. Schedl, and G. Widmer. Multiple lyrics alignment: Automatic retrieval of song lyrics. In ISMIR, pages 564–569, 2005. ⇒160Search in Google Scholar

[27] D. E. Knuth. The Art of Computer Programming, Vol. 3: Sorting and Searching. Addison-Wesley, Reading, MA, 1973. ⇒172Search in Google Scholar

[28] Q. Le and T. Mikolov. Distributed representations of sentences and documents. In Proceedings of The 31st International Conference on Machine Learning, pages 1188–1196, 2014. ⇒178Search in Google Scholar

[29] V. I. Levenshtein. Binary codes capable of correcting deletions, insertions, and reversals. Soviet physics doklady, 10(8):707–710, 1966. ⇒172Search in Google Scholar

[30] T. L. H. Li, A. B. Chan,and A. Chun. Automatic musical pattern feature extraction using convolutional neural network. In Proc. Int. Conf. Data Mining and Applications, 2010. ⇒161Search in Google Scholar

[31] D. Liang,H.Gu, and B. O’Connor. Music genre classification with the million song dataset. Technical report, Machine Learning Department, CMU, 2011. ⇒161, 170Search in Google Scholar

[32] J. P. G. Mahedero, A. Martinez, P. Cano, M. Koppenberger, and F. Gouyon. Natural language processing of lyrics. In ACM Multimedia, pages 475–478. ACM, 2005. ⇒17010.1145/1101149.1101255Search in Google Scholar

[33] R. Malheiro, R. Panda, P. Gomes, and R. Paiva. Classification and regression of music lyrics: Emotionally-significant features. In 8th International Conference on Knowledge Discovery and Information Retrieval, Porto, Portugal, 2016. ⇒16110.5220/0006037400450055Search in Google Scholar

[34] C. D. Manning, P. Raghavan,and H. Schütze. Introduction to information retrieval. Cambridge University Press, 2008. ⇒17410.1017/CBO9780511809071Search in Google Scholar

[35] M. Mauch, R. M. MacCallum, M. Levy, and A. M. Leroi. The evolution of popular music: USA 1960–2010. Royal Society Open Science, 2(5), 2015. ⇒16310.1098/rsos.150081445325326064663Search in Google Scholar

[36] R. Mayer, R. Neumayer, and A. Rauber. Rhyme and style features for musical genre classification by song lyrics. In J. P. Bello, E. Chew, and D. Turnbull, editors, ISMIR, pages 337–342, 2008. ⇒161, 170, 173, 174Search in Google Scholar

[37] R. Mayer and A. Rauber. Music genre classification by ensembles of audio and lyrics features. In A. Klapuri and C. Leider, editors, ISMIR, pages 675–680. University of Miami, 2011. ⇒159Search in Google Scholar

[38] C. McKay and I. Fujinaga. Musical genre classification: Is it worth pursuing and how can it be improved? In ISMIR, pages 101–106, 2006. ⇒161, 169, 170Search in Google Scholar

[39] J.-B. Michel, Y. K. Shen, A. P. Aiden, A. Veres, M. K. Gray, J. P. Pickett, D. Hoiberg,D.Clancy, P. Norvig,J.Orwant, S. Pinker, M. A. Nowak,and E. Lieberman Aiden. Quantitative analysis of culture using millions of digitized books. Science, 331:176–182, 2011. ⇒17810.1126/science.1199644327974221163965Search in Google Scholar

[40] T. Mikolov, K. Chen, G. Corrado,and J. Dean. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781, 2013. ⇒178Search in Google Scholar

[41] T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado,and J. Dean. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems, pages 3111–3119, 2013. ⇒178Search in Google Scholar

[42] L. Németh. Automatic non-standard hyphenation in OpenOffice.org. TUGboat, 27(1):32–37, 2006. ⇒172Search in Google Scholar

[43] F. Pachet and D. Cazaly. A taxonomy of musical genres. In J.-J. Mariani and D. Harman, editors, RIAO, pages 1238–1245. CID, 2000. ⇒170Search in Google Scholar

