{"id":"https://openalex.org/W4408345773","doi":"https://doi.org/10.1109/icassp49660.2025.10890279","title":"Improving Contextual ASR with Enhanced Phrase-Level Representation Based on MCTC Loss","display_name":"Improving Contextual ASR with Enhanced Phrase-Level Representation Based on MCTC Loss","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345773","doi":"https://doi.org/10.1109/icassp49660.2025.10890279"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5080919889","display_name":"Ming Fang","orcid":"https://orcid.org/0000-0003-1932-2037"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ming Fang","raw_affiliation_strings":["Ping An Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012261926","display_name":"Tao Wei","orcid":"https://orcid.org/0000-0002-6549-3999"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Wei","raw_affiliation_strings":["Ping An Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010391671","display_name":"Kaikai Guo","orcid":"https://orcid.org/0000-0002-4219-5171"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Guo","raw_affiliation_strings":["Ping An Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088311121","display_name":"Ziyang Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Zhuang","raw_affiliation_strings":["Ping An Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002110970","display_name":"Yan Shi","orcid":"https://orcid.org/0000-0002-6954-0537"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Shi","raw_affiliation_strings":["Ping An Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977180","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0002-0988-5023"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Cheng","raw_affiliation_strings":["Ping An Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702017","display_name":"Shaojun Wang","orcid":"https://orcid.org/0009-0001-8955-8566"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Wang","raw_affiliation_strings":["Ping An Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5080919889"],"corresponding_institution_ids":["https://openalex.org/I4401726822"],"apc_list":null,"apc_paid":null,"fwci":4.8241,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93957713,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9595999717712402,"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":0.9595999717712402,"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":0.9225000143051147,"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":0.7251836061477661},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6508193016052246},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6075324416160583},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.439247190952301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38308286666870117},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33558809757232666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251836061477661},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6508193016052246},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6075324416160583},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.439247190952301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38308286666870117},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33558809757232666},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2886319145","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2962826786","https://openalex.org/W2972625221","https://openalex.org/W3016167541","https://openalex.org/W3140235797","https://openalex.org/W3160405885","https://openalex.org/W3160413945","https://openalex.org/W3197478142","https://openalex.org/W3198004110","https://openalex.org/W4225289150","https://openalex.org/W4319862261","https://openalex.org/W4385822246","https://openalex.org/W4392903019","https://openalex.org/W4392903078","https://openalex.org/W6623517193","https://openalex.org/W6675365184","https://openalex.org/W6754473786"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2012262991","https://openalex.org/W2373794620","https://openalex.org/W2060629350","https://openalex.org/W2357294589","https://openalex.org/W2386861027","https://openalex.org/W2349302580","https://openalex.org/W2390154576","https://openalex.org/W2916983164","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Contextual":[0],"biasing":[1,59],"is":[2],"essential":[3],"for":[4,34,125],"addressing":[5],"scenario-specific":[6],"challenges":[7],"in":[8,95,107,123],"End-to-End":[9],"(E2E)":[10],"Automatic":[11],"Speech":[12],"Recognition":[13],"(ASR)":[14],"systems.":[15],"Prior":[16],"contextual":[17,24,58,87],"E2E":[18],"ASR":[19,45,75],"methods,":[20],"such":[21],"as":[22],"the":[23,41,44,63,72,110,115],"bias":[25,31,38,47,77],"with":[26,118],"CPP":[27],"Network,":[28],"have":[29],"utilized":[30],"CTC":[32,67],"loss":[33],"explicit":[35],"supervision":[36],"of":[37],"tasks,":[39],"However,":[40],"alignment":[42],"between":[43,74],"and":[46,76],"tasks":[48],"has":[49],"been":[50],"largely":[51],"neglected.":[52],"This":[53],"paper":[54],"introduces":[55],"a":[56,104],"novel":[57],"approach":[60],"that":[61],"employs":[62],"Multi-label":[64],"Synchronous":[65],"Output":[66],"(MCTC)":[68],"algorithm":[69],"to":[70,85,114],"enhance":[71],"synchronization":[73],"task":[78],"outputs.":[79],"Furthermore,":[80],"we":[81],"propose":[82],"an":[83,119],"enhancement":[84],"phrase-level":[86],"representation.":[88],"Our":[89],"proposed":[90],"method":[91],"demonstrates":[92],"significant":[93],"improvements":[94],"Word":[96],"Error":[97],"Rate":[98],"(WER).":[99],"Specifically,":[100],"our":[101],"experiments":[102],"reveal":[103],"15.0%":[105],"reduction":[106,122],"WER":[108,124],"on":[109],"Librispeech-960":[111],"dataset":[112],"compared":[113],"CPPN":[116],"method,":[117],"impressive":[120],"29.0%":[121],"context":[126],"phrases.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}