{"id":"https://openalex.org/W11060696","doi":"https://doi.org/10.21437/eurospeech.2003-765","title":"Unsupervised speaker indexing using anchor models and automatic transcription of discussions","display_name":"Unsupervised speaker indexing using anchor models and automatic transcription of discussions","alternate_titles":[],"publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W11060696","doi":"https://doi.org/10.21437/eurospeech.2003-765","mag":"11060696"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-765","doi":"https://doi.org/10.21437/eurospeech.2003-765","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-765","pdf_url":null,"source":{"id":"https://openalex.org/S7407089324","display_name":"European Conference on Speech Communication and Technology (Eurospeech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},"parent_works":[{"id":"https://openalex.org/W4299468814","display_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","relationship":"volume","link_type":"volume"}],"lineage":["https://openalex.org/W11060696","https://openalex.org/W4299468814"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5066545740","display_name":"Yuya Akita","orcid":"https://orcid.org/0009-0003-3036-0883","observed_orcids":["https://orcid.org/0009-0003-3036-0883"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Yuya Akita","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296","observed_orcids":["https://orcid.org/0000-0002-2686-2296"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4228,"has_fulltext":false,"cited_by_count":17,"reviewed_by_count":0,"citation_normalized_percentile":{"value":0.89167466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":92},"biblio":{"volume":null,"issue":null,"first_page":"2985","last_page":"2988"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.000699999975040555,"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":9.999999747378752e-05,"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/anchor-model","display_name":"anchor models","score":0.984000027179718},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7300000190734863},{"id":"https://openalex.org/keywords/speaker-adaptation","display_name":"speaker adaptation","score":0.5770000219345093},{"id":"https://openalex.org/keywords/acoustic-model-adaptation","display_name":"acoustic model adaptation","score":0.3409999907016754}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8443301916122437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8417510986328125},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6387527585029602},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5756511688232422},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5701025128364563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5625004172325134},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.45929282903671265},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.433404803276062},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41435861587524414},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4123609960079193},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.40959250926971436},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3359518349170685},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06607967615127563},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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:10.21437/eurospeech.2003-765","doi":"https://doi.org/10.21437/eurospeech.2003-765","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-765","pdf_url":null,"source":{"id":"https://openalex.org/S7407089324","display_name":"European Conference on Speech Communication and Technology (Eurospeech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W85845213","https://openalex.org/W310645910","https://openalex.org/W1502984613","https://openalex.org/W1591300715","https://openalex.org/W1890250336","https://openalex.org/W2100336732","https://openalex.org/W2119603452","https://openalex.org/W2141262306"],"related_works":["https://openalex.org/W2063201546","https://openalex.org/W7097946846","https://openalex.org/W1900033650","https://openalex.org/W2133042973","https://openalex.org/W2136091744","https://openalex.org/W2130499067","https://openalex.org/W2186080853","https://openalex.org/W2365039010","https://openalex.org/W2143187963","https://openalex.org/W2915312149"],"abstract_inverted_index":{"We":[0,89,104],"present":[1],"unsupervised":[2],"speaker":[3,77,107],"indexing":[4,19,108],"combined":[5],"with":[6,37],"automatic":[7],"speech":[8,12,43],"recognition":[9],"(ASR)":[10],"for":[11,118],"archives":[13],"such":[14],"as":[15],"discussions.":[16],"Our":[17],"proposed":[18],"method":[20],"is":[21,54,65],"based":[22,33,85],"on":[23,34,86],"anchor":[24],"models,":[25],"by":[26,95],"which":[27],"we":[28,74],"define":[29],"a":[30,40,92],"feature":[31],"vector":[32],"the":[35,57,76,81,87,106,113],"similarity":[36],"speakers":[38],"of":[39,59,110,116],"large":[41],"scale":[42],"database.":[44],"Several":[45],"techniques":[46],"are":[47],"introduced":[48],"to":[49,67,80],"improve":[50],"discriminant":[51],"ability.":[52],"ASR":[53,117],"performed":[55],"using":[56],"results":[58],"this":[60],"indexing.":[61,88],"No":[62],"discussion":[63,120],"corpus":[64],"available":[66],"train":[68],"acoustic":[69,83],"and":[70,112],"language":[71,93],"models.":[72],"So":[73],"applied":[75],"adaptation":[78],"technique":[79],"baseline":[82],"model":[84,94],"also":[90],"constructed":[91],"merging":[96],"two":[97],"models":[98],"that":[99],"cover":[100],"different":[101],"linguistic":[102],"features.":[103],"achieved":[105],"accuracy":[109],"93%":[111],"significant":[114],"improvement":[115],"real":[119],"data.":[121]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W11060696","counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-22T12:46:00.618207","created_date":"2016-06-24T00:00:00"}
