{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T04:21:36Z","timestamp":1784521296375,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,8,27]],"date-time":"2017-08-27T00:00:00Z","timestamp":1503792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,8,27]]},"DOI":"10.1145\/3125486.3125492","type":"proceedings-article","created":{"date-parts":[[2017,8,24]],"date-time":"2017-08-24T11:58:11Z","timestamp":1503575891000},"page":"32-37","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":77,"title":["A Deep Multimodal Approach for Cold-start Music Recommendation"],"prefix":"10.1145","author":[{"given":"Sergio","family":"Oramas","sequence":"first","affiliation":[{"name":"Music Technology Group, Universitat Pompeu Fabra"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oriol","family":"Nieto","sequence":"additional","affiliation":[{"name":"Pandora Media, Inc., Oakland, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Sordo","sequence":"additional","affiliation":[{"name":"Pandora Media, Inc., Oakland, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xavier","family":"Serra","sequence":"additional","affiliation":[{"name":"Music Technology Group, Universitat Pompeu Fabra"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,8,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959180"},{"key":"e_1_3_2_1_2_1","volume-title":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","author":"Bechet M. Rouvier","year":"2015","unstructured":"M. Rouvier Bechet , S. Delecraz , B. Favre , M. Bendris , and F. 2015 . Multimodal embedding fusion for robust speaker role recognition in video broadcast . IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) (2015). M. Rouvier Bechet, S. Delecraz, B. Favre, M. Bendris, and F. 2015. Multimodal embedding fusion for robust speaker role recognition in video broadcast. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) (2015)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944966"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 12th International Conference on Music Information Retrieval (ISMIR","author":"Bertin-Mahieux Thierry","year":"2011","unstructured":"Thierry Bertin-Mahieux , Daniel P.W. Ellis , Brian Whitman , and Paul Lamere . 2011 . The Million Song Dataset . In Proceedings of the 12th International Conference on Music Information Retrieval (ISMIR 2011). Thierry Bertin-Mahieux, Daniel P.W. Ellis, Brian Whitman, and Paul Lamere. 2011. The Million Song Dataset. In Proceedings of the 12th International Conference on Music Information Retrieval (ISMIR 2011)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1021240730564"},{"key":"e_1_3_2_1_6_1","volume-title":"The Long Tail in Recommender Systems","author":"Celma \u00d2scar","unstructured":"\u00d2scar Celma . 2010. The Long Tail in Recommender Systems . Springer Berlin Heidelberg , Berlin, Heidelberg , 87--107. \u00d2scar Celma. 2010. The Long Tail in Recommender Systems. Springer Berlin Heidelberg, Berlin, Heidelberg, 87--107."},{"key":"e_1_3_2_1_7_1","volume-title":"Information-theoretical label embeddings for large-scale image classification. CoRR","author":"Chollet Fran\u00e7ois","year":"2016","unstructured":"Fran\u00e7ois Chollet . 2016. Information-theoretical label embeddings for large-scale image classification. CoRR ( 2016 ), 1--10. arXiv:1607.05691 http:\/\/arxiv.org\/abs\/1607.05691 Fran\u00e7ois Chollet. 2016. Information-theoretical label embeddings for large-scale image classification. CoRR (2016), 1--10. arXiv:1607.05691 http:\/\/arxiv.org\/abs\/1607.05691"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078186"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 8th International Society for Music Information Retrieval Conference.","author":"Flexer Arthur","year":"2007","unstructured":"Arthur Flexer . 2007 . A Closer Look on Artist Filters for Musical Genre Classification . In Proceedings of the 8th International Society for Music Information Retrieval Conference. Arthur Flexer. 2007. A Closer Look on Artist Filters for Musical Genre Classification. In Proceedings of the 8th International Society for Music Information Retrieval Conference."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.129"},{"key":"e_1_3_2_1_11_1","first-page":"1","article-title":"Knowledge matters: Importance of prior information for optimization","volume":"17","author":"G\u00fcl\u00e7ehre \u00c7a\u011flar","year":"2016","unstructured":"\u00c7a\u011flar G\u00fcl\u00e7ehre and Yoshua Bengio . 