TABLE II
ONE EXAMPLE OF AUDIO-BASED RECOMMENDATION. THE TABLE SHOWS
ONE TRACK/TRACK TRANSITION FROM THE TEST SUBSET, AND THE
TRACKS RECOMMENDED BY AGRU4REC SORTED BY RELEVANCE.
Track Artist
Previous Track Blunderbuss Jack White
Next Track Speak to Me/Breathe Pink Floyd
Rec. Tracks
Atom Heart Mother Pink Floyd
Cirrus Minor Pink Floyd
Astronomy Domine Pink Floyd
Comfortably Numb Pink Floyd
If Pink Floyd
Speak to Me/Breathe Pink Floyd
Shine on You Crazy Diamond Pink Floyd
One of These Days Pink Floyd
Let There Be More Light Pink Floyd
Wish You Were Here Pink Floyd
One potential application for audio-based models is the
generation of playlists given a local collection of tracks stored
on a user’s device. In this specific case, AGRU4REC could be
applied for generating recommendations based on the stored
audio files, even without having access to metadata associated
with these tracks. This can be particularly interesting in a sit-
uation where users are trying to expand their music collection
with tracks that are related to the ones they already have.
VII. ACKNOWLEDGEMENTS
During the development of this project, the first
author received financial support from CAPES Grant
88881.189985/2018-01 and the second author received finan-
cial support from CNPq Grant 310141/2022-2.
REFERENCES
[1] Brian McFee and Gert R. G. Lanckriet, “The natural language of
playlists,” in Proceedings of the 12th International Society for Music
Information Retrieval Conference, ISMIR 2011, Miami, Florida, USA,
October 24-28, 2011, 2011, pp. 537–542.
[2] Bruno L. Pereira, Alberto Ueda, Gustavo Penha, Rodrygo L. T. Santos,
and Nivio Ziviani, “Online learning to rank for sequential music
recommendation,” in Proceedings of the 13th ACM Conference on
Recommender Systems, 2019, RecSys ’19, p. 237–245.
[3] Mehdi Hosseinzadeh Aghdam, Negar Hariri, Bamshad Mobasher, and
Robin Burke, “Adapting recommendations to contextual changes using
hierarchical hidden markov models,” in Proceedings of the 9th ACM
Conference on Recommender Systems, 2015, RecSys ’15, p. 241–244.
[4] Malte Ludewig and Dietmar Jannach, “Evaluation of session-based
recommendation algorithms,” User Modeling and User-Adapted Inter-
action, vol. 28, no. 4-5, pp. 331–390, 2018.
[5] Massimo Quadrana, Paolo Cremonesi, and Dietmar Jannach, “Sequence-
aware recommender systems,” ACM Comput. Surv., vol. 51, no. 4, 2018.
[6] Chengfeng Xu, Pengpeng Zhao, Yanchi Liu, Jiajie Xu, Victor S.Sheng
S.Sheng, Zhiming Cui, Xiaofang Zhou, and Hui Xiong, “Recurrent
convolutional neural network for sequential recommendation,” in The
World Wide Web Conference, 2019, WWW ’19, p. 3398–3404.
[7] Arthur Flexer, Martin Gasser, and Dominik Schnitzer, “Limitations of
interactive music recommendation based on audio content,” in AM ’10,
The 5th Audio Mostly Conference, Pite
˚
a, Sweden, September 15-17,
2010. 2010, p. 13, ACM.
[8] Peter Forbes and Mu Zhu, “Content-boosted matrix factorization for
recommender systems: Experiments with recipe recommendation,” in
Proceedings of the Fifth ACM Conference on Recommender Systems,
2011, RecSys ’11, p. 261–264.
[9] A
¨
aron van den Oord, Sander Dieleman, and Benjamin Schrauwen,
“Deep content-based music recommendation,” in Proceedings of the
26th International Conference on Neural Information Processing Sys-
tems - Volume 2, 2013, NIPS’13, p. 2643–2651.
[10] Bal
´
azs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos
Tikk, “Session-based recommendations with recurrent neural networks,”
in 4th International Conference on Learning Representations, ICLR,
2016.
[11] Pedro Cano, Markus Koppenberger, and Nicolas Wack, “Content-based
music audio recommendation,” in Proceedings of the 13th Annual ACM
International Conference on Multimedia, 2005, MULTIMEDIA ’05, p.
