Predicting Hit Music using MIDI features and Machine Learning

Rajyashree, R; Anand, Anmol; Soni, Yash; Mahajan, Harshitaa

doi:10.1109/cesys.2018.8724001

Cited by 4 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some works in this field rely on Machine Learning models for this task. Thus, the work in [21] analyzes songs' audio features (such as rhythm and instrumentation) and metadata to discover past successful music trends and then replicate them for future songs. The authors in [22] add to the study of audio features a sentiment analysis on song lyrics for a more accurate prediction.…”

Section: Related Workmentioning

confidence: 99%

PRESTO: A Recommender of Musical Collaborations based on Heterogeneous Graph Neural Networks

Terroso-Sáenz

Soto

Muñoz

et al. 2023

Preprint

View full text Add to dashboard Cite

The music industry is now more complex and competitive than ever before. In recent years, the search for collaborations with other artists has become a common strategy of musicians to maintain their presence in the sector. Besides, existing music streaming services such as Spotify have exposed large data feeds that can be used to develop innovative services within the realm of music. In this context, the present work introduces PRESTO, a novel recommendation system to suggest musicians new collaborations with other artists by means of an ensemble of Graph Neural Networks. The system is fed with an heterogeneous graph representing the time evolution and the stationary aspects of a musician's career. Finally, the proposal has been evaluated with a dataset comprising more than 200,000 artists, with an average F1 score above 0.75.

show abstract

Section: Related Workmentioning

confidence: 99%

PRESTO: A Recommender of Musical Collaborations based on Heterogeneous Graph Neural Networks

Terroso-Sáenz

Soto

Muñoz

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Rajyashree et al 24 proposed a methodology based on the jSymbolic library † , which extracts features from the MIDI data. Then a machine learning technique like the random forest, logistic regression and so forth is used for recommendation generation.…”

Section: Midi In Music Information Retrievalmentioning

confidence: 99%

“…Then a machine learning technique like the random forest, logistic regression and so forth is used for recommendation generation. 24 Some deep learning models have also been proposed for content-based recommendation and music track generation. Ranjan et al 25 use the Bi-LSTM model to generate similar music using melodic information extracted from MIDI data.…”

Section: Midi In Music Information Retrievalmentioning

confidence: 99%

Improved self‐attentive Musical Instrument Digital Interface content‐based music recommendation system

Yadav

Singh

Pal

2022

Computational Intelligence

View full text Add to dashboard Cite

Automatic music recommendation is an open research problem that has seen much work in recent years.A common and successful music recommendation approach is collaborative filtering, which has worked well in this domain. One major drawback of this method is that it suffers from a cold-start problem, and it requires a lot of user-personalized information. It is an ineffective mechanism for recommending new and unpopular songs as well as for new users. In this article, we report a hybrid methodology that uses the song's content information. We use MIDI (Musical Instrument Digital Interface) content data, a compressed version of an audio song that contains digital information about a song and is machine-readable. We describe a model called MSA-SRec (MIDI Based Self Attentive Sequential Music Recommendation), a latent factor-based self-attentive deep learning model that uses a substantial amount of sequential information as content information of the song for recommendation generation. We use MIDI data of a song that is under-explored content information for music recommendation. We show that using MIDI as content data with user and item latent vector produces reasonable recommendations. We also demonstrate that using MIDI over other music metadata performs better

show abstract