2016 . Knowledge matters: Importance of prior information for optimization . Journal of Machine Learning Research 17 , 8 (2016), 1 -- 32 . \u00c7a\u011flar G\u00fcl\u00e7ehre and Yoshua Bengio. 2016. Knowledge matters: Importance of prior information for optimization. Journal of Machine Learning Research 17, 8 (2016), 1--32.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.22"},{"key":"e_1_3_2_1_13_1","volume-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. CoRR abs\/1502.03167","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy . 2015 . Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. CoRR abs\/1502.03167 (2015). http:\/\/arxiv.org\/abs\/1502.03167 Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. CoRR abs\/1502.03167 (2015). http:\/\/arxiv.org\/abs\/1502.03167"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"e_1_3_2_1_15_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba . 2014 . Adam : A Method for Stochastic Optimization. CoRR abs\/1412.6980 (2014). http:\/\/arxiv.org\/abs\/1412.6980 Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. CoRR abs\/1412.6980 (2014). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2542205.2542206"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_18_1","first-page":"1","article-title":"Exploring strategies for training deep neural networks","author":"Larochelle Hugo","year":"2009","unstructured":"Hugo Larochelle , Yoshua Bengio , J\u00e9r\u00f4me Louradour , and Pascal Lamblin . 2009 . Exploring strategies for training deep neural networks . Journal of Machine Learning Research 10 , Jan (2009), 1 -- 40 . Hugo Larochelle, Yoshua Bengio, J\u00e9r\u00f4me Louradour, and Pascal Lamblin. 2009. Exploring strategies for training deep neural networks. Journal of Machine Learning Research 10, Jan (2009), 1--40.","journal-title":"Journal of Machine Learning Research 10"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2187980.2188222"},{"key":"e_1_3_2_1_20_1","volume-title":"Matt Mcvicar, Eric Battenberg, and Oriol Nieto.","author":"Mcfee Brian","year":"2015","unstructured":"Brian Mcfee , Colin Raffel , Dawen Liang , Daniel P W Ellis , Matt Mcvicar, Eric Battenberg, and Oriol Nieto. 2015 . librosa: Audio and Music Signal Analysis in Python. PROC. OF THE 14th PYTHON IN SCIENCE CONF Scipy ( 2015), 1--7. Brian Mcfee, Colin Raffel, Dawen Liang, Daniel P W Ellis, Matt Mcvicar, Eric Battenberg, and Oriol Nieto. 2015. librosa: Audio and Music Signal Analysis in Python. PROC. OF THE 14th PYTHON IN SCIENCE CONF Scipy (2015), 1--7."},{"key":"e_1_3_2_1_21_1","volume-title":"Distributed Representations of Words and Phrases and their Compositionality. Nips","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov , Kai Chen , Greg Corrado , and Jeffrey Dean . 2013. Distributed Representations of Words and Phrases and their Compositionality. Nips ( 2013 ), 1--9. arXiv:1310.4546 Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. Nips (2013), 1--9. arXiv:1310.4546"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the SIGIR-99 Workshop on Recommender Systems: Algorithms and Evaluation","author":"Mooney Raymond J","year":"1999","unstructured":"Raymond J Mooney and Loriene Roy . 1999 . Content-Based Book Recommending . Proceedings of the SIGIR-99 Workshop on Recommender Systems: Algorithms and Evaluation August (1999). Raymond J Mooney and Loriene Roy. 1999. Content-Based Book Recommending. Proceedings of the SIGIR-99 Workshop on Recommender Systems: Algorithms and Evaluation August (1999)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00179"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2012.07.001"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 28th international conference on machine learning (ICML-11)","author":"Ngiam Jiquan","year":"2011","unstructured":"Jiquan Ngiam , Aditya Khosla , Mingyu Kim , Juhan Nam , Honglak Lee , and Andrew Y Ng . 2011 . Multimodal deep learning . In Proceedings of the 28th international conference on machine learning (ICML-11) . 689--696. Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, and Andrew Y Ng. 2011. Multimodal deep learning. In Proceedings of the 28th international conference on machine learning (ICML-11). 689--696."},{"key":"e_1_3_2_1_26_1","volume-title":"Sabine Schulte im Walde, and Ngoc Thang Vu","author":"Nguyen Kim Anh","year":"2016","unstructured":"Kim Anh Nguyen , Sabine Schulte im Walde, and Ngoc Thang Vu . 