211–212.
[12] Malcolm Slaney, Kilian Q. Weinberger, and William White, “Learning
a metric for music similarity,” in ISMIR 2008, 9th International Confer-
ence on Music Information Retrieval, Drexel University, Philadelphia,
PA, USA, September 14-18, 2008, 2008, pp. 313–318.
[13] B. Logan and A. Salomon, “A music similarity function based on signal
analysis,” in IEEE International Conference on Multimedia and Expo,
2001. ICME 2001., 2001, pp. 745–748.
[14] Dmitry Bogdanov, Joan Serr
`
a, Nicolas Wack, Perfecto Herrera, and
Xavier Serra, “Unifying low-level and high-level music similarity
measures,” IEEE Transactions on Multimedia, vol. 13, no. 4, pp. 687–
701, 2011.
[15] Matthew D. Hoffman, David M. Blei, and Perry R. Cook, “Content-
based musical similarity computation using the hierarchical dirichlet
process,” in ISMIR 2008, 9th International Conference on Music Infor-
mation Retrieval, Drexel University, Philadelphia, PA, USA, September
14-18, 2008, 2008, pp. 349–354.
[16] Qing Li, Byeong Man Kim, Dong Hai Guan, and Duk whan Oh, “A
music recommender based on audio features,” in Proceedings of the
27th Annual International ACM SIGIR Conference on Research and
Development in Information Retrieval, 2004, SIGIR ’04, p. 532–533.
[17] B. Shao, D. Wang, T. Li, and M. Ogihara, “Music recommendation
based on acoustic features and user access patterns,” IEEE Transactions
on Audio, Speech, and Language Processing, vol. 17, no. 8, pp. 1602–
1611, 2009.
[18] B. McFee, L. Barrington, and G. Lanckriet, “Learning content similarity
for music recommendation,” IEEE Transactions on Audio, Speech, and
Language Processing, vol. 20, no. 8, pp. 2207–2218, 2012.
[19] Zhe Xing, Xinxi Wang, and Ye Wang, “Enhancing collaborative filtering
music recommendation by balancing exploration and exploitation,” in
Proceedings of the 15th International Society for Music Information
Retrieval Conference, ISMIR 2014, Taipei, Taiwan, October 27-31, 2014,
2014, pp. 445–450.
[20] Xinxi Wang, Yi Wang, David Hsu, and Ye Wang, “Exploration
in interactive personalized music recommendation: A reinforcement
learning approach,” ACM Trans. Multimedia Comput. Commun. Appl.,
vol. 11, no. 1, 2014.
[21] Emilie Kaufmann, Olivier Cappe, and Aurelien Garivier, “On bayesian
upper confidence bounds for bandit problems,” in Proceedings of
the Fifteenth International Conference on Artificial Intelligence and
Statistics, 2012, vol. 22 of Proceedings of Machine Learning Research,
pp. 592–600.
[22] Szu-Yu Chou, Yi-Hsuan Yang, Jyh-Shing Roger Jang, and Yu-Ching Lin,
“Addressing cold start for next-song recommendation,” in Proceedings
of the 10th ACM Conference on Recommender Systems, 2016, RecSys
’16, p. 115–118.
[23] Steffen Rendle, Christoph Freudenthaler, and Lars Schmidt-Thieme,
“Factorizing personalized markov chains for next-basket recommenda-
tion,” in Proceedings of the 19th International Conference on World
Wide Web, 2010, WWW ’10, pp. 811–820.
[24] Markus Schedl, “The lfm-1b dataset for music retrieval and recommen-
dation,” in Proceedings of the 2016 ACM on International Conference
on Multimedia Retrieval, 2016, ICMR ’16, pp. 103–110.
[25] Jongpil Lee, Jiyoung Park, Keunhyoung Luke Kim, and Juhan Nam,
“Sample-level deep convolutional neural networks for music auto-
tagging using raw waveforms,” CoRR, vol. abs/1703.01789, 2017.
[26] Sander Dieleman and Benjamin Schrauwen, “End-to-end learning for
music audio,” in 2014 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP), 2014, pp. 6964–6968.
[27] Arthur Tofani, Rodrigo Borges, and Marcelo Queiroz, “Dynamic
session-based music recommendation using information retrieval tech-
niques,” User Model. User Adapt. Interact., vol. 32, no. 4, pp. 575–609,
2022.
425