Attributes Relevance in Content-Based Music Recommendation System
Source abstract
Abstract
The possibility of recommendations of musical songs is becoming increasingly required because of the millions of users and songs included in online databases. Therefore, effective methods that automatically solve this issue need to be created. In this paper, the mentioned task is solved using three basic factors based on genre classification made by neural network, Mel-frequency cepstral coefficients (MFCCs), and the tempo of the song. The recommendation system is built using a probability function based on these three factors. The authors’ contribution to the development of an automatic content-based recommendation system are methods built with the use of the mentioned three factors. Using different combinations of them, four strategies were created. All four strategies were evaluated based on the feedback score of 37 users, who created a total of 300 surveys. The proposed recommendation methods show a definite improvement in comparison with a random method. The obtained results indicate that the MFCC parameters have the greatest impact on the quality of recommendations.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Music and Audio Processing · Music Technology and Sound Studies · Speech and Audio Processing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Applied Informatics, Silesian University of Technology, 44-100 Gliwice, Poland
Funding
Statutory Research Fund of Department of Applied Informatics, Silesian University of Technology, Gliwice, Poland
References (49)
Show source-provided references
1. Ko, H., Lee, S., Park, Y., and Choi, A. (2022). A survey of recommendation systems: Recommendation models, techniques, and application fields. Electronics, 11.10.3390/electronics11010141 ↗
2. Recommendation systems: Principles, methods and evaluation10.1016/j.eij.2015.06.005 ↗
3. Naumov, M., Mudigere, D., Shi, H.J.M., Huang, J., Sundaraman, N., Park, J., Wang, X., Gupta, U., Wu, C.J., and Azzolini, A.G. (2019). Deep learning recommendation model for personalization and recommendation systems. arXiv.
4. Ebesu, T., Shen, B., and Fang, Y. (2018, January 8–12). Collaborative memory network for recommendation systems. Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, Ann Arbor, MI, USA.10.1145/3209978.3209991 ↗
5. Singhal, A., Sinha, P., and Pant, R. (2017). Use of deep learning in modern recommendation system: A summary of recent works. arXiv.10.5120/ijca2017916055 ↗
6. Rumiantcev, M., and Khriyenko, O. (2020, January 7–9). Emotion based music recommendation system. Proceedings of the Conference of Open Innovations Association FRUCT, Trento, Italy.
7. Chavare, S.R., Awati, C.J., and Shirgave, S.K. (2021, January 20–22). Smart recommender system using deep learning. Proceedings of the 2021 IEEE 6th international conference on inventive computation technologies (ICICT), Coimbatore, India.10.1109/ICICT50816.2021.9358580 ↗
8. Fessahaye, F., Perez, L., Zhan, T., Zhang, R., Fossier, C., Markarian, R., Chiu, C., Zhan, J., Gewali, L., and Oh, P. (2019, January 11–13). T-recsys: A novel music recommendation system using deep learning. Proceedings of the 2019 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA.10.1109/ICCE.2019.8662028 ↗
9. Mood based music recommendation system
10. Heterogeneous information network-based music recommendation system in mobile networks10.1016/j.comcom.2019.12.002 ↗
11. Representing musical genre: A state of the art10.1076/jnmr.32.1.83.16801 ↗
12. Heakl, A., Abdelgawad, A., and Parque, V. (2022, January 18–23). A Study on Broadcast Networks for Music Genre Classification. Proceedings of the 2022 IEEE International Joint Conference on Neural Networks (IJCNN), Padua, Italy.10.1109/IJCNN55064.2022.9892651 ↗
13. Xu, Z., Feng, Y., Song, S., Xu, Y., Wang, R., Zhang, L., and Liu, J. (2022, January 17–18). Research on Music Genre Classification Based on Residual Network. Proceedings of the International Conference on Mobile Computing, Applications, and Services, Messina, Italy.10.1007/978-3-031-23902-1_16 ↗
14. Oramas, S., Nieto, O., Sordo, M., and Serra, X. (2017, January 27). A deep multimodal approach for cold-start music recommendation. Proceedings of the 2nd Workshop on Deep Learning for Recommender Systems, Como, Italy.10.1145/3125486.3125492 ↗
15. Madathil, M. (2017). Music Recommendation System Spotify-Collaborative Filtering, Aachen University. Reports in Computer Music.
16. Niyazov, A., Mikhailova, E., and Egorova, O. (2011, January 13–15). Content-based music recommendation system. Proceedings of the 2021 IEEE 29th Conference of Open Innovations Association (FRUCT), Madrid, Spain.10.23919/FRUCT52173.2021.9435533 ↗
17. Web-Scale Multimedia Analysis: Does Content Matter?10.1109/MMUL.2011.34 ↗
18. An overview of distance and similarity functions for structured data10.1007/s10462-020-09821-w ↗
19. Deep content-based music recommendation
20. Learning Content Similarity for Music Recommendation10.1109/TASL.2012.2199109 ↗
21. (2023, November 20). About Spotify. Available online: https://newsroom.spotify.com/company-info/.
22. (2023, November 20). The Magic That Makes Spotify’s Discover Weekly Playlists so Damn Good. Available online: https://qz.com/571007/the-magic-that-makes-spotifys-discover-weekly-playlists-so-damn-good.
