{"id":"https://openalex.org/W4391021684","doi":"https://doi.org/10.1109/asru57964.2023.10389803","title":"Mask-Conformer: Augmenting Conformer with Mask-Predict Decoder","display_name":"Mask-Conformer: Augmenting Conformer with Mask-Predict Decoder","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021684","doi":"https://doi.org/10.1109/asru57964.2023.10389803"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5102017467","display_name":"Yosuke Higuchi","orcid":"https://orcid.org/0000-0003-4500-8957"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Yosuke Higuchi","raw_affiliation_strings":["Google Inc.,USA","Google Inc., USA","Waseda University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc.,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024913801","display_name":"Andrew E. Rosenberg","orcid":"https://orcid.org/0000-0002-4536-8824"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["Google Inc.,USA","Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc.,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002438548","display_name":"Yuan Wang","orcid":"https://orcid.org/0000-0002-4951-4286"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Wang","raw_affiliation_strings":["Google Inc.,USA","Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc.,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064113992","display_name":"Murali Karthick Baskar","orcid":"https://orcid.org/0000-0002-9396-6319"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murali Karthick Baskar","raw_affiliation_strings":["Google Inc.,USA","Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc.,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["Google Inc.,USA","Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc.,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9868000149726868,"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":0.9868000149726868,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9735999703407288,"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"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9656999707221985,"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/conformational-isomerism","display_name":"Conformational isomerism","score":0.9362785220146179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4901779294013977},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.230838805437088},{"id":"https://openalex.org/keywords/molecule","display_name":"Molecule","score":0.0712914764881134},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.05578744411468506}],"concepts":[{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.9362785220146179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4901779294013977},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.230838805437088},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.0712914764881134},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.05578744411468506}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1964175594","https://openalex.org/W1985258458","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2884975363","https://openalex.org/W2963240019","https://openalex.org/W2973122799","https://openalex.org/W2988975212","https://openalex.org/W3011339933","https://openalex.org/W3015537910","https://openalex.org/W3015686596","https://openalex.org/W3015960524","https://openalex.org/W3015995734","https://openalex.org/W3016010032","https://openalex.org/W3016011332","https://openalex.org/W3024308166","https://openalex.org/W3034775979","https://openalex.org/W3095173472","https://openalex.org/W3097777922","https://openalex.org/W3097882114","https://openalex.org/W3112157188","https://openalex.org/W3161532853","https://openalex.org/W3162249256","https://openalex.org/W3163793923","https://openalex.org/W3197140813","https://openalex.org/W3197976839","https://openalex.org/W3198270883","https://openalex.org/W3198654230","https://openalex.org/W3204696009","https://openalex.org/W3205920203","https://openalex.org/W3206573929","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224919446","https://openalex.org/W4225824617","https://openalex.org/W4226033575","https://openalex.org/W4226120743","https://openalex.org/W4285192675","https://openalex.org/W4296068993","https://openalex.org/W4319862255","https://openalex.org/W4319862660","https://openalex.org/W4372260576","https://openalex.org/W4385567350","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6694517276","https://openalex.org/W6739901393","https://openalex.org/W6743726175","https://openalex.org/W6755207826","https://openalex.org/W6760633627","https://openalex.org/W6774835902","https://openalex.org/W6780218876","https://openalex.org/W6784400248","https://openalex.org/W6784614252","https://openalex.org/W6791904447","https://openalex.org/W6792376965","https://openalex.org/W6839026989","https://openalex.org/W6840202044","https://openalex.org/W6845926471"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2023036309","https://openalex.org/W1972863456","https://openalex.org/W2089371831","https://openalex.org/W2052399476","https://openalex.org/W2810163160","https://openalex.org/W3083970380","https://openalex.org/W2037964119","https://openalex.org/W4220905048"],"abstract_inverted_index":{"Much":[0],"of":[1,92,140],"the":[2,34,58,81,96,101,118,138,141],"recent":[3],"progress":[4],"in":[5,11,40,61],"automatic":[6],"speech":[7,27],"recognition":[8],"(ASR)":[9],"lies":[10],"developing":[12],"an":[13,53,62],"acoustic":[14],"encoder,":[15],"such":[16],"as":[17,43],"enlarging":[18],"its":[19,41],"capacity":[20],"and":[21],"designing":[22],"a":[23,44,69,73,109,115],"refined":[24],"architecture":[25],"for":[26,56],"processing.":[28],"With":[29],"these":[30],"highly":[31],"optimized":[32],"encoders,":[33],"decoder":[35,87,97],"has":[36],"become":[37],"less":[38],"influential":[39],"role":[42],"language":[45],"model":[46,71,143],"(LM).":[47],"In":[48,133],"this":[49],"work,":[50],"we":[51],"explore":[52],"effective":[54],"approach":[55],"employing":[57],"LM":[59,83],"structure":[60],"ASR":[63],"model.":[64],"The":[65,85],"proposed":[66,142],"Mask-Conformer":[67,126],"augments":[68],"Conformer-based":[70],"with":[72],"mask-predict":[74,86],"decoder,":[75],"which":[76],"learns":[77],"output":[78,98],"context":[79],"via":[80],"masked":[82],"objective.":[84],"is":[88],"applied":[89],"to":[90],"stacks":[91],"encoder":[93],"layers,":[94],"where":[95],"explicitly":[99],"conditions":[100],"subsequent":[102],"layers":[103],"using":[104,117],"cross-attention.":[105],"We":[106],"also":[107],"propose":[108],"fill-mask":[110],"decoding":[111],"algorithm":[112],"that":[113,125],"refines":[114],"sequence":[116],"decoder\u2019s":[119],"linguistic":[120],"information.":[121],"Experimental":[122],"results":[123],"show":[124],"outperforms":[127],"strong":[128],"baselines":[129],"on":[130],"some":[131],"tasks.":[132],"addition,":[134],"our":[135],"analyses":[136],"validate":[137],"effectiveness":[139],"design.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}