{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T05:36:29Z","timestamp":1751607389584,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,1,30]],"date-time":"2019-01-30T00:00:00Z","timestamp":1548806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Oath","award":["The Connected Experiences Lab"],"award-info":[{"award-number":["The Connected Experiences Lab"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1700832"],"award-info":[{"award-number":["1700832"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,1,30]]},"DOI":"10.1145\/3289600.3290993","type":"proceedings-article","created":{"date-parts":[[2019,3,11]],"date-time":"2019-03-11T12:33:01Z","timestamp":1552307581000},"page":"276-284","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["More Than Just Words"],"prefix":"10.1145","author":[{"given":"Longqi","family":"Yang","sequence":"first","affiliation":[{"name":"Cornell Tech, Cornell University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Himalaya Inc., San Francisco, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Drew","family":"Dunne","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Sobolev","sequence":"additional","affiliation":[{"name":"Cornell Tech, Cornell University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mor","family":"Naaman","sequence":"additional","affiliation":[{"name":"Cornell Tech, Cornell University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deborah","family":"Estrin","sequence":"additional","affiliation":[{"name":"Cornell Tech, Cornell University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,1,30]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1109\/ICASSP.2017.7952655"},{"key":"e_1_3_2_1_2_1","volume-title":"Brian Whitman, and Paul Lamere.","author":"Bertin-Mahieux Thierry","year":"2011","unstructured":"Thierry Bertin-Mahieux , Daniel PW Ellis , Brian Whitman, and Paul Lamere. 2011 . The Million Song Dataset.. In Ismir . Thierry Bertin-Mahieux, Daniel PW Ellis, Brian Whitman, and Paul Lamere. 2011. The Million Song Dataset.. In Ismir ."},{"key":"e_1_3_2_1_3_1","volume-title":"Podcast search: User goals and retrieval technologies. Online information review","author":"Besser Jana","year":"2010","unstructured":"Jana Besser , Martha Larson , and Katja Hofmann . 2010. Podcast search: User goals and retrieval technologies. Online information review ( 2010 ). Jana Besser, Martha Larson, and Katja Hofmann. 2010. Podcast search: User goals and retrieval technologies. Online information review (2010)."},{"unstructured":"Sebastian B\u00f6ck Florian Krebs and Gerhard Widmer. 2016. Joint Beat and Downbeat Tracking with Recurrent Neural Networks.. In ISMIR .  Sebastian B\u00f6ck Florian Krebs and Gerhard Widmer. 2016. Joint Beat and Downbeat Tracking with Recurrent Neural Networks.. In ISMIR .","key":"e_1_3_2_1_4_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1145\/2846092"},{"key":"e_1_3_2_1_6_1","volume-title":"A computational approach to politeness with application to social factors. arXiv preprint arXiv:1306.6078","author":"Danescu-Niculescu-Mizil Cristian","year":"2013","unstructured":"Cristian Danescu-Niculescu-Mizil , Moritz Sudhof , Dan Jurafsky , Jure Leskovec , and Christopher Potts . 2013. A computational approach to politeness with application to social factors. arXiv preprint arXiv:1306.6078 ( 2013 ). Cristian Danescu-Niculescu-Mizil, Moritz Sudhof, Dan Jurafsky, Jure Leskovec, and Christopher Potts. 2013. A computational approach to politeness with application to social factors. arXiv preprint arXiv:1306.6078 (2013)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1145\/1873951.1874246"},{"key":"e_1_3_2_1_8_1","volume-title":"M Rijke, et almbox.","author":"Fuller Marguerite","year":"2008","unstructured":"Marguerite Fuller , E Tsagkias , Eamonn Newman , Jana Besser , Martha Larson , Gareth JF Jones , M Rijke, et almbox. 2008 . Using term clouds to represent segment-level semantic content of podcasts. (2008). Marguerite Fuller, E Tsagkias, Eamonn Newman, Jana Besser, Martha Larson, Gareth JF Jones, M Rijke, et almbox. 2008. Using term clouds to represent segment-level semantic content of podcasts. (2008)."