2016 . Neural-based Noise Filtering from Word Embeddings. Coling- 2016 (2016), 2699--2707. arXiv:1610.01874 http:\/\/arxiv.org\/abs\/1610.01874 Kim Anh Nguyen, Sabine Schulte im Walde, and Ngoc Thang Vu. 2016. Neural-based Noise Filtering from Word Embeddings. Coling-2016 (2016), 2699--2707. arXiv:1610.01874 http:\/\/arxiv.org\/abs\/1610.01874"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2016.06.001"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2926718"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of 16th the International Society for Music Information Retrieval Conference","author":"Oramas Sergio","year":"2015","unstructured":"Sergio Oramas , Mohamed Sordo , Luis Espinosa-Anke , and Xavier Serra . 2015 . A Semantic-based Approach for Artist Similarity . Proceedings of 16th the International Society for Music Information Retrieval Conference October (2015), 100--106. Sergio Oramas, Mohamed Sordo, Luis Espinosa-Anke, and Xavier Serra. 2015. A Semantic-based Approach for Artist Similarity. Proceedings of 16th the International Society for Music Information Retrieval Conference October (2015), 100--106."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2645710.2645751"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000042"},{"key":"e_1_3_2_1_32_1","volume-title":"7th Sound and Music Computing Conference JANUARY","author":"Sch\u00f6rkhuber Christian","year":"2010","unstructured":"Christian Sch\u00f6rkhuber and Anssi Klapuri . 2010 . Constant-Q transform toolbox for music processing . 7th Sound and Music Computing Conference JANUARY (2010), 3--64. Christian Sch\u00f6rkhuber and Anssi Klapuri. 2010. Constant-Q transform toolbox for music processing. 7th Sound and Music Computing Conference JANUARY (2010), 3--64."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079002"},{"key":"e_1_3_2_1_34_1","volume-title":"International conference on machine learning workshop.","author":"Srivastava Nitish","year":"2012","unstructured":"Nitish Srivastava and Ruslan Salakhutdinov . 2012 . Learning representations for multimodal data with deep belief nets . In International conference on machine learning workshop. Nitish Srivastava and Ruslan Salakhutdinov. 2012. Learning representations for multimodal data with deep belief nets. In International conference on machine learning workshop."},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of 9th the International Society for Music Information Retrieval Conference","author":"Turnbull Douglas","year":"2008","unstructured":"Douglas Turnbull , Luke Barrington , and Gert Lanckriet . 2008 . Five approaches to collecting tags for music . Proceedings of 9th the International Society for Music Information Retrieval Conference (2008), 225--230. http:\/\/books.google.com\/books?hl=en Douglas Turnbull, Luke Barrington, and Gert Lanckriet. 2008. Five approaches to collecting tags for music. Proceedings of 9th the International Society for Music Information Retrieval Conference (2008), 225--230. http:\/\/books.google.com\/books?hl=en"},{"key":"e_1_3_2_1_36_1","volume-title":"Deep content-based music recommendation. Electronics and Information Systems department (ELIS)","author":"van den Oord Aaron","year":"2013","unstructured":"Aaron van den Oord , Sander Dieleman , and Benjamin Schrauwen . 2013. Deep content-based music recommendation. Electronics and Information Systems department (ELIS) ( 2013 ), 9. Aaron van den Oord, Sander Dieleman, and Benjamin Schrauwen. 2013. Deep content-based music recommendation. Electronics and Information Systems department (ELIS) (2013), 9."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/281250.281256"}],"event":{"name":"DLRS 2017: Workshop on Deep Learning for Recommender Systems","location":"Como Italy","acronym":"DLRS 2017","sponsor":["IBMR IBM Research"]},"container-title":["Proceedings of the 2nd Workshop on Deep Learning for Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3125486.3125492","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3125486.3125492","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:11:23Z","timestamp":1750212683000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3125486.3125492"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8,27]]},"references-count":37,"alternative-id":["10.1145\/3125486.3125492","10.1145\/3125486"],"URL":"https:\/\/doi.org\/10.1145\/3125486.3125492","relation":{},"subject":[],"published":{"date-parts":[[2017,8,27]]},"assertion":[{"value":"2017-08-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}