23. Germain, A., and Chakareski, J. (October, January 30). Spotify Me: Facebook-assisted automatic playlist generation. Proceedings of the 2013 IEEE 15th International Workshop on Multimedia Signal Processing (MMSP), Pula, Italy.10.1109/MMSP.2013.6659258 ↗
24. Unifying low-level and high-level music similarity measures10.1109/TMM.2011.2125784 ↗
25. Mak, C.M., Lee, T., Senapati, S., Yeung, Y.T., and Lam, W.K. (2010, January 9–13). Similarity Measures for Chinese Pop Music Based on Low-level Audio Signal Attributes. Proceedings of the International Society for Music Information Retrieval Conference (ISMIR 2010), Utrecht, The Netherlands.
26. Klapuri, A., and Leider, C. (2011, January 24–28). How much metadata do we need in music recommendation? A subjective evaluation using preference sets. Proceedings of the 12th International Society for Music Information Retrieval Conference (ISMIR 2011), Miami, FL, USA.
27. Cano, P., Koppenberger, M., and Wack, N. (2005, January 15–19). An industrial-strength content-based music recommendation system. Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Salvador, Brazil.10.1145/1076034.1076185 ↗
28. Hoffmann, P., Kaczmarek, A., Spaleniak, P., and Kostek, B. (2014). Music recommendation system. J. Telecommun. Inf. Technol., 59–69.
29. Liang, D., Zhan, M., and Ellis, D.P. (2015, January 26–30). Content-Aware Collaborative Music Recommendation Using Pre-trained Neural Networks. Proceedings of the International Society for Music Information Retrieval Conference, Malaga, Spain.
30. Wang, X., and Wang, Y. (2014, January 3–7). Improving content-based and hybrid music recommendation using deep learning. Proceedings of the 22nd ACM International Conference on Multimedia, Orlando, FL, USA.10.1145/2647868.2654940 ↗
31. Magno, T., and Sable, C. (2008, January 14–18). A Comparison of Signal Based Music Recommendation to Genre Labels, Collaborative Filtering, Musicological Analysis, Human Recommendation and Random Baseline. Proceedings of the International Society for Music Information Retrieval Conference, Philadelphia, PA, USA.
32. Deep learning in music recommendation systems10.3389/fams.2019.00044 ↗
33. Sachdeva, N., Gupta, K., and Pudi, V. (2018, January 2). Attentive neural architecture incorporating song features for music recommendation. Proceedings of the 12th ACM Conference on Recommender Systems, Vancouver, BC, Canada.10.1145/3240323.3240397 ↗
34. Heterogeneous knowledge-based attentive neural networks for short-term music recommendations10.1109/ACCESS.2018.2874959 ↗
35. Feature-combination hybrid recommender systems for automated music playlist continuation10.1007/s11257-018-9215-8 ↗
36. Abdul, A., Chen, J., Liao, H.Y., and Chang, S.H. (2018). An emotion-aware personalized music recommendation system using a convolutional neural networks approach. Appl. Sci., 8.10.3390/app8071103 ↗
37. Music recommendation system and recommendation model based on convolutional neural network
38. Music recommendation system based on fusion deep learning models10.1088/1742-6596/1544/1/012029 ↗
39. Music genre classification and music recommendation by using deep learning10.1049/el.2019.4202 ↗
40. Vall, A., Quadrana, M., Schedl, M., and Widmer, G. (2018). The importance of song context and song order in automated music playlist generation. arXiv.
41. Pulis, M., and Bajada, J. (October, January 27). Siamese Neural Networks for Content-based Cold-Start Music Recommendation. Proceedings of the 15th ACM Conference on Recommender Systems, Amsterdam, The Netherlands.
42. Computer Experimentation on Echo Detection, Using the Cepstrum and Pseudoautocovariance10.1121/1.1942899 ↗
43. Stern, R.M., and Acero, A. (1989). Acoustical Pre-Processing for Robust Speech Recognition, Carnegie-Mellon University Pittsburgh, PA, School of Computer Science. Technical Report.10.3115/1075434.1075488 ↗
44. Musical genre classification of audio signals10.1109/TSA.2002.800560 ↗
45. Sigurdsson, S., Petersen, K.B., and Lehn-Schiøler, T. (2006, January 8–12). Mel Frequency Cepstral Coefficients: An Evaluation of Robustness of MP3 Encoded Music. Proceedings of the International Conference on Music Information Retrieval, Victoria, BC, Canada.
46. Kostrzewa, D., Ciszynski, M., and Brzeski, R. (2022, January 9–13). Evolvable hybrid ensembles for musical genre classification. Proceedings of the Genetic and Evolutionary Computation Conference Companion, Boston, MA, USA.10.1145/3520304.3528792 ↗
47. Kostrzewa, D., Mazur, W., and Brzeski, R. (2022, January 21–23). Wide Ensembles of Neural Networks in Music Genre Classification. Proceedings of the Computational Science–ICCS 2022: 22nd International Conference, London, UK. Proceedings, Part II.10.1007/978-3-031-08754-7_9 ↗
48. (2023, November 20). Librosa Library. Available online: https://librosa.org.
49. An integrated music recommendation system10.1109/TCE.2006.1706489 ↗