Abstract
Learning and analyzing rap lyrics is a significant basis for many applications, such as music recommendation, automatic music categorization, and music information retrieval. Although numerous studies have explored the topic, knowledge in this field is far from satisfactory, because critical issues, such as prosodic information and its effective representation, as well as appropriate integration of various features are usually ignored. In this paper, we propose a hierarchical attention variational autoencoder framework (HAVAE), which simultaneously consider semantic and prosodic features for rap lyrics representation learning. Specifically, the representation of the prosodic features is encoded by phonetic transcriptions with a novel and effective strategy (i.e., rhyme2vec). Moreover, a feature aggregation strategy is proposed to appropriately integrate various features and generate prosodic-enhanced representation. A comprehensive empirical evaluation demonstrates that the proposed framework outperforms the state-of-the-art approaches under various metrics in both NextLine prediction task and rap genre classification task.
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
Notes
- 1.
Monorhyme is a rhyme scheme in which each line has an identical rhyme.
- 2.
In alternate rhyme, the rhyme is on alternate lines.
- 3.
The dimension of \(\varvec{\hat{u}}\) is equal to that of \(\varvec{u}\).
- 4.
- 5.
The source code and dataset are available at https://github.com/mengshor/HAVAE.
- 6.
In the current paper, we report the results in the original work, and reproduce it on the crawled dataset.
References
Addanki, K., Wu, D.: Unsupervised rhyme scheme identification in hip hop lyrics using hidden Markov models. In: ISMIR (2013)
Alexey, T., Ivan, P.Y.: Music generation with variational recurrent autoencoder supported by history. In: CMMR (2017)
Ashman, R., Baird, A., Allard, R., et al.: Effect of spinal construct stiffness on early fusion mass incorporation. Experimental study. Spine 15(9), 908–912 (1990)
Association, I.P.: Handbook of the International Phonetic Association: A guide to the use of the International Phonetic Alphabet. Cambridge University Press, Cambridge (1999)
Bengio, Y.: Learning deep architectures for AI. Mach. Learn. 2(1), 1–127 (2009)
Bryant, P.E., MacLean, M., Bradley, L.L., Crossland, J.: Rhyme and alliteration, phoneme detection, and learning to read. Dev. Psychol. 26(3), 429–438 (1990)
Dosovitskiy, A., Brox, T.: Generating images with perceptual similarity metrics based on deep networks. In: NIPS (2016)
Duddington, J.: eSpeak text to speech (2012)
Fabius, O., van Amersfoort, J.R.: Variational recurrent auto-encoders. arXiv preprint arXiv:1412.6581 (2014)
Hadjeres, G., Nielsen, F., Pachet, F.: GLSR-VAE: geodesic latent space regularization for variational autoencoder architectures. In: SSCI (2017)
He, J., Zhou, M., Jiang, L.: Generating Chinese classical poems with statistical machine translation models. In: AAAI (2012)
Hirjee, H., Brown, D.G.: Automatic detection of internal and imperfect rhymes in rap lyrics. In: ISMIR (2009)
Hirjee, H., Brown, D.G.: Rhyme analyzer: an analysis tool for rap lyrics. In: ISMIR (2010)
Hirjee, H., Brown, D.G.: Using automated rhyme detection to characterize rhyming style in rap music. Empirical Musicology Rev. 5(4), 121–145 (2010)
Hou, X., Shen, L., Sun, K., Qiu, G.: Deep feature consistent variational autoencoder. In: WACV (2017)
Kingma, D.P., Rezende, D.J., Mohamed, S., Welling, M.: Semi-supervised learning with deep generative models. In: NIPS (2014)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2014)
Malmi, E., Takala, P., Toivonen, H., Raiko, T., Gionis, A.: DopeLearning: a computational approach to rap lyrics generation. In: SIGKDD (2016)
Mauch, M., MacCallum, R.M., Levy, M., Leroi, A.M.: The evolution of popular music: USA 1960–2010. Royal Soc. Open Sci. 2(5), 150081 (2015)
Oliveira, H.G.: PoeTryMe: a versatile platform for poetry generation. In: ECAI (2012)
Potash, P., Romanov, A., Rumshisky, A.: GhostWriter: using an LSTM for automatic rap lyric generation. In: EMNLP (2015)
Potash, P., Romanov, A., Rumshisky, A.: Evaluating creative language generation: the case of rap lyric ghostwriting. arXiv preprint arXiv:1612.03205 (2016)
Quoc, L., Tomas, M.: Distributed representations of sentences and documents. In: ICML (2014)
Ruli, M., Graeme, R., Henry, S.T.: Using genetic algorithms to create meaningful poetic text. J. Exp. Theor. Artif. Intell. 24(1), 43–64 (2012)
Thorsten, J.: Training linear SVMs in linear time. In: SIGKDD (2006)
Tsaptsinos, A.: Lyrics-based music genre classification using a hierarchical attention network. In: ISMIR (2017)
Wang, Q., Luo, T., Wang, D., Xing, C.: Chinese song iambics generation with neural attention-based model. In: IJCAI (2016)
Wu, D., Addanki, V.S.K., Saers, M.S., Beloucif, M.: Learning to freestyle: hip hop challenge-response induction via transduction rule segmentation. In: EMNLP (2013)
Yan, R., Jiang, H., Lapata, M., Lin, S.D., Lv, X., Li, X.: i, Poet: automatic Chinese poetry composition through a generative summarization framework under constrained optimization. In: IJCAI (2013)
Yu, C., Mohammed, J.Z.: KATE: K-competitive autoencoder for text. In: SIGKDD (2017)
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China under Grant No. U1636116, 11431006, 61772288, the Research Fund for International Young Scientists under Grant No. 61650110510 and 61750110530, and the Ministry of education of Humanities and Social Science project under grant 16YJC790123.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Liang, H. et al. (2018). HAVAE: Learning Prosodic-Enhanced Representations of Rap Lyrics. In: Geng, X., Kang, BH. (eds) PRICAI 2018: Trends in Artificial Intelligence. PRICAI 2018. Lecture Notes in Computer Science(), vol 11012. Springer, Cham. https://doi.org/10.1007/978-3-319-97304-3_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-97304-3_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-97303-6
Online ISBN: 978-3-319-97304-3
eBook Packages: Computer ScienceComputer Science (R0)