{"id":"https://openalex.org/W2010114458","doi":"https://doi.org/10.1109/slt.2014.7078608","title":"Artificial neural network features for speaker diarization","display_name":"Artificial neural network features for speaker diarization","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2010114458","doi":"https://doi.org/10.1109/slt.2014.7078608","mag":"2010114458"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/203865","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065571234","display_name":"Sree Harsha Yella","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH","GB"],"is_corresponding":true,"raw_author_name":"Sree Harsha Yella","raw_affiliation_strings":["Idiap Research Institute, Switzerland","Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Microsoft Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046802864","display_name":"Malcolm Slaney","orcid":"https://orcid.org/0000-0001-9733-4864"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Malcolm Slaney","raw_affiliation_strings":["Microsoft Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065571234"],"corresponding_institution_ids":["https://openalex.org/I4210164937","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":6.7656,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96716814,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"402","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9260197877883911},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7956433892250061},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7317186594009399},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7299534678459167},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.597032368183136},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5592406988143921},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5589185953140259},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5493419766426086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4334176778793335},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41975781321525574},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40691423416137695}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9260197877883911},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956433892250061},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7317186594009399},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7299534678459167},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.597032368183136},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5592406988143921},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5589185953140259},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5493419766426086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4334176778793335},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41975781321525574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40691423416137695},{"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/slt.2014.7078608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.679.7018","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.679.7018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.slaney.org/malcolm/Microsoft/Yella2014%28ANNSpeakerDiarization%29.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.994.218","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.994.218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://infoscience.epfl.ch/record/203865/files/Yella_SLT_2014.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:203865","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/203865","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:203865","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/203865","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W40124310","https://openalex.org/W1556474518","https://openalex.org/W1591607137","https://openalex.org/W1787748203","https://openalex.org/W1876378865","https://openalex.org/W2069448468","https://openalex.org/W2081074144","https://openalex.org/W2098726438","https://openalex.org/W2115599677","https://openalex.org/W2125336414","https://openalex.org/W2159591770","https://openalex.org/W2168175751","https://openalex.org/W2170695863","https://openalex.org/W2171700247","https://openalex.org/W2289985966","https://openalex.org/W2338994564","https://openalex.org/W2497516627","https://openalex.org/W3186851455","https://openalex.org/W6601610752","https://openalex.org/W6638325099","https://openalex.org/W6639431793","https://openalex.org/W6659344013"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W2185075503","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2162158162","https://openalex.org/W2019475500"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,138,167],"finds":[2],"contiguous":[3],"speaker":[4,14,57,79,137],"segments":[5,92],"in":[6,126,132,166],"an":[7,64,175],"audio":[8],"recording":[9],"and":[10,157],"clusters":[11],"them":[12],"by":[13],"identity,":[15],"without":[16],"any":[17],"a-priori":[18],"knowledge.":[19,180],"Diarization":[20],"is":[21,76,145],"typically":[22],"based":[23],"on":[24,139,147],"short-term":[25],"spectral":[26],"features":[27,36,107,131,159,172],"such":[28],"as":[29,121],"Mel-frequency":[30],"cepstral":[31],"coefficients":[32],"(MFCCs).":[33],"Though":[34],"these":[35,171],"carry":[37],"average":[38],"information":[39],"about":[40],"the":[41,56,95,105,117],"vocal":[42],"tract":[43],"characteristics":[44],"of":[45,104,150,155,179],"a":[46,72,83,101,111,133],"speaker,":[47],"they":[48],"are":[49,173],"also":[50],"susceptible":[51],"to":[52,55,70,86,162],"factors":[53],"unrelated":[54],"identity.":[58],"In":[59],"this":[60],"study,":[61],"we":[62],"propose":[63],"artificial":[65],"neural":[66],"network":[67],"(ANN)":[68],"architecture":[69],"learn":[71],"feature":[73],"transform":[74,103],"that":[75,108,170],"optimized":[77],"for":[78,136],"diarization.":[80],"We":[81,114],"train":[82],"multi-hidden-layer":[84],"ANN":[85,158],"judge":[87],"whether":[88],"two":[89],"given":[90],"speech":[91],"came":[93],"from":[94],"same":[96],"or":[97,125],"different":[98],"speakers,":[99],"using":[100],"shared":[102],"input":[106],"feeds":[109],"into":[110],"bottleneck":[112,118],"layer.":[113],"then":[115],"use":[116],"layer":[119],"activations":[120],"features,":[122],"either":[123],"alone":[124],"combination":[127,154],"with":[128],"baseline":[129],"MFCC":[130,156],"multistream":[134],"mode,":[135],"test":[140],"data.":[141],"The":[142],"resulting":[143],"system":[144],"evaluated":[146],"various":[148],"corpora":[149],"multi-party":[151],"meetings.":[152],"A":[153],"gives":[160],"up":[161],"14%":[163],"relative":[164],"reduction":[165],"error,":[168],"demonstrating":[169],"providing":[174],"additional":[176],"independent":[177],"source":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}