{"id":"https://openalex.org/W4408352003","doi":"https://doi.org/10.1109/icassp49660.2025.10888002","title":"Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition with Speaker Tokens","display_name":"Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition with Speaker Tokens","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352003","doi":"https://doi.org/10.1109/icassp49660.2025.10888002"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888002","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":"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/A5109644502","display_name":"Yosuke Kashiwagi","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yosuke Kashiwagi","raw_affiliation_strings":["Sony Group Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034216052","display_name":"Hayato Futami","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hayato Futami","raw_affiliation_strings":["Sony Group Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":["Sony Group Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047892839","display_name":"Siddhant Arora","orcid":"https://orcid.org/0000-0003-0375-496X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhant Arora","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02507762,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9745000004768372,"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":0.9745000004768372,"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":0.9624999761581421,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7601884603500366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7455230355262756},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6043667793273926},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.603891909122467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4651630222797394},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.412422239780426},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32389721274375916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7601884603500366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7455230355262756},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6043667793273926},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.603891909122467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4651630222797394},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.412422239780426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32389721274375916}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888002","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1904457459","https://openalex.org/W2007995029","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2739883972","https://openalex.org/W2786835190","https://openalex.org/W2800022361","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2963477857","https://openalex.org/W2963843276","https://openalex.org/W2964309797","https://openalex.org/W2972541922","https://openalex.org/W2981087920","https://openalex.org/W2982471419","https://openalex.org/W3024869864","https://openalex.org/W3094821064","https://openalex.org/W3097643313","https://openalex.org/W3143843080","https://openalex.org/W3154262773","https://openalex.org/W3178462146","https://openalex.org/W3196194966","https://openalex.org/W3205878676","https://openalex.org/W4226491018","https://openalex.org/W4297841877","https://openalex.org/W4372259971","https://openalex.org/W4381786045","https://openalex.org/W4385822683","https://openalex.org/W4391021779","https://openalex.org/W4392904451","https://openalex.org/W4392904528","https://openalex.org/W4392909760","https://openalex.org/W4402111259","https://openalex.org/W4402112082","https://openalex.org/W4402112539","https://openalex.org/W6668990524","https://openalex.org/W6777776875","https://openalex.org/W6853998256"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"In":[0],"many":[1],"real-world":[2],"scenarios,":[3],"such":[4],"as":[5],"meetings,":[6],"multiple":[7,47],"speakers":[8,85],"are":[9,59],"present":[10],"with":[11,34,80,126],"an":[12],"unknown":[13],"number":[14,83],"of":[15,84],"participants,":[16],"and":[17,56,116],"their":[18],"utterances":[19],"often":[20],"overlap.":[21],"We":[22],"address":[23],"these":[24,57],"multi-speaker":[25,78],"challenges":[26],"by":[27,40,61,87],"a":[28,108,117],"novel":[29],"attention-based":[30],"encoder-decoder":[31],"method":[32,99],"augmented":[33],"special":[35],"speaker":[36,41,53],"class":[37],"tokens":[38],"obtained":[39],"clustering.":[42],"During":[43],"inference,":[44],"we":[45],"select":[46],"recognition":[48],"hypotheses":[49,58,74],"conditioned":[50],"on":[51,67,91,113,122],"predicted":[52],"cluster":[54],"tokens,":[55],"merged":[60],"agglomerative":[62],"hierarchical":[63],"clustering":[64],"(AHC)":[65],"based":[66],"the":[68,77,81,92],"normalized":[69],"edit":[70],"distance.":[71],"The":[72],"clustered":[73],"result":[75],"in":[76,103],"transcriptions":[79],"appropriate":[82],"determined":[86],"AHC.":[88],"Our":[89],"experiments":[90],"LibriMix":[93],"dataset":[94],"demonstrate":[95],"that":[96],"our":[97],"proposed":[98],"was":[100],"particularly":[101],"effective":[102],"complex":[104],"3-mix":[105],"environments,":[106],"achieving":[107],"55%":[109],"relative":[110,119],"error":[111,120],"reduction":[112,121],"clean":[114],"data":[115,124],"36%":[118],"noisy":[123],"compared":[125],"conventional":[127],"serialized":[128],"output":[129],"training.":[130]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}