{"id":"https://openalex.org/W2159104102","doi":"https://doi.org/10.1109/mmsp.2008.4665062","title":"Light weight mobile device targeted speaker clustering algorithm","display_name":"Light weight mobile device targeted speaker clustering algorithm","publication_year":2008,"publication_date":"2008-10-01","ids":{"openalex":"https://openalex.org/W2159104102","doi":"https://doi.org/10.1109/mmsp.2008.4665062","mag":"2159104102"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2008.4665062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2008.4665062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE 10th Workshop on Multimedia Signal Processing","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/A5042764084","display_name":"Olli Vuorinen","orcid":null},"institutions":[{"id":"https://openalex.org/I87653560","display_name":"VTT Technical Research Centre of Finland","ror":"https://ror.org/04b181w54","country_code":"FI","type":"nonprofit","lineage":["https://openalex.org/I4210089493","https://openalex.org/I87653560"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Olli Vuorinen","raw_affiliation_strings":["VTT Technical Research Center of Finland, Oulu, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VTT Technical Research Center of Finland, Oulu, Finland","institution_ids":["https://openalex.org/I87653560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087629198","display_name":"Tommi Lahti","orcid":null},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tommi Lahti","raw_affiliation_strings":["Nokia Research Center, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nokia Research Center, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023800350","display_name":"Satu-Marja M\u00e4kel\u00e4","orcid":"https://orcid.org/0000-0003-1601-0660"},"institutions":[{"id":"https://openalex.org/I87653560","display_name":"VTT Technical Research Centre of Finland","ror":"https://ror.org/04b181w54","country_code":"FI","type":"nonprofit","lineage":["https://openalex.org/I4210089493","https://openalex.org/I87653560"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Satu-Marja Makela","raw_affiliation_strings":["VTT Technical Research Center of Finland, Oulu, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VTT Technical Research Center of Finland, Oulu, Finland","institution_ids":["https://openalex.org/I87653560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076850081","display_name":"Johannes Peltola","orcid":"https://orcid.org/0000-0002-6248-152X"},"institutions":[{"id":"https://openalex.org/I87653560","display_name":"VTT Technical Research Centre of Finland","ror":"https://ror.org/04b181w54","country_code":"FI","type":"nonprofit","lineage":["https://openalex.org/I4210089493","https://openalex.org/I87653560"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Johannes Peltola","raw_affiliation_strings":["VTT Technical Research Center of Finland, Oulu, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VTT Technical Research Center of Finland, Oulu, Finland","institution_ids":["https://openalex.org/I87653560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1407,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80358423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"41","issue":null,"first_page":"131","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},{"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.8436892032623291},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7626022696495056},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5981132388114929},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.5829387903213501},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48626458644866943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4646818935871124},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3639897108078003},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32282114028930664}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8436892032623291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7626022696495056},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5981132388114929},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.5829387903213501},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48626458644866943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4646818935871124},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3639897108078003},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32282114028930664}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2008.4665062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2008.4665062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE 10th Workshop on Multimedia Signal Processing","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":8,"referenced_works":["https://openalex.org/W21391682","https://openalex.org/W1482605500","https://openalex.org/W2009049512","https://openalex.org/W2115717467","https://openalex.org/W2143714442","https://openalex.org/W2148671289","https://openalex.org/W2171700247","https://openalex.org/W6682409218"],"related_works":["https://openalex.org/W1566728629","https://openalex.org/W1502087262","https://openalex.org/W2617987378","https://openalex.org/W2509820422","https://openalex.org/W3122388856","https://openalex.org/W2107617395","https://openalex.org/W2626271282","https://openalex.org/W2999695592","https://openalex.org/W2963415778","https://openalex.org/W2058458419"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"a":[5,43],"novel":[6],"light":[7,44],"weight":[8,45],"speaker":[9,34,39,89,120,129],"clustering":[10,46,121],"algorithm":[11,66,82,122],"based":[12],"on":[13],"the":[14,58,62,107],"Bayesian":[15],"information":[16],"criterion":[17,64],"(BIC).":[18],"Algorithm":[19],"utilises":[20],"BIC":[21],"profiles,":[22],"which":[23,91],"were":[24],"earlier":[25],"used":[26],"for":[27,88,128],"false":[28],"alarm":[29],"compensation":[30],"(FAC)":[31],"in":[32,57,65,78,132],"our":[33,118],"change":[35],"detector":[36],"(SCD).":[37],"Proposed":[38],"segmentation":[40,130],"followed":[41],"by":[42],"is":[47,92,123],"targeted":[48],"to":[49,69,97],"segment":[50,101],"and":[51,126],"label":[52],"mobile":[53,133],"device":[54,59],"recordings":[55],"directly":[56],"itself.":[60],"Thus":[61],"main":[63],"design":[67],"was":[68,104,111],"maintain":[70],"high":[71],"detection":[72],"accuracy":[73],"while":[74],"keeping":[75],"computational":[76],"costs":[77],"low":[79],"level.":[80],"Clustering":[81],"gave":[83],"F-score":[84],"performance":[85,103],"of":[86,109],"0.90":[87],"segmentation,":[90],"29%":[93],"relative":[94],"improvement":[95],"compared":[96],"baseline":[98],"results.":[99],"Speaker":[100],"labelling":[102],"88%,":[105],"when":[106],"number":[108],"speakers":[110],"undetermined.":[112],"The":[113],"experimental":[114],"results":[115],"indicate":[116],"that":[117],"unsupervised":[119],"sufficiently":[124],"effective":[125],"efficient":[127],"applications":[131],"devices.":[134]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}