{"id":"https://openalex.org/W2130950425","doi":"https://doi.org/10.21437/interspeech.2010-140","title":"Improving monaural speaker identification by double-talk detection","display_name":"Improving monaural speaker identification by double-talk detection","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W2130950425","doi":"https://doi.org/10.21437/interspeech.2010-140","mag":"2130950425"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-140","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/ws/files/62679649/interspeech2010.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023224767","display_name":"Rahim Saeidi","orcid":"https://orcid.org/0000-0002-9084-0091"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rahim Saeidi","raw_affiliation_strings":["Department of Computer Science, Speech and Image Processing Unit (SIPU), Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Speech and Image Processing Unit (SIPU), Finland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088787456","display_name":"Pejman Mowlaee","orcid":"https://orcid.org/0000-0003-0136-8002"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pejman Mowlaee","raw_affiliation_strings":["Institut for Elektroniske Systemer"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut for Elektroniske Systemer","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["Department of Computer Science, Speech and Image Processing Unit (SIPU), Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Speech and Image Processing Unit (SIPU), Finland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Institut for Elektroniske Systemer"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut for Elektroniske Systemer","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026658144","display_name":"Mads Gr\u00e6sb\u00f8ll Christensen","orcid":"https://orcid.org/0000-0003-3586-7969"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mads Gr\u00e6sb\u00f8ll Christensen","raw_affiliation_strings":["Institut for Arkitektur og Medieteknologi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut for Arkitektur og Medieteknologi","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103115969","display_name":"S\u00f8ren Holdt Jensen","orcid":"https://orcid.org/0000-0002-1050-470X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00f8ren Holdt Jensen","raw_affiliation_strings":["Institut for Elektroniske Systemer"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut for Elektroniske Systemer","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037846871","display_name":"Pasi Fr\u00e4nti","orcid":"https://orcid.org/0000-0002-9554-2827"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pasi Fr\u00e4nti","raw_affiliation_strings":["Department of Computer Science, Speech and Image Processing Unit (SIPU), Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Speech and Image Processing Unit (SIPU), Finland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1069","last_page":"1072"},"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":0.9990000128746033,"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-identification","display_name":"Speaker identification","score":0.8212441205978394},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.8081145286560059},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7578964233398438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7390192151069641},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7317680716514587},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6754504442214966},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6723768711090088},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.590243935585022},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5700031518936157},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5570867657661438},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4511144459247589},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4411331117153168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42609164118766785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41206106543540955},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08089479804039001}],"concepts":[{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.8212441205978394},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8081145286560059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7578964233398438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7390192151069641},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7317680716514587},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6754504442214966},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6723768711090088},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.590243935585022},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5700031518936157},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5570867657661438},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4511144459247589},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4411331117153168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42609164118766785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41206106543540955},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08089479804039001},{"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2010-140","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/9d30e627-a4d8-4026-a583-86e5c3046d47","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/9d30e627-a4d8-4026-a583-86e5c3046d47","pdf_url":"https://vbn.aau.dk/ws/files/62679649/interspeech2010.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Saeidi, R, Mowlaee, P, Kinnunen, T, Tan, Z-H, Christensen, M G, Jensen, S H & Fr\u00e4nti, P 2010, 'Improving Monaural Speaker Identification by Double-Talk Detection', Proceedings of the International Conference on Spoken Language Processing, pp. 1069-1072. < http://cs.joensuu.fi/pages/saeidi/Interspeech2010_1.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.178.7710","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.178.7710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.joensuu.fi/pages/tkinnu/webpage/pdf/Monaural_IS2010.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.904.7652","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.904.7652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vbn.aau.dk/files/62679649/interspeech2010.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/9d30e627-a4d8-4026-a583-86e5c3046d47","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/9d30e627-a4d8-4026-a583-86e5c3046d47","pdf_url":"https://vbn.aau.dk/ws/files/62679649/interspeech2010.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Saeidi, R, Mowlaee, P, Kinnunen, T, Tan, Z-H, Christensen, M G, Jensen, S H & Fr\u00e4nti, P 2010, 'Improving Monaural Speaker Identification by Double-Talk Detection', Proceedings of the International Conference on Spoken Language Processing, pp. 1069-1072. < http://cs.joensuu.fi/pages/saeidi/Interspeech2010_1.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2130950425.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W44831635","https://openalex.org/W1865095259","https://openalex.org/W2015143272","https://openalex.org/W2041823554","https://openalex.org/W2079362249","https://openalex.org/W2098769365","https://openalex.org/W2106934198","https://openalex.org/W2147147599","https://openalex.org/W2148249824","https://openalex.org/W2149648698","https://openalex.org/W2154278880","https://openalex.org/W2541366197"],"related_works":["https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W4401661962","https://openalex.org/W4247736853","https://openalex.org/W1521049138","https://openalex.org/W2129090883","https://openalex.org/W2997340161","https://openalex.org/W2972577568","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,17,40,45],"novel":[4],"approach":[5,36],"to":[6,23,79],"improve":[7],"monoau-ral":[8],"speaker":[9,48,60,83],"identification":[10,49,61],"where":[11],"two":[12],"speakers":[13,29],"are":[14],"present":[15],"in":[16,30],"single-microphone":[18],"recording.":[19],"The":[20,34],"goal":[21],"is":[22,37],"identify":[24],"both":[25],"of":[26,39],"the":[27,31,55,59,70],"underlying":[28],"given":[32],"mixture.":[33],"proposed":[35],"composed":[38],"double-talk":[41,56,85],"detector":[42,57],"(DTD)":[43],"as":[44],"pre-processor":[46],"and":[47],"back-end.":[50],"We":[51],"demonstrate":[52],"that":[53,68],"including":[54,69],"improves":[58,72],"accuracy.":[62],"Experiments":[63],"on":[64],"GRID":[65],"corpus":[66],"show":[67],"DTD":[71],"average":[73],"recognition":[74],"accuracy":[75],"from":[76],"96.53":[77],"%":[78],"97.43%.":[80],"Index":[81],"Terms:":[82],"identification,":[84],"detection,":[86],"single-channel,":[87],"Gaussian":[88],"mixture":[89],"models.":[90]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}