{"id":"https://openalex.org/W2181212125","doi":"https://doi.org/10.1109/waspaa.2015.7336928","title":"Single-channel speaker diarization based on spatial features","display_name":"Single-channel speaker diarization based on spatial features","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2181212125","doi":"https://doi.org/10.1109/waspaa.2015.7336928","mag":"2181212125"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2015.7336928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2015.7336928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5042482531","display_name":"Mathieu Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mathieu Hu","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060097629","display_name":"Pablo Peso Parada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142256","display_name":"Nuance Communications (United Kingdom)","ror":"https://ror.org/03ae66d75","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210125787","https://openalex.org/I4210142256"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pablo Peso Parada","raw_affiliation_strings":["Voicemail-To-Text Research, Nuance Communications Inc., Marlow, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Voicemail-To-Text Research, Nuance Communications Inc., Marlow, UK","institution_ids":["https://openalex.org/I4210142256"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108774400","display_name":"Dushyant Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142256","display_name":"Nuance Communications (United Kingdom)","ror":"https://ror.org/03ae66d75","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210125787","https://openalex.org/I4210142256"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dushyant Sharma","raw_affiliation_strings":["Voicemail-To-Text Research, Nuance Communications Inc., Marlow, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Voicemail-To-Text Research, Nuance Communications Inc., Marlow, UK","institution_ids":["https://openalex.org/I4210142256"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062526199","display_name":"Simon Doclo","orcid":"https://orcid.org/0000-0002-3392-2381"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]},{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Doclo","raw_affiliation_strings":["Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4AII, University of Oldenburg, Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4AII, University of Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375","https://openalex.org/I129877168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073284331","display_name":"Toon van Waterschoot","orcid":"https://orcid.org/0000-0002-6323-7350"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Toon van Waterschoot","raw_affiliation_strings":["Dept. of Electrical Engineering (ESAT-STADIUSIETC), KU Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering (ESAT-STADIUSIETC), KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004899548","display_name":"Mike Brookes","orcid":"https://orcid.org/0000-0001-7105-4936"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mike Brookes","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7398,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8543332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"15","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.9043546915054321},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7920687198638916},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6957207322120667},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6701368689537048},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5867608189582825},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5185092687606812},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.510230302810669},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5095577239990234},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4699811041355133},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.43869689106941223},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17855730652809143},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09112441539764404},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.05849382281303406}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9043546915054321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7920687198638916},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6957207322120667},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6701368689537048},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5867608189582825},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5185092687606812},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.510230302810669},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5095577239990234},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4699811041355133},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.43869689106941223},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17855730652809143},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09112441539764404},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.05849382281303406},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa.2015.7336928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2015.7336928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/522726","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/bitstream/123456789/522726/2/15-137.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WASPAA 2015, New Paltz, NY, 18-21 October 2015","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W3189630","https://openalex.org/W304834817","https://openalex.org/W1686946872","https://openalex.org/W1963976507","https://openalex.org/W1978681480","https://openalex.org/W1989314204","https://openalex.org/W2081074144","https://openalex.org/W2096465424","https://openalex.org/W2103723258","https://openalex.org/W2118313846","https://openalex.org/W2130722890","https://openalex.org/W2148613904","https://openalex.org/W2157287565","https://openalex.org/W2159591770","https://openalex.org/W2162607306","https://openalex.org/W2172491908","https://openalex.org/W2296434735","https://openalex.org/W2979454998","https://openalex.org/W6610843619","https://openalex.org/W6637108112","https://openalex.org/W6674535885","https://openalex.org/W6675471587","https://openalex.org/W6677982106","https://openalex.org/W6683324433"],"related_works":["https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W2206035908","https://openalex.org/W4389082013","https://openalex.org/W1879255185","https://openalex.org/W1977167953","https://openalex.org/W2162158162","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W4247736853"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1],"has":[2],"gained":[3],"much":[4],"importance":[5],"over":[6],"the":[7,40],"past":[8],"five":[9],"years":[10],"in":[11],"helping":[12],"overcome":[13],"key":[14],"challenges":[15],"faced":[16],"by":[17,69],"automatic":[18],"meeting":[19],"transcription":[20],"systems.":[21,78],"Current":[22],"state-of-the-art":[23],"algorithms":[24],"can":[25],"only":[26],"utilize":[27],"spatial":[28,49],"information":[29,50],"when":[30,71],"multi-microphone":[31],"recordings":[32,54],"are":[33],"available.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38],"propose":[39],"novel":[41],"use":[42],"of":[43,48],"reverberation":[44],"as":[45],"a":[46],"source":[47],"obtained":[51],"from":[52],"single-channel":[53,77],"to":[55,64],"perform":[56],"speaker":[57,66],"diarization.":[58],"The":[59],"proposed":[60],"system":[61],"is":[62],"shown":[63],"reduce":[65],"classification":[67],"errors":[68],"34%":[70],"compared":[72],"with":[73],"current":[74],"MFCC":[75],"based":[76]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}