[44] J. Pennington, R. Socher,and C. Manning. GloVe: Global vectors for word representation. In EMNLP, pages 1532–1543, 2014. ⇒17810.3115/v1/D14-1162Search in Google Scholar

[45] L. Philips. Hanging on the metaphone. Computer Language Magazine, 7(12):38, December 1990. ⇒178Search in Google Scholar

[46] L. Philips. The double metaphone search algorithm. C/C++ Users Journal, 18(6), June 2000. ⇒178Search in Google Scholar

[47] J. Pons, T. Lidy,and X. Serra. Experimenting with musically motivated convolutional neural networks. In CBMI, pages 1–6. IEEE, 2016. ⇒16110.1109/CBMI.2016.7500246Search in Google Scholar

[48] R. Priedhorsky, J. Chen, S. T. K. Lam, K. Panciera, L. Terveen,and J. Riedl. Creating, destroying, and restoring value in Wikipedia. In Proceedings of the 2007 international ACM conference on Supporting group work, pages 259–268. ACM, 2007. ⇒16010.1145/1316624.1316663Search in Google Scholar

[49] S. Reddy and K. Knight. Unsupervised discovery of rhyme schemes. In ACL (Short Papers), pages 77–82. The Association for Computer Linguistics, 2011. ⇒172Search in Google Scholar

[50] G. Salton, A. Wong, and A. C. S. Yang. A vector space model for automatic indexing. Communications of the ACM, 18:229–237, 1975. ⇒159, 17110.1145/361219.361220Search in Google Scholar

[51] H. Schreiber. Improving genre annotations for the million song dataset. In M. Müller and F. Wiering, editors, ISMIR, pages 241–247, 2015. ⇒170Search in Google Scholar

[52] F. Sebastiani. Machine learning in automated text categorization. ACM Computing Surveys, 34(1):1–47, 2002. ⇒17410.1145/505282.505283Search in Google Scholar

[53] S. Sigtia and S. Dixon. Improved music feature learning with deep neural networks. In ICASSP, pages 6959–6963. IEEE, 2014. ⇒16110.1109/ICASSP.2014.6854949Search in Google Scholar

[54] A. Singhi and D. G. Brown. Are poetry and lyrics all that different? In H.-M. Wang, Y.-H. Yang, and J. H. Lee, editors, Proceedings of the 15th International Society for Music Information Retrieval Conference, ISMIR 2014, Taipei, Taiwan, October 27–31, 2014, pages 471–476, 2014. ⇒161Search in Google Scholar

[55] B. L. Sturm. An analysis of the gtzan music genre dataset. In Proceedings of the second international ACM workshop on Music information retrieval with user-centered and multimodal strategies, pages 7–12. ACM, 2012. ⇒16010.1145/2390848.2390851Search in Google Scholar

[56] B. L. Sturm. A survey of evaluation in music genre recognition. In International Workshop on Adaptive Multimedia Retrieval, pages 29–66. Springer, 2012. ⇒16110.1007/978-3-319-12093-5_2Search in Google Scholar

[57] A. Swartz. MusicBrainz: a semantic Web service. IEEE Intelligent Systems, 17(1):76–77, 2002. ⇒164Search in Google Scholar

[58] A. Tsaptsinos. Lyrics-based music genre classification using a hierarchical attention network. In ISMIR, pages 694–701, 2017. ⇒162Search in Google Scholar

[59] G. Tzanetakis and P. Cook. Musical genre classification of audio signals. IEEE Transactions on speech and audio processing, 10(5):293–302, 2002. ⇒16010.1109/TSA.2002.800560Search in Google Scholar

[60] E. Zangerle, M. Tschuggnall, S. Wurzinger, and G. Specht. Alf-200k: Towards extensive multimodal analyses of music tracks and playlists. In European Conference on Information Retrieval, pages 584–590. Springer, 2018. ⇒16210.1007/978-3-319-76941-7_48Search in Google Scholar

Recommended articles from Trend MD

Plan your remote conference with Sciendo