{"id":"https://openalex.org/W4391021754","doi":"https://doi.org/10.1109/asru57964.2023.10389654","title":"PP-MET: A Real-World Personalized Prompt Based Meeting Transcription System","display_name":"PP-MET: A Real-World Personalized Prompt Based Meeting Transcription System","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021754","doi":"https://doi.org/10.1109/asru57964.2023.10389654"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389654","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389654","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/A5103221689","display_name":"Xiang Lyu","orcid":"https://orcid.org/0009-0006-4889-9678"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Lyu","raw_affiliation_strings":["Ximalaya Inc.,Shanghai,China","Ximalaya Inc., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,Shanghai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010183483","display_name":"Yuhang Cao","orcid":"https://orcid.org/0009-0008-3627-590X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhang Cao","raw_affiliation_strings":["Ximalaya Inc.,Shanghai,China","Ximalaya Inc., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,Shanghai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691702","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0001-9504-4273"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Ximalaya Inc.,Shanghai,China","Ximalaya Inc., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,Shanghai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004857861","display_name":"Jingjing Yin","orcid":"https://orcid.org/0000-0003-4843-613X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingjing Yin","raw_affiliation_strings":["Ximalaya Inc.,Shanghai,China","Ximalaya Inc., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,Shanghai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022888361","display_name":"Yuguang Yang","orcid":"https://orcid.org/0000-0002-9523-9254"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuguang Yang","raw_affiliation_strings":["Ximalaya Inc.,Shanghai,China","Ximalaya Inc., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,Shanghai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102606577","display_name":"Pengpeng Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengpeng Zou","raw_affiliation_strings":["Ximalaya Inc.,Shanghai,China","Ximalaya Inc., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,Shanghai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101250603","display_name":"Yanni Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanni Hu","raw_affiliation_strings":["Ximalaya Inc.,Shanghai,China","Ximalaya Inc., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,Shanghai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Lu","raw_affiliation_strings":["Ximalaya Inc.,Shanghai,China","Ximalaya Inc., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,Shanghai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., Shanghai, China","institution_ids":[]}]}],"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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980999827384949,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9980000257492065,"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":0.7810935974121094},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6935001015663147},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.679103672504425},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5916847586631775},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5439959764480591},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5164187550544739},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5163413286209106},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5062824487686157},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4852037727832794},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.46623513102531433},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.4622369408607483},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4497062563896179},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.41800931096076965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38203519582748413},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0748530924320221},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07024714350700378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7810935974121094},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6935001015663147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.679103672504425},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5916847586631775},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5439959764480591},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5164187550544739},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5163413286209106},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5062824487686157},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4852037727832794},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.46623513102531433},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.4622369408607483},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4497062563896179},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.41800931096076965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38203519582748413},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0748530924320221},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07024714350700378},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/asru57964.2023.10389654","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389654","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":22,"referenced_works":["https://openalex.org/W2148613904","https://openalex.org/W2164502538","https://openalex.org/W2194775991","https://openalex.org/W2884797218","https://openalex.org/W2969985801","https://openalex.org/W2997419692","https://openalex.org/W3015598461","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3097777922","https://openalex.org/W3105031100","https://openalex.org/W3140898556","https://openalex.org/W3196117288","https://openalex.org/W3198667862","https://openalex.org/W3198858272","https://openalex.org/W3207834622","https://openalex.org/W4221167707","https://openalex.org/W4224916733","https://openalex.org/W4297841877","https://openalex.org/W4372340947","https://openalex.org/W4391021535","https://openalex.org/W6801496586"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W4280634406"],"abstract_inverted_index":{"Speaker-attributed":[0],"automatic":[1],"speech":[2],"recognition":[3],"(SA-ASR)":[4],"improves":[5],"the":[6,124],"accuracy":[7],"and":[8,40,68,80,107,132],"applicability":[9],"of":[10,59,121],"multi-speaker":[11],"ASR":[12],"systems":[13],"in":[14,78,83,129],"real-world":[15,50],"scenarios":[16],"by":[17],"assigning":[18],"speaker":[19,34,36],"labels":[20],"to":[21,30],"transcribed":[22],"texts.":[23],"However,":[24],"SA-ASR":[25],"poses":[26],"unique":[27],"challenges":[28],"due":[29],"factors":[31],"such":[32],"as":[33,75],"overlap,":[35],"variability,":[37],"background":[38],"noise,":[39],"reverberation.":[41],"In":[42,87],"this":[43],"study,":[44],"we":[45,71,92],"propose":[46],"PP-MeT":[47],"system,":[48,56,62,91],"a":[49,60,76,119],"personalized":[51],"prompt":[52,77],"based":[53],"meeting":[54],"transcription":[55],"which":[57],"consists":[58],"clustering":[61],"target-speaker":[63,73],"voice":[64],"activity":[65],"detection":[66],"(TS-VAD),":[67],"TS-ASR.":[69],"Specifically,":[70],"utilize":[72],"embedding":[74],"TS-VAD":[79],"TS-ASR":[81],"modules":[82],"our":[84,102,116],"proposed":[85],"system.":[86],"constrast":[88],"with":[89,104],"previous":[90],"fully":[93],"leverage":[94],"pre-trained":[95],"models":[96],"for":[97],"system":[98,117],"initialization,":[99],"thereby":[100],"bestowing":[101],"approach":[103],"heightened":[105],"generalizability":[106],"precision.":[108],"Experiments":[109],"on":[110,123],"M2MeT2.0":[111],"Challenge":[112],"dataset":[113],"show":[114],"that":[115],"achieves":[118],"cp-CER":[120],"11.27%":[122],"test":[125],"set,":[126],"ranking":[127],"first":[128],"both":[130],"fixed":[131],"open":[133],"training":[134],"conditions.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}