},{"key":"e_1_3_2_1_9_1","volume-title":"TIMIT acoustic-phonetic continuous speech corpus. Linguistic data consortium","author":"Garofolo John S","year":"1993","unstructured":"John S Garofolo , Lori F Lamel , William M Fisher , Jonathan G Fiscus , David S Pallett , Nancy L Dahlgren , and Victor Zue . 1993. TIMIT acoustic-phonetic continuous speech corpus. Linguistic data consortium ( 1993 ). John S Garofolo, Lori F Lamel, William M Fisher, Jonathan G Fiscus, David S Pallett, Nancy L Dahlgren, and Victor Zue. 1993. TIMIT acoustic-phonetic continuous speech corpus. Linguistic data consortium (1993)."},{"key":"e_1_3_2_1_10_1","volume-title":"Dylan Freedman, Aren Jansen, Wade Lawrence, R Channing Moore, Manoj Plakal, and Marvin Ritter.","author":"Gemmeke Jort F","year":"2017","unstructured":"Jort F Gemmeke , Daniel PW Ellis , Dylan Freedman, Aren Jansen, Wade Lawrence, R Channing Moore, Manoj Plakal, and Marvin Ritter. 2017 . Audio Set : An ontology and human-labeled dataset for audio events. In IEEE ICASSP . Jort F Gemmeke, Daniel PW Ellis, Dylan Freedman, Aren Jansen, Wade Lawrence, R Channing Moore, Manoj Plakal, and Marvin Ritter. 2017. Audio Set: An ontology and human-labeled dataset for audio events. In IEEE ICASSP ."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1007\/s00799-004-0101-0"},{"volume-title":"Deep Learning","author":"Goodfellow Ian","unstructured":"Ian Goodfellow , Yoshua Bengio , and Aaron Courville . 2016. Deep Learning . MIT Press . http:\/\/www.deeplearningbook.org. Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning .MIT Press. http:\/\/www.deeplearningbook.org.","key":"e_1_3_2_1_12_1"},{"unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems .   Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems .","key":"e_1_3_2_1_13_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.21437\/Interspeech.2011-769"},{"key":"e_1_3_2_1_15_1","volume-title":"et almbox","author":"Hannun Awni","year":"2014","unstructured":"Awni Hannun , Carl Case , Jared Casper , Bryan Catanzaro , Greg Diamos , Erich Elsen , Ryan Prenger , Sanjeev Satheesh , Shubho Sengupta , Adam Coates , et almbox . 2014 . Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014). Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta, Adam Coates, et almbox. 2014. Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1145\/2365952.2365979"},{"key":"e_1_3_2_1_17_1","volume-title":"Answering the call for a standard reliability measure for coding data. Communication methods and measures","author":"Hayes Andrew F","year":"2007","unstructured":"Andrew F Hayes and Klaus Krippendorff . 2007. Answering the call for a standard reliability measure for coding data. Communication methods and measures ( 2007 ). Andrew F Hayes and Klaus Krippendorff. 2007. Answering the call for a standard reliability measure for coding data. Communication methods and measures (2007)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1109\/CVPR.2016.90"},{"unstructured":"Eric J Humphrey and Juan Pablo Bello. 2015. Four Timely Insights on Automatic Chord Estimation.. In ISMIR .  Eric J Humphrey and Juan Pablo Bello. 2015. Four Timely Insights on Automatic Chord Estimation.. In ISMIR .","key":"e_1_3_2_1_19_1"},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Machine Learning .","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy . 2015 . Batch normalization: Accelerating deep network training by reducing internal covariate shift . In International Conference on Machine Learning . Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning ."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_21_1","DOI":"10.21437\/Interspeech.2017-196"},{"key":"e_1_3_2_1_22_1","volume-title":"Image-to-image translation with conditional adversarial networks. arXiv preprint arXiv:1611.07004","author":"Isola Phillip","year":"2016","unstructured":"Phillip Isola , Jun-Yan Zhu , Tinghui Zhou , and Alexei A Efros . 2016. Image-to-image translation with conditional adversarial networks. arXiv preprint arXiv:1611.07004 ( 2016 ). Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A Efros. 