{"id":"https://openalex.org/W4391021551","doi":"https://doi.org/10.1109/asru57964.2023.10389653","title":"Multi Transcription-Style Speech Transcription Using Attention-Based Encoder-Decoder Model","display_name":"Multi Transcription-Style Speech Transcription Using Attention-Based Encoder-Decoder Model","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021551","doi":"https://doi.org/10.1109/asru57964.2023.10389653"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389653","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389653","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":"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/A5100764458","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-6144-476X"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Yan Huang","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044402723","display_name":"Piyush Behre","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Piyush Behre","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008578397","display_name":"Guoli Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Guoli Ye","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057106988","display_name":"Shawn Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Shawn Chang","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100764458"],"corresponding_institution_ids":["https://openalex.org/I4210105678"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59625491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.9965999722480774,"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":0.7926414012908936},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7471948266029358},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7085931897163391},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.541593074798584},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5339779853820801},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14781373739242554},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06679478287696838}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926414012908936},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7471948266029358},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7085931897163391},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.541593074798584},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5339779853820801},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14781373739242554},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06679478287696838},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389653","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389653","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2025198378","https://openalex.org/W2161274063","https://openalex.org/W2294108103","https://openalex.org/W2426479676","https://openalex.org/W2526425061","https://openalex.org/W2545177271","https://openalex.org/W2749051922","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963414781","https://openalex.org/W3007227084","https://openalex.org/W3011339933","https://openalex.org/W3034625919","https://openalex.org/W3105681039","https://openalex.org/W3152534858","https://openalex.org/W3160789530","https://openalex.org/W3198587774","https://openalex.org/W3198739096","https://openalex.org/W3198878148","https://openalex.org/W3211278025","https://openalex.org/W4292595872","https://openalex.org/W4307322847","https://openalex.org/W4311000453","https://openalex.org/W4313655760","https://openalex.org/W4319862718","https://openalex.org/W4386840154","https://openalex.org/W4392903704","https://openalex.org/W6713490458","https://openalex.org/W6729005282","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Human":[0],"professional":[1],"transcription":[2,8,32,59,63,91],"services":[3],"provide":[4],"a":[5,27,74,87],"variety":[6],"of":[7,64],"styles":[9,66,130],"to":[10,29,107],"customize":[11],"different":[12,16,41,129],"needs.":[13],"To":[14],"accommodate":[15],"users":[17],"and":[18,60,117],"facilitate":[19],"seamless":[20],"integration":[21],"with":[22,94,111],"downstream":[23],"applications,":[24],"we":[25],"propose":[26],"framework":[28,100],"generate":[30],"multi-style":[31],"in":[33,86,114],"an":[34,123],"attention-based":[35],"encoder-decoder":[36],"model":[37,115],"(AED)":[38],"using":[39],"three":[40],"architectures:":[42],"(A)":[43],"style-dependent":[44,50],"layers;":[45],"(B)":[46],"mixed-style":[47],"output;":[48],"(C)":[49],"prompt.":[51],"In":[52],"this":[53],"framework,":[54],"both":[55],"the":[56,61,108],"verbatim":[57],"lexical":[58],"readable":[62],"various":[65],"can":[67,101],"be":[68],"generated":[69],"simultaneously":[70],"or":[71,78],"separately,":[72],"through":[73,131],"single":[75],"decoding":[76,80,118],"pass":[77],"multiple":[79],"passes":[81],"on-demand.":[82],"We":[83],"conduct":[84],"experiments":[85],"large-scale":[88],"AED-based":[89],"speech":[90],"system":[92],"trained":[93],"50k":[95],"hours":[96],"speech.":[97],"The":[98],"proposed":[99],"achieve":[102],"nearly":[103],"on-par":[104],"performance":[105],"compared":[106],"single-style":[109],"AED":[110],"significant":[112],"savings":[113],"footprint":[116],"cost.":[119],"Moreover,":[120],"it":[121],"provides":[122],"efficient":[124],"data":[125],"sharing":[126],"mechanism":[127],"across":[128],"knowledge":[132],"transfer.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}