{"id":"https://openalex.org/W7148319401","doi":"https://doi.org/10.1109/asru65441.2025.11434597","title":"Phoneme Overlapping-Aware Pre-Training with External Text Resources for Multi-Talker ASR","display_name":"Phoneme Overlapping-Aware Pre-Training with External Text Resources for Multi-Talker ASR","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148319401","doi":"https://doi.org/10.1109/asru65441.2025.11434597"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132794058","display_name":"Tomohiro Tanaka","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082466886","display_name":"Naoki Makishima","orcid":"https://orcid.org/0000-0002-7065-315X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoki Makishima","raw_affiliation_strings":["NTT Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027118468","display_name":"Mana Ihori","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mana Ihori","raw_affiliation_strings":["NTT Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013009514","display_name":"Shota Orihashi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Orihashi","raw_affiliation_strings":["NTT Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016817412","display_name":"Naotaka Kawata","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naotaka Kawata","raw_affiliation_strings":["NTT Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102511251","display_name":"Taiga Yamane","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taiga Yamane","raw_affiliation_strings":["NTT Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132820735","display_name":"Satoshi Suzuki","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Suzuki","raw_affiliation_strings":["NTT Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032842000","display_name":"Takafumi Moriya","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5060644399"],"corresponding_institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87552671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.7829999923706055,"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":0.7829999923706055,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.07150000333786011,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.04670000076293945,"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/process","display_name":"Process (computing)","score":0.28700000047683716},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.26669999957084656},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.25760000944137573},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.241799995303154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5963000059127808},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4487000107765198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41449999809265137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38269999623298645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.241799995303154},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24060000479221344},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.21819999814033508}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":38,"referenced_works":["https://openalex.org/W2577366047","https://openalex.org/W2888779557","https://openalex.org/W2890244912","https://openalex.org/W2936774411","https://openalex.org/W2963574857","https://openalex.org/W2963773971","https://openalex.org/W3013139777","https://openalex.org/W3015280134","https://openalex.org/W3015834770","https://openalex.org/W3017474798","https://openalex.org/W3020336359","https://openalex.org/W3097632072","https://openalex.org/W3162037819","https://openalex.org/W3162244132","https://openalex.org/W3163605596","https://openalex.org/W3181056718","https://openalex.org/W3197533300","https://openalex.org/W3209059054","https://openalex.org/W3212886388","https://openalex.org/W4226491018","https://openalex.org/W4367597591","https://openalex.org/W4372260044","https://openalex.org/W4372348115","https://openalex.org/W4372349800","https://openalex.org/W4385245566","https://openalex.org/W4385822321","https://openalex.org/W4385822643","https://openalex.org/W4385822736","https://openalex.org/W4385823377","https://openalex.org/W4392904528","https://openalex.org/W4392909582","https://openalex.org/W4402111558","https://openalex.org/W4402112082","https://openalex.org/W4402116591","https://openalex.org/W4406461489","https://openalex.org/W4406461575","https://openalex.org/W4406461869","https://openalex.org/W4408352078"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,108],"new":[4],"pre-training":[5,34],"method":[6,95,123],"utilizing":[7],"external":[8,53,65,114],"text":[9,51,54,66,115],"resources":[10,67],"to":[11,39,76,80,97,106,111],"improve":[12],"the":[13,27,78,93,121,126],"robustness":[14],"of":[15,29,92],"single-channel":[16],"multi-talker":[17],"automatic":[18],"speech":[19],"recognition":[20],"(MTASR)":[21],"across":[22],"various":[23,33],"linguistic":[24,134],"domains.":[25],"In":[26],"development":[28],"single-talker":[30],"ASR":[31],"systems,":[32],"methods":[35,57],"have":[36],"been":[37],"studied":[38],"acquire":[40,77],"knowledge":[41],"about":[42],"word":[43],"order":[44,105],"and":[45,50,132],"correspondence":[46],"between":[47],"phonetic":[48,87],"information":[49],"from":[52],"resources.":[55,116],"However,":[56],"focusing":[58],"on":[59,129],"improving":[60],"MT-ASR":[61,112,127],"performance":[62,128],"by":[63],"leveraging":[64],"remain":[68],"underexplored.":[69],"To":[70],"bridge":[71],"this":[72],"gap,":[73],"we":[74],"aim":[75],"ability":[79],"discover":[81],"multiple":[82],"texts":[83],"contained":[84],"within":[85],"overlapping":[86,99],"information.":[88],"The":[89],"key":[90],"idea":[91],"proposed":[94,122],"is":[96],"induce":[98],"phenomena":[100],"in":[101,104],"phoneme":[102],"sequences":[103],"reproduce":[107],"task":[109],"similar":[110],"using":[113],"Our":[117],"experiments":[118],"demonstrate":[119],"that":[120],"significantly":[124],"improves":[125],"both":[130],"in-domain":[131],"out-of-domain":[133],"tasks.":[135]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}
