{"id":"https://openalex.org/W2962865004","doi":"https://doi.org/10.1007/978-3-030-01246-5_35","title":"The Sound of Pixels","display_name":"The Sound of Pixels","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2962865004","doi":"https://doi.org/10.1007/978-3-030-01246-5_35","mag":"2962865004"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-01246-5_35","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-01246-5_35","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101826600","display_name":"Hang Zhao","orcid":"https://orcid.org/0009-0002-8690-415X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hang Zhao","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040877128","display_name":"Chuang Gan","orcid":"https://orcid.org/0000-0003-4031-5886"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuang Gan","raw_affiliation_strings":["MIT-IBM Watson AI Lab, Cambridge, USA","Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab, Cambridge, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010091252","display_name":"Andrew Rouditchenko","orcid":"https://orcid.org/0000-0002-0063-3612"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rouditchenko","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103033393","display_name":"Carl Vondrick","orcid":"https://orcid.org/0000-0001-5676-2387"},"institutions":[{"id":"https://openalex.org/I45029084","display_name":"City University of Seattle","ror":"https://ror.org/008a9hf75","country_code":"US","type":"education","lineage":["https://openalex.org/I4210086682","https://openalex.org/I45029084"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Vondrick","raw_affiliation_strings":["Columbia University, New York City, USA","Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York City, USA","institution_ids":["https://openalex.org/I78577930","https://openalex.org/I45029084"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110628266","display_name":"Josh H. McDermott","orcid":"https://orcid.org/0000-0002-3965-2503"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Josh McDermott","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085020955","display_name":"Antonio Torralba","orcid":"https://orcid.org/0000-0003-4915-0256"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Torralba","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101826600"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":85.2501,"has_fulltext":false,"cited_by_count":467,"citation_normalized_percentile":{"value":1.0,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"587","last_page":"604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8982702493667603},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6011301279067993},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5707977414131165},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5640538930892944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5515232682228088},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5393843650817871},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5136699080467224},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4750273823738098},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3851754367351532},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09362262487411499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8982702493667603},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6011301279067993},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5707977414131165},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5640538930892944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5515232682228088},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5393843650817871},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5136699080467224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4750273823738098},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3851754367351532},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09362262487411499},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-01246-5_35","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-01246-5_35","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W84281818","https://openalex.org/W219040644","https://openalex.org/W343636949","https://openalex.org/W1246381107","https://openalex.org/W1755563775","https://openalex.org/W1901129140","https://openalex.org/W1971168548","https://openalex.org/W2065274193","https://openalex.org/W2098950531","https://openalex.org/W2104298926","https://openalex.org/W2105582566","https://openalex.org/W2113896236","https://openalex.org/W2127851351","https://openalex.org/W2142638745","https://openalex.org/W2143132653","https://openalex.org/W2143169494","https://openalex.org/W2150415460","https://openalex.org/W2161219071","https://openalex.org/W2164899449","https://openalex.org/W2184188583","https://openalex.org/W2194775991","https://openalex.org/W2198618282","https://openalex.org/W2221409856","https://openalex.org/W2295107390","https://openalex.org/W2315268655","https://openalex.org/W2404400936","https://openalex.org/W2407685581","https://openalex.org/W2422305492","https://openalex.org/W2511428026","https://openalex.org/W2526050071","https://openalex.org/W2544224704","https://openalex.org/W2562637781","https://openalex.org/W2575671312","https://openalex.org/W2587994092","https://openalex.org/W2599837529","https://openalex.org/W2607170299","https://openalex.org/W2619697695","https://openalex.org/W2737258237","https://openalex.org/W2775505379","https://openalex.org/W2798271879","https://openalex.org/W2799062425","https://openalex.org/W2895013824","https://openalex.org/W2949099979","https://openalex.org/W2962960500","https://openalex.org/W2963420272","https://openalex.org/W2963426332","https://openalex.org/W2963680395","https://openalex.org/W2963807156","https://openalex.org/W2963887950","https://openalex.org/W2964207404","https://openalex.org/W2964345931","https://openalex.org/W4289665794","https://openalex.org/W6602452458"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W4306353150","https://openalex.org/W8219677","https://openalex.org/W2909726438","https://openalex.org/W2168054807","https://openalex.org/W2058990474","https://openalex.org/W2026860389","https://openalex.org/W2043363698","https://openalex.org/W3207883763","https://openalex.org/W4386977688"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":37},{"year":2024,"cited_by_count":54},{"year":2023,"cited_by_count":47},{"year":2022,"cited_by_count":52},{"year":2021,"cited_by_count":104},{"year":2020,"cited_by_count":98},{"year":2019,"cited_by_count":50},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}