Shafi Ahmed
ABSTRACT
Music is one of the most important factors of human lives. People express their inner thoughts, emotions and feelings with the combination of both lyrics and musical instruments. With the passage of time, languages have also evolved and the structure of the languages have also changed. By listening to music, we can understand which genre the song belongs to. So, we have come up with an idea of classifying genre based on the music lyrics. There are few works where the researchers worked on genre based lyrics classification. However, those works were based on different languages such as English, Hindi and Spanish. As a result, we have got an opportunity to work on Bangla language. In this paper, we have used different machine learning (ML) models and a custom CNN model to classify Bangla Lyrics on “Bangla Song Lyrics” dataset which is available on Kaggle. Our proposed CNN model achieved highest accuracy of 69.36% with an F1-score of 69.17% among all models.
- Felipe Almeida and Geraldo Xexéo. 2019. Word Embeddings: A Survey. arxiv:1901.09069 [cs.CL]Google Scholar
- Ravneet Arora, Chen-Tse Tsai, Ketevan Tsereteli, Prabhanjan Kambadur, and Yi Yang. 2019. A Semi-Markov Structured Support Vector Machine Model for High-Precision Named Entity Recognition. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 5862–5866. https://doi.org/10.18653/v1/P19-1587Google ScholarCross Ref
- Tianqi Chen and Carlos Guestrin. 2016. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (San Francisco, California, USA) (KDD ’16). ACM, New York, NY, USA, 785–794. https://doi.org/10.1145/2939672.2939785Google ScholarDigital Library
- Tu Chengsheng, Liu Huacheng, and Xu Bing. 2017. AdaBoost typical Algorithm and its application research. MATEC Web of Conferences 139 (01 2017), 00222. https://doi.org/10.1051/matecconf/201713900222Google ScholarCross Ref
- Shilpa Desai, Jyoti Pawar, and Pushpak Bhattacharyya. 2015. Logistic Regression for Automatic Lexical Level Morphological Paradigm Selection for Konkani Nouns. In Proceedings of the 12th International Conference on Natural Language Processing. NLP Association of India, Trivandrum, India, 203–208. https://aclanthology.org/W15-5931Google Scholar
- Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen Lin. 2008. LIBLINEAR: A Library for Large Linear Classification. J. Mach. Learn. Res. 9 (jun 2008), 1871–1874.Google Scholar
- A. Hassan, M. R. Amin, N. Mohammed, and A. K. A. Azad. 2016. Sentiment Analysis on Bangla and Romanized Bangla Text (BRBT) using Deep Recurrent models. arxiv:1610.00369 [cs.CL]Google Scholar
- Kawisorn Kamtue, Kasina Euchukanonchai, Dittaya Wanvarie, and Naruemon Pratanwanich. 2019. Lukthung Classification Using Neural Networks on Lyrics and Audios. 269–274. https://doi.org/10.1109/ICSEC47112.2019.8974740Google Scholar
- Shakirul Hasan Khan. 2020. Bangla Song Lyrics. https://www.kaggle.com/shakirulhasan/bangla-song-lyricsGoogle Scholar
- Raul Lima. 2020. Brazilian Lyrics-Based Music Genre Classification Using a BLSTM Network. https://doi.org/10.1007/978-3-030-61401-0_49Google ScholarDigital Library
- F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12 (2011), 2825–2830.Google ScholarDigital Library
- Payam Refaeilzadeh, Lei Tang, and Huan Liu. 2009. Cross-Validation. Springer US, Boston, MA, 532–538. https://doi.org/10.1007/978-0-387-39940-9_565Google ScholarCross Ref
- Jürgen Schmidhuber. 2015. Deep learning in neural networks: An overview. Neural Networks 61 (Jan 2015), 85–117. https://doi.org/10.1016/j.neunet.2014.09.003Google ScholarDigital Library
- Alexandros Tsaptsinos. 2017. Lyrics-Based Music Genre Classification Using a Hierarchical Attention Network. arxiv:1707.04678 [cs.IR]Google Scholar
- Makarand Velankar, Rachita Kotian, and Parag Kulkarni. 2021. Contextual Mood Analysis with Knowledge Graph Representation for Hindi Song Lyrics in Devanagari Script. arxiv:2108.06947 [cs.CL]Google Scholar
- Zhongheng Zhang. 2016. Introduction to machine learning: k-nearest neighbors. Annals of translational medicine 4, 11 (Jun 2016), 218–218. https://pubmed.ncbi.nlm.nih.gov/27386492 27386492[pmid].Google ScholarCross Ref
Index Terms
- Bangla Music Lyrics Classification
Recommendations
Music/lyrics composition system considering user's image and music genre
SMC'09: Proceedings of the 2009 IEEE international conference on Systems, Man and CyberneticsThis paper proposes a music/lyrics composition system consisting of two sections, a lyric composing section and a music composing section, which considers user's image of a song and music genre. First of all, a user has an image of music/lyrics to ...
Music classification method based on lyrics for music therapy
IDEAS '14: Proceedings of the 18th International Database Engineering & Applications SymposiumMusic is used for people practicing sports, for elderly individuals, and to help train the mind. Recently in music information science, studies have been conducted on music therapy and on music classification from a therapeutic point of view. However, ...
Multimodal Music Mood Classification Using Audio and Lyrics
ICMLA '08: Proceedings of the 2008 Seventh International Conference on Machine Learning and ApplicationsIn this paper we present a study on music mood classification using audio and lyrics information. The mood of a song is expressed by means of musical features but a relevant part also seems to be conveyed by the lyrics. We evaluate each factor ...
Comments