{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:54:49Z","timestamp":1781016889237,"version":"3.54.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030678319","type":"print"},{"value":"9783030678326","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-67832-6_5","type":"book-chapter","created":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T17:44:48Z","timestamp":1611337488000},"page":"50-61","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Stacked Sparse Autoencoder for Audio Object Coding"],"prefix":"10.1007","author":[{"given":"Yulin","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruimin","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaochen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenhao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,1,21]]},"reference":[{"key":"5_CR1","unstructured":"Dolby Laboratories: Dolby ATMOS cinema specifications (2014). http:\/\/www.dolby.com\/us\/en\/technologies\/dolby-atmos\/dolby-atmos-specifications.pdf"},{"issue":"9","key":"5_CR2","first-page":"655","volume":"60","author":"J Herre","year":"2012","unstructured":"Herre, J., Purnhagen, H., Koppens, J., Hellmuth, O., Engdegrd, J., Hilper, J.: Valero ML (2012) MPEG spatial audio object coding - the ISO\/MPEG standard for efficient coding of interactive audio scenes. J. Audio Eng. Soc. 60(9), 655\u2013673 (2012)","journal-title":"J. Audio Eng. Soc."},{"issue":"5","key":"5_CR3","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/JSTSP.2015.2411578","volume":"9","author":"J Herre","year":"2015","unstructured":"Herre, J., Hilpert, J., Kuntz, A., Plogsties, J.: MPEG-H 3D audio-the new standard for coding of immersive spatial audio. IEEE J. Sel. Top. Signal Process. 9(5), 770\u2013779 (2015)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Herre, J., Disch, S.: New concepts in parametric coding of spatial audio: from SAC to SAOC. In: IEEE International Conference on Multimedia and Expo (ICME), pp. 1894\u20131897. IEEE (2007)","DOI":"10.1109\/ICME.2007.4285045"},{"key":"5_CR5","unstructured":"Herre, J., et al.: Spatial audio coding: next-generation efficient and compatible coding of multichannel audio. In: Audio Engineering Society Convention, vol. 117 (2004)"},{"issue":"6","key":"5_CR6","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.1109\/TMM.2011.2168197","volume":"13","author":"K Kim","year":"2011","unstructured":"Kim, K., Seo, J., Beack, S., Kang, K., Hahn, M.: Spatial audio object coding with two-step coding structure for interactive audio service. IEEE Trans. Multimedia 13(6), 1208\u20131216 (2011)","journal-title":"IEEE Trans. Multimedia"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Zheng, X., Ritz, C., Xi, J.: A psychoacoustic-based analysis-by-synthesis scheme for jointly encoding multiple audio objects into independent mixtures. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 281\u2013285. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6637653"},{"issue":"6","key":"5_CR8","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.1109\/TASLP.2015.2419980","volume":"23","author":"M Jia","year":"2015","unstructured":"Jia, M., Yang, Z., Bao, C., Zheng, X., Ritz, C.: Encoding multiple audio objects using intra-object sparsity. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(6), 1082\u20131095 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Rohlfing, C., Cohen, J. E., Liutkus, A.: Very low bitrate spatial audio coding with dimensionality reduction. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, pp. 741\u2013745 (2017)","DOI":"10.1109\/ICASSP.2017.7952254"},{"issue":"9","key":"5_CR10","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/CC.2017.8068762","volume":"14","author":"T Wu","year":"2017","unstructured":"Wu, T., Hu, R., Wang, X., Ke, S., Wang, J.: High quality audio object coding framework based on non-negative matrix factorization. China Commun. 14(9), 32\u201341 (2017)","journal-title":"China Commun."},{"issue":"15","key":"5_CR11","doi-asserted-by":"publisher","first-page":"20723","DOI":"10.1007\/s11042-019-7409-7","volume":"78","author":"T Wu","year":"2019","unstructured":"Wu, T., Hu, R., Wang, X., Ke, S.: Audio object coding based on optimal parameter frequency resolution. Multimedia Tools Appl. 78(15), 20723\u201320738 (2019)","journal-title":"Multimedia Tools Appl."},{"key":"5_CR12","unstructured":"Zhang, S., Wu, X., Qu, T.: Sparse autoencoder based multiple audio objects coding method. In: Audio Engineering Society Convention, vol. 146. Audio Engineering Society (2019)"},{"key":"5_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1007\/978-3-030-37731-1_54","volume-title":"MultiMedia Modeling","author":"C Hu","year":"2020","unstructured":"Hu, C., Hu, R., Wang, X., Wu, T., Li, D.: Multi-step coding structure of spatial audio object coding. In: Ro, Y.M., et al. (eds.) MMM 2020. LNCS, vol. 11961, pp. 666\u2013678. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-37731-1_54"},{"issue":"1","key":"5_CR14","first-page":"1957","volume":"11","author":"A Ilin","year":"2010","unstructured":"Ilin, A., Raiko, T.: Practical approaches to principal component analysis in the presence of missing values. J. Mach. Learn. Res. 11(1), 1957\u20132000 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR15","doi-asserted-by":"publisher","first-page":"2157","DOI":"10.1007\/s11042-018-6273-1","volume":"78","author":"G Mariem","year":"2019","unstructured":"Mariem, G., Ammar, L., Ridha, E., Mourad, Z.: Stacked sparse autoencoder and history of binary motion image for human activity recognition. Multimedia Tools Appl. 78, 2157\u20132179 (2019)","journal-title":"Multimedia Tools Appl."},{"issue":"6","key":"5_CR16","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1109\/TSA.2003.818108","volume":"11","author":"C Faller","year":"2003","unstructured":"Faller, C., Baumgarte, F.: Binaural cue coding-part II: schemes and applications. IEEE Trans. Speech Audio Process. 11(6), 520\u2013531 (2003)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"5","key":"5_CR17","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.neucom.2015.08.104","volume":"184","author":"Y Wang","year":"2016","unstructured":"Wang, Y., Yao, H., Zhao, S.: Auto-encoder based dimensionality reduction. Neurocomputing 184(5), 232\u2013242 (2016)","journal-title":"Neurocomputing"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Liutkus, A., Fabian-Robert, S., Rafii, Z., Kitamura, D., Rivet, B.: The 2016 Signal Separation Evaluation Campaign (2017). https:\/\/sigsep.github.io\/datasets\/dsd100.html","DOI":"10.1007\/978-3-319-53547-0_31"},{"key":"5_CR19","unstructured":"Fevotte, C., Gribonval R., Vincent, E.: BSS$$\\_$$EVAL Toolbox User Guide. IRISA, Technical report 1706 (2005). http:\/\/www.irisa.fr\/metiss\/bss_eval\/user_guide.pdf"},{"issue":"4","key":"5_CR20","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"Vincent, E., Gribonval, R., Fevotte, C.: Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Process. 14(4), 1462\u20131469 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"5_CR21","unstructured":"ITU Radiocommunication Bureau: \u201cBS.1534-3: Method for the subjective assessment of intermediate quality level of coding systems,\u201d Recommendation ITUR BS. 1534 (2015)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-67832-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,14]],"date-time":"2021-06-14T08:17:07Z","timestamp":1623658627000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-67832-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030678319","9783030678326"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-67832-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 January 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2021.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"211","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"73","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2,63","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2,5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}