{"id":"https://openalex.org/W90546637","doi":"https://doi.org/10.21437/interspeech.2009-271","title":"Speaker diarization for meeting room audio","display_name":"Speaker diarization for meeting room audio","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W90546637","doi":"https://doi.org/10.21437/interspeech.2009-271","mag":"90546637"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-271","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5100813843","display_name":"Hanwu Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hanwu Sun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050008407","display_name":"Tin Lay Nwe","orcid":"https://orcid.org/0000-0003-1111-580X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tin Lay Nwe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Agency for Science, Technology and Research, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research, Singapore, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Agency for Science, Technology and Research"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research","institution_ids":["https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100813843"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.2875,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.97535107,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"900","last_page":"903"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9373465776443481},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7811571955680847},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7281346321105957},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6929545402526855},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6705973148345947},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6531515121459961},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6373844146728516},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.48372963070869446},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.4479871094226837},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43327203392982483},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.42799222469329834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39810773730278015},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34568122029304504},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1358175277709961},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08217263221740723}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9373465776443481},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7811571955680847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281346321105957},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6929545402526855},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6705973148345947},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6531515121459961},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6373844146728516},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.48372963070869446},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.4479871094226837},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43327203392982483},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.42799222469329834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39810773730278015},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34568122029304504},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1358175277709961},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08217263221740723},{"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/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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2009-271","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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":9,"referenced_works":["https://openalex.org/W41021157","https://openalex.org/W1548779692","https://openalex.org/W1800068500","https://openalex.org/W2040023846","https://openalex.org/W2041823554","https://openalex.org/W2106015547","https://openalex.org/W2114863372","https://openalex.org/W2216290105","https://openalex.org/W2338994564"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1977167953","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W107154053"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,102],"speaker":[4,37,79,111],"diarization":[5,112],"system":[6,29,100],"in":[7,24],"2007":[8],"NIST":[9],"Rich":[10],"Transcription":[11],"(RT07)":[12],"Meeting":[13],"Recognition":[14],"Evaluation":[15],"for":[16,96,108],"the":[17,47,65,77],"task":[18],"of":[19,46,56,106],"Multiple":[20],"Distant":[21],"Microphone":[22],"(MDM)":[23],"meeting":[25],"room":[26],"scenarios.":[27],"The":[28,42,99],"includes":[30],"three":[31],"major":[32],"modules:":[33],"data":[34,43,49],"preparation,":[35],"initial":[36,66,78],"clustering":[38,88],"and":[39,52,59],"cluster":[40,97],"purification/merging.":[41],"preparation":[44],"consists":[45],"raw":[48],"Wiener":[50],"filtering":[51],"beamforming,":[53],"Time":[54],"Difference":[55],"Arrival":[57],"estimate":[58],"speech":[60],"activity":[61],"detection.":[62],"Based":[63],"on":[64],"processed":[67],"data,":[68],"two-stage":[69],"histogram":[70],"quantization":[71],"has":[72],"been":[73],"used":[74],"to":[75],"perform":[76],"clustering.":[80],"A":[81],"modified":[82],"purification":[83],"strategy":[84],"via":[85],"high-order":[86],"GMM":[87],"method":[89],"is":[90,94],"proposed.":[91],"BIC":[92],"criterion":[93],"applied":[95],"merging.":[98],"achieves":[101],"competitive":[103],"overall":[104],"DER":[105],"8.31%":[107],"RT07":[109],"MDM":[110],"task.":[113]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}