2016. Image-to-image translation with conditional adversarial networks. arXiv preprint arXiv:1611.07004 (2016)."},{"key":"e_1_3_2_1_23_1","volume-title":"Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759","author":"Joulin Armand","year":"2016","unstructured":"Armand Joulin , Edouard Grave , Piotr Bojanowski , and Tomas Mikolov . 2016. Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759 ( 2016 ). Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. 2016. Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759 (2016)."},{"key":"e_1_3_2_1_24_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik","year":"2014","unstructured":"Diederik Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"volume-title":"Content analysis: An introduction to its methodology","author":"Krippendorff Klaus","unstructured":"Klaus Krippendorff . 2012. Content analysis: An introduction to its methodology . Sage . Klaus Krippendorff. 2012. Content analysis: An introduction to its methodology .Sage.","key":"e_1_3_2_1_25_1"},{"key":"e_1_3_2_1_26_1","volume-title":"The measurement of observer agreement for categorical data. biometrics","author":"Richard Landis J","year":"1977","unstructured":"J Richard Landis and Gary G Koch . 1977. The measurement of observer agreement for categorical data. biometrics ( 1977 ). J Richard Landis and Gary G Koch. 1977. The measurement of observer agreement for categorical data. biometrics (1977)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_27_1","DOI":"10.1561\/1500000020"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.1145\/2328967.2328968"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_29_1","DOI":"10.21437\/Interspeech.2017-1326"},{"key":"e_1_3_2_1_30_1","volume-title":"mbox","author":"Beth Logan","year":"2000","unstructured":"Beth Logan et al mbox . 2000 . Mel Frequency Cepstral Coefficients for Music Modeling.. In ISMIR . Beth Logan et almbox. 2000. Mel Frequency Cepstral Coefficients for Music Modeling.. In ISMIR ."},{"key":"e_1_3_2_1_31_1","volume-title":"The proceedings of the seventh IEEE international conference on","volume":"2","author":"Lowe David G","year":"1999","unstructured":"David G Lowe . 1999 . Object recognition from local scale-invariant features. In Computer vision, 1999 . The proceedings of the seventh IEEE international conference on , Vol. 2 . Ieee, 1150--1157. David G Lowe. 1999. Object recognition from local scale-invariant features. In Computer vision, 1999. The proceedings of the seventh IEEE international conference on, Vol. 2. Ieee, 1150--1157."},{"key":"e_1_3_2_1_32_1","volume-title":"MALLET: A Machine Learning for Language Toolkit.","author":"McCallum Andrew Kachites","year":"2002","unstructured":"Andrew Kachites McCallum . 2002 . MALLET: A Machine Learning for Language Toolkit. (2002). http:\/\/mallet.cs.umass.edu. Andrew Kachites McCallum. 2002. MALLET: A Machine Learning for Language Toolkit. (2002). http:\/\/mallet.cs.umass.edu."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.1109\/SLT.2008.4777899"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_34_1","DOI":"10.5555\/3104322.3104425"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_35_1","DOI":"10.1109\/ICCV.2015.178"},{"key":"e_1_3_2_1_36_1","volume-title":"Unlocking the potential of the spoken word. Science","author":"Oard Douglas W","year":"2008","unstructured":"Douglas W Oard . 2008. Unlocking the potential of the spoken word. Science ( 2008 ). Douglas W Oard. 2008. Unlocking the potential of the spoken word. Science (2008)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_37_1","DOI":"10.21437\/Interspeech.2009-454"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_38_1","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_2_1_39_1","volume-title":"Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434","author":"Radford Alec","year":"2015","unstructured":"Alec Radford , Luke Metz , and Soumith Chintala . 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 ( 2015 ). Alec Radford, Luke Metz, and Soumith Chintala. 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)."