{"id":"https://openalex.org/W4415537348","doi":"https://doi.org/10.1145/3746027.3754919","title":"CCStereo: Audio-Visual Contextual and Contrastive Learning for Binaural Audio Generation","display_name":"CCStereo: Audio-Visual Contextual and Contrastive Learning for Binaural Audio Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537348","doi":"https://doi.org/10.1145/3746027.3754919"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754919","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754919","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754919","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040468008","display_name":"Yuanhong Chen","orcid":"https://orcid.org/0000-0002-8983-2895"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuanhong Chen","raw_affiliation_strings":["Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8983-2895","affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051965288","display_name":"Kazuki Shimada","orcid":"https://orcid.org/0000-0001-5389-2346"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuki Shimada","raw_affiliation_strings":["Sony AI, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5389-2346","affiliations":[{"raw_affiliation_string":"Sony AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103918149","display_name":"Christian Simon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Simon","raw_affiliation_strings":["Sony Group Corporation, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0000-3642-820X","affiliations":[{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087321595","display_name":"Yukara Ikemiya","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukara Ikemiya","raw_affiliation_strings":["Sony AI, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0006-0296-4390","affiliations":[{"raw_affiliation_string":"Sony AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084845461","display_name":"Takashi Shibuya","orcid":"https://orcid.org/0000-0002-4277-0164"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Shibuya","raw_affiliation_strings":["Sony AI, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4277-0164","affiliations":[{"raw_affiliation_string":"Sony AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony AI, Sony Group Corporation, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-6806-6140","affiliations":[{"raw_affiliation_string":"Sony AI, Sony Group Corporation, New York, NY, USA","institution_ids":["https://openalex.org/I2800278093"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7510","last_page":"7518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/T10860","display_name":"Speech and Audio Processing","score":0.9940999746322632,"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":0.9872999787330627,"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/monaural","display_name":"Monaural","score":0.7447999715805054},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.7289999723434448},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5679000020027161},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44530001282691956},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3228999972343445},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.32179999351501465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.771399974822998},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7447999715805054},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7289999723434448},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5679000020027161},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5346999764442444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.524399995803833},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44530001282691956},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3228999972343445},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30059999227523804},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754919","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754919","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3754919","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754919","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2120847449","https://openalex.org/W2194775991","https://openalex.org/W2475287302","https://openalex.org/W2603777577","https://openalex.org/W2962770929","https://openalex.org/W2962865004","https://openalex.org/W2962974533","https://openalex.org/W2964008635","https://openalex.org/W2964313012","https://openalex.org/W2982624843","https://openalex.org/W2997909293","https://openalex.org/W3035333188","https://openalex.org/W3035524453","https://openalex.org/W3047371217","https://openalex.org/W3170088426","https://openalex.org/W3171007011","https://openalex.org/W3174854700","https://openalex.org/W3198586259","https://openalex.org/W4205278059","https://openalex.org/W4214592090","https://openalex.org/W4313023122","https://openalex.org/W4323657311","https://openalex.org/W4390873054","https://openalex.org/W4390975304","https://openalex.org/W4396620480","https://openalex.org/W4402753794"],"related_works":[],"abstract_inverted_index":{"Binaural":[0],"audio":[1,8,11,53,129],"generation":[2,65,115,172],"(BAG)":[3],"aims":[4],"to":[5,9,62,94,158,165],"convert":[6],"monaural":[7],"stereo":[10],"using":[12,131],"visual":[13,47,132,150],"prompts,":[14],"requiring":[15],"a":[16,111,141,155],"deep":[17],"understanding":[18],"of":[19,26,34,46,87],"spatial":[20,38,72,89,136],"and":[21,37,67,71,79,91,178],"semantic":[22],"information.":[23],"The":[24],"success":[25],"the":[27,32,44,64,69,85,106,126,175],"BAG":[28],"systems":[29],"depends":[30],"on":[31,59,174],"effectiveness":[33],"cross-modal":[35],"reasoning":[36],"understanding.":[39],"Current":[40],"methods":[41],"have":[42],"explored":[43],"use":[45],"information":[48,73],"as":[49],"guidance":[50],"for":[51],"binaural":[52,114],"generation.":[54],"However,":[55],"they":[56],"rely":[57],"solely":[58],"cross-attention":[60],"mechanisms":[61],"guide":[63],"process":[66],"under-utilise":[68],"temporal":[70],"in":[74,84,162],"video":[75,163],"data":[76,164],"during":[77],"training":[78],"inference.":[80],"These":[81],"limitations":[82],"result":[83],"loss":[86],"fine-grained":[88],"details":[90],"risk":[92],"overfitting":[93],"specific":[95],"environments,":[96],"ultimately":[97],"constraining":[98],"model":[99,116],"performance.":[100,167],"In":[101],"this":[102],"paper,":[103],"we":[104,138],"address":[105],"aforementioned":[107],"issues":[108],"by":[109],"introducing":[110],"new":[112],"audio-visual":[113,119],"with":[117],"an":[118],"conditional":[120],"normalisation":[121],"layer":[122],"that":[123,145],"dynamically":[124],"aligns":[125],"target":[127],"difference":[128],"features":[130],"context.":[133],"To":[134],"enhance":[135,166],"sensitivity,":[137],"also":[139,153],"introduce":[140,154],"contrastive":[142],"learning":[143],"method":[144],"mines":[146],"negatives":[147],"from":[148],"shuffled":[149],"features.":[151],"We":[152],"cost-efficient":[156],"way":[157],"utilise":[159],"test-time":[160],"augmentation":[161],"Our":[168],"approach":[169],"achieves":[170],"state-of-the-art":[171],"accuracy":[173],"FAIR-Play,":[176],"MUSIC-Stereo,":[177],"YT-MUSIC":[179],"benchmarks.":[180],"Code":[181],"is":[182],"available":[183],"at":[184],"https://github.com/SonyResearch/CCStereo.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}