{"id":"https://openalex.org/W4392908925","doi":"https://doi.org/10.1109/icassp48485.2024.10446126","title":"S2E: Towards an End-to-End Entity Resolution Solution from Acoustic Signal","display_name":"S2E: Towards an End-to-End Entity Resolution Solution from Acoustic Signal","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908925","doi":"https://doi.org/10.1109/icassp48485.2024.10446126"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5022653372","display_name":"Kangrui Ruan","orcid":"https://orcid.org/0009-0000-7850-0206"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kangrui Ruan","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626703","display_name":"Xin He","orcid":"https://orcid.org/0000-0002-5189-7204"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin He","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032989092","display_name":"Jiyang Wang","orcid":"https://orcid.org/0009-0004-5079-4299"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiyang Wang","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102065966","display_name":"Xiaozhou Zhou","orcid":"https://orcid.org/0009-0007-5128-6052"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaozhou Zhou","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104260153","display_name":"Helian Feng","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Helian Feng","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049026549","display_name":"Ali Kebarighotbi","orcid":"https://orcid.org/0009-0004-6153-0483"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Kebarighotbi","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8328,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86724508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10441","last_page":"10445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11719","display_name":"Data Quality and Management","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.8390613198280334},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7109094262123108},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6709450483322144},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6484039425849915},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6192541122436523},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.568363606929779},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.539357602596283},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5033170580863953},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40659183263778687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37519168853759766},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34017497301101685},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0840902328491211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8390613198280334},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7109094262123108},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6709450483322144},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6484039425849915},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6192541122436523},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.568363606929779},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.539357602596283},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5033170580863953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40659183263778687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37519168853759766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34017497301101685},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0840902328491211},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2106053110","https://openalex.org/W2132679783","https://openalex.org/W2555897561","https://openalex.org/W2885588259","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2919350184","https://openalex.org/W2946417913","https://openalex.org/W2964051877","https://openalex.org/W2972327934","https://openalex.org/W2972584841","https://openalex.org/W3015885816","https://openalex.org/W3086154751","https://openalex.org/W3091432621","https://openalex.org/W3092962901","https://openalex.org/W3098169801","https://openalex.org/W3144724153","https://openalex.org/W3176896803","https://openalex.org/W3185050821","https://openalex.org/W4285137661","https://openalex.org/W4287887705","https://openalex.org/W4296069273","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4384661103","https://openalex.org/W4390582266","https://openalex.org/W6675751002","https://openalex.org/W6679781796","https://openalex.org/W6730323794","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6791353385","https://openalex.org/W6847363464","https://openalex.org/W6860127287","https://openalex.org/W7062415574"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W3179968364","https://openalex.org/W2043093291"],"abstract_inverted_index":{"Traditional":[0],"cascading":[1,111],"Entity":[2],"Resolution":[3],"(ER)":[4],"pipeline":[5],"suffers":[6],"from":[7,10,38],"propagated":[8],"errors":[9],"upstream":[11],"tasks.":[12],"We":[13,67],"address":[14],"this":[15],"issue":[16],"by":[17,59,113],"formulating":[18],"a":[19,61,78],"new":[20],"end-to-end":[21],"(E2E)":[22],"ER":[23,65],"problem,":[24],"Signal-to-Entity":[25],"(S2E),":[26],"resolving":[27],"query":[28],"entity":[29],"mentions":[30],"to":[31,64],"actionable":[32],"entities":[33],"in":[34,45,99],"textual":[35],"catalogs":[36],"directly":[37],"audio":[39,43],"queries":[40],"instead":[41],"of":[42,101],"transcriptions":[44],"raw":[46],"or":[47],"parsed":[48],"format.":[49],"Additionally,":[50],"we":[51],"extend":[52],"the":[53,73,83,102,106,110,119],"E2E":[54],"Spoken":[55],"Language":[56],"Understanding":[57],"framework":[58],"introducing":[60],"novel":[62,79],"dimension":[63],"research.":[66],"adapt":[68],"three":[69,120],"public":[70],"datasets":[71,121],"for":[72],"S2E":[74],"task,":[75],"and":[76,92,116],"propose":[77],"solution,":[80],"which":[81],"aligns":[82],"multimodal":[84,94],"signals":[85],"via":[86],"an":[87],"effective":[88],"retrieval":[89],"co-attention":[90],"mechanism":[91],"refined":[93],"objectives.":[95],"Despite":[96],"42%":[97],"smaller":[98],"terms":[100],"total":[103],"model":[104],"size,":[105],"proposed":[107],"design":[108],"outperforms":[109],"baseline":[112],"2.6%,":[114],"47.0%,":[115],"73.3%":[117],"across":[118],"respectively":[122],"with":[123],"different":[124],"acoustic":[125],"conditions.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}