{"id":"https://openalex.org/W2972430654","doi":"https://doi.org/10.21437/interspeech.2019-3173","title":"Cross-Attention End-to-End ASR for Two-Party Conversations","display_name":"Cross-Attention End-to-End ASR for Two-Party Conversations","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972430654","doi":"https://doi.org/10.21437/interspeech.2019-3173","mag":"2972430654"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-3173","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","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/A5062940343","display_name":"Suyoun Kim","orcid":"https://orcid.org/0000-0002-6822-337X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suyoun Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068873086","display_name":"Siddharth Dalmia","orcid":"https://orcid.org/0000-0003-0437-5988"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siddharth Dalmia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4380","last_page":"4384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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/T12031","display_name":"Speech and dialogue systems","score":0.9884999990463257,"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/T10860","display_name":"Speech and Audio Processing","score":0.9865000247955322,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8304023742675781},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7932096719741821},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6817598938941956},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5986909866333008},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5225224494934082},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.4974518120288849},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4786902070045471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37010979652404785},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34174251556396484},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09552192687988281},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08042958378791809}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8304023742675781},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7932096719741821},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6817598938941956},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5986909866333008},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5225224494934082},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.4974518120288849},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4786902070045471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37010979652404785},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34174251556396484},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09552192687988281},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08042958378791809},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-3173","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"We":[0,74],"present":[1],"an":[2,38],"end-to-end":[3,39,91],"speech":[4,20,82,92],"recognition":[5,21,93],"model":[6,24,88],"that":[7,32,48,86],"learns":[8],"interaction":[9],"between":[10],"two":[11,26],"speakers":[12],"based":[13],"on":[14,78],"the":[15,52,55,62,65,76,79],"turn-changing":[16],"information.":[17],"Unlike":[18],"conventional":[19],"models,":[22],"our":[23,87],"exploits":[25],"speakers'":[27],"history":[28],"of":[29,54,64],"conversational-context":[30],"information":[31],"spans":[33],"across":[34],"multiple":[35],"turns":[36],"within":[37],"framework.":[40],"Specifically,":[41],"we":[42],"propose":[43],"a":[44],"speaker-specific":[45],"cross-attention":[46],"mechanism":[47],"can":[49],"look":[50],"at":[51,70],"output":[53],"other":[56],"speaker":[57,67],"side":[58],"as":[59,61],"well":[60],"one":[63],"current":[66],"for":[68],"better":[69],"recognizing":[71],"long":[72],"conversations.":[73],"evaluated":[75],"models":[77],"Switchboard":[80],"conversational":[81],"corpus":[83],"and":[84],"show":[85],"outperforms":[89],"standard":[90],"models.":[94]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
