{"id":"https://openalex.org/W7160333719","doi":"https://doi.org/10.1145/3779211.3793160","title":"Cold-Start Audiobook Recommendation via Cross-Domain Sub-Tower Fusion","display_name":"Cold-Start Audiobook Recommendation via Cross-Domain Sub-Tower Fusion","publication_year":2026,"publication_date":"2026-02-22","ids":{"openalex":"https://openalex.org/W7160333719","doi":"https://doi.org/10.1145/3779211.3793160"},"language":null,"primary_location":{"id":"doi:10.1145/3779211.3793160","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779211.3793160","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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3779211.3793160","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102013451","display_name":"Kirandeep Kaur","orcid":"https://orcid.org/0000-0003-2424-4563"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kirandeep Kaur","raw_affiliation_strings":["University of Washington, Seattle, Washington, USA"],"raw_orcid":"https://orcid.org/0009-0000-7128-1792","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, Washington, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078703356","display_name":"Amit Goyal","orcid":"https://orcid.org/0009-0002-8354-3336"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I2800075581","display_name":"San Francisco Conservatory of Music","ror":"https://ror.org/016gc3g35","country_code":"US","type":"education","lineage":["https://openalex.org/I2800075581"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit Goyal","raw_affiliation_strings":["Amazon Music, San Francisco, California, USA"],"raw_orcid":"https://orcid.org/0009-0002-8354-3336","affiliations":[{"raw_affiliation_string":"Amazon Music, San Francisco, California, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I2800075581"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52709202,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.38830000162124634,"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":0.38830000162124634,"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":0.2702000141143799,"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/T11439","display_name":"Video Analysis and Summarization","score":0.04439999908208847,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.8040000200271606},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5837000012397766},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4828000068664551},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4763000011444092},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.4607999920845032},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4253999888896942},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.35499998927116394}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.8040000200271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779699981212616},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5837000012397766},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3662000000476837},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3400000035762787},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3059000074863434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2937000095844269},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26339998841285706},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3779211.3793160","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779211.3793160","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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3779211.3793160","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779211.3793160","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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.40924039483070374}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2046974451","https://openalex.org/W2114079787","https://openalex.org/W2117420919","https://openalex.org/W2158515176","https://openalex.org/W2183341477","https://openalex.org/W2512971201","https://openalex.org/W2760103357","https://openalex.org/W2796608345","https://openalex.org/W4283324687"],"related_works":[],"abstract_inverted_index":{"For":[0],"music":[1,71,117],"streaming":[2,118,279],"services":[3],"expanding":[4],"into":[5,137,178,282],"audiobooks,":[6],"cold-start":[7,34,42,267],"personalization":[8,45,103],"presents":[9],"a":[10,16,87,115,121,239,262,270],"critical":[11],"challenge:":[12],"as":[13],"audiobooks":[14],"are":[15],"newly":[17],"introduced":[18],"content":[19,164,275],"type,":[20],"the":[21,54,66,112,130,155,179,235],"vast":[22],"majority":[23],"of":[24,70,114,213],"existing":[25],"users":[26,60,214],"have":[27],"no":[28],"audiobook":[29,83,159,244],"listening":[30],"history.":[31],"This":[32,181],"domain-level":[33],"scenario":[35],"differs":[36],"from":[37],"traditional":[38],"item":[39,156],"or":[40],"user":[41,131],"scenarios,":[43],"since":[44],"must":[46],"begin":[47],"before":[48],"any":[49,278],"behavioral":[50],"data":[51],"exists":[52],"in":[53,65,105,111,234,242],"target":[55],"domain.":[56],"Yet":[57],"these":[58,152],"same":[59],"possess":[61],"rich":[62],"engagement":[63],"histories":[64],"platform's":[67],"established":[68],"offerings":[69],"and":[72,93,135,145,185,196,219,228],"pod-casts,":[73],"creating":[74],"an":[75,147],"opportunity":[76],"to":[77,211,221,247],"transfer":[78,99],"cross-modal":[79,98],"signals":[80,141],"for":[81,91,171,265,273],"early-stage":[82],"recommendations.":[84],"We":[85],"present":[86],"lightweight":[88],"framework":[89],"designed":[90],"scalability":[92],"minimal":[94,216],"retraining,":[95],"showing":[96],"that":[97,253],"can":[100],"yield":[101],"strong":[102,204],"even":[104],"sparse":[106],"domains.":[107],"Our":[108,208],"framework,":[109],"studied":[110],"context":[113],"large-scale":[116],"service,":[119],"adopts":[120],"two-tower":[122],"design":[123,127],"with":[124,203,215,257],"two":[125],"key":[126],"choices:":[128],"(1)":[129],"side":[132,157],"is":[133],"frozen":[134,254],"structured":[136],"modality-specific":[138],"sub-towers,":[139],"preserving":[140],"without":[142],"retraining":[143],"overhead;":[144],"(2)":[146],"adaptive":[148],"fusion":[149],"mechanism":[150],"integrates":[151],"signals,":[153],"while":[154],"learns":[158],"embeddings.":[160],"To":[161],"further":[162],"enrich":[163],"representations,":[165],"we":[166],"incorporate":[167],"BAAI's":[168],"BGE":[169],"model":[170],"text":[172,259],"encoding,":[173],"which":[174],"injects":[175],"semantic":[176],"knowledge":[177],"towers.":[180],"combination":[182],"yields":[183],"consistent":[184],"substantial":[186],"relative":[187],"gains:":[188],"offline":[189],"precision":[190],"exceeds":[191],"+100%":[192],"over":[193,198],"popularity":[194,248],"baselines":[195],"+50%":[197],"single-domain":[199],"based":[200],"collocation":[201],"methods,":[202],"complementarity":[205],"between":[206],"modalities.":[207],"method":[209],"scales":[210],"millions":[212],"training":[217],"cost":[218],"generalizes":[220],"public":[222],"datasets,":[223],"enabling":[224],"both":[225],"open":[226],"research":[227],"industrial":[229],"adoption.":[230],"Large-scale":[231],"A/B":[232],"testing":[233],"US":[236],"marketplace":[237],"demonstrates":[238],"~10%":[240],"improvement":[241],"first":[243],"listens":[245],"compared":[246],"baselines.":[249],"These":[250],"results":[251],"demonstrate":[252],"multi-modal":[255],"sub-towers":[256],"pretrained":[258],"enrichment":[260],"offer":[261],"principled":[263],"alternative":[264],"cross-domain":[266],"personalization,":[268],"providing":[269],"generalizable":[271],"architecture":[272],"efficient":[274],"expansion":[276],"across":[277],"platform":[280],"diversifying":[281],"new":[283],"media":[284],"types.":[285]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}