},{"key":"e_1_3_2_1_40_1","volume-title":"The Podcast Consumer","author":"Research Edison","year":"2017","unstructured":"Edison Research . 2017a. The Podcast Consumer 2017 . (2017). http:\/\/www.edisonresearch.com\/the-podcast-consumer-2017\/ Edison Research. 2017a. The Podcast Consumer 2017. (2017). http:\/\/www.edisonresearch.com\/the-podcast-consumer-2017\/"},{"unstructured":"Google Research. 2017b. Launching the Speech Commands Dataset. (2017). https:\/\/research.googleblog.com\/2017\/08\/launching-speech-commands-dataset.html  Google Research. 2017b. Launching the Speech Commands Dataset. (2017). https:\/\/research.googleblog.com\/2017\/08\/launching-speech-commands-dataset.html","key":"e_1_3_2_1_41_1"},{"unstructured":"Anthony Rousseau Paul Del\u00e9glise and Yannick Est\u00e8ve. 2014. Enhancing the TED-LIUM Corpus with Selected Data for Language Modeling and More TED Talks.. In LREC .  Anthony Rousseau Paul Del\u00e9glise and Yannick Est\u00e8ve. 2014. Enhancing the TED-LIUM Corpus with Selected Data for Language Modeling and More TED Talks.. In LREC .","key":"e_1_3_2_1_42_1"},{"unstructured":"Tim Salimans Ian Goodfellow Wojciech Zaremba Vicki Cheung Alec Radford and Xi Chen. 2016. Improved techniques for training gans. In Advances in Neural Information Processing Systems .   Tim Salimans Ian Goodfellow Wojciech Zaremba Vicki Cheung Alec Radford and Xi Chen. 2016. Improved techniques for training gans. In Advances in Neural Information Processing Systems .","key":"e_1_3_2_1_43_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_44_1","DOI":"10.1007\/978-3-319-23461-8_16"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_45_1","DOI":"10.1145\/2578726.2582612"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_46_1","DOI":"10.1145\/3109859.3109934"},{"doi-asserted-by":"crossref","unstructured":"Tobias Schnabel Igor Labutov David M Mimno and Thorsten Joachims. 2015. Evaluation methods for unsupervised word embeddings.. In EMNLP .  Tobias Schnabel Igor Labutov David M Mimno and Thorsten Joachims. 2015. Evaluation methods for unsupervised word embeddings.. In EMNLP .","key":"e_1_3_2_1_47_1","DOI":"10.18653\/v1\/D15-1036"},{"key":"e_1_3_2_1_48_1","volume-title":"The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism.","author":"Bj\u00f6rn","year":"2013","unstructured":"Bj\u00f6rn Schuller et almbox. 2013 . The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism. ( 2013 ). Bj\u00f6rn Schuller et almbox. 2013. The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism. (2013)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_49_1","DOI":"10.21437\/Interspeech.2009-103"},{"unstructured":"Aaron Van den Oord Sander Dieleman and Benjamin Schrauwen. 2013. Deep content-based music recommendation. In Advances in neural information processing systems .   Aaron Van den Oord Sander Dieleman and Benjamin Schrauwen. 2013. Deep content-based music recommendation. In Advances in neural information processing systems .","key":"e_1_3_2_1_50_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_51_1","DOI":"10.1145\/3159652.3159681"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_52_1","DOI":"10.1145\/3240323.3240389"}],"event":{"sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"],"acronym":"WSDM '19","name":"WSDM '19: The Twelfth ACM International Conference on Web Search and Data Mining","location":"Melbourne VIC Australia"},"container-title":["Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3289600.3290993","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3289600.3290993","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3289600.3290993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:02:21Z","timestamp":1750208541000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3289600.3290993"}},"subtitle":["Modeling Non-Textual Characteristics of Podcasts"],"short-title":[],"issued":{"date-parts":[[2019,1,30]]},"references-count":52,"alternative-id":["10.1145\/3289600.3290993","10.1145\/3289600"],"URL":"https:\/\/doi.org\/10.1145\/3289600.3290993","relation":{},"subject":[],"published":{"date-parts":[[2019,1,30]]},"assertion":[{"value":"2019-01-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}