{"id":"https://openalex.org/W2394778886","doi":"https://doi.org/10.21437/interspeech.2012-424","title":"Overlapped speech detection in meeting using cross-channel spectral subtraction and spectrum similarity","display_name":"Overlapped speech detection in meeting using cross-channel spectral subtraction and spectrum similarity","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2394778886","doi":"https://doi.org/10.21437/interspeech.2012-424","mag":"2394778886"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-424","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100644510/ATD100000413/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021151396","display_name":"R. Yokoyama","orcid":"https://orcid.org/0000-0002-2278-9706"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryo Yokoyama","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, 152-8552, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, 152-8552, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063793244","display_name":"Yu Nasu","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu Nasu","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, 152-8552, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, 152-8552, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081629487","display_name":"Koichi Shinoda","orcid":"https://orcid.org/0000-0003-1095-3203"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Shinoda","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, 152-8552, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, 152-8552, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084374665","display_name":"Koji Iwano","orcid":"https://orcid.org/0000-0002-7373-5353"},"institutions":[{"id":"https://openalex.org/I185088104","display_name":"Tokyo City University","ror":"https://ror.org/04dt6bw53","country_code":"JP","type":"education","lineage":["https://openalex.org/I185088104"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koji Iwano","raw_affiliation_strings":["Faculty of Environmental and Information Studies, Tokyo City University, 224-8551, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Environmental and Information Studies, Tokyo City University, 224-8551, Japan","institution_ids":["https://openalex.org/I185088104"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021151396"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.2481,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61181247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1500","last_page":"1503"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9991999864578247,"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":0.9980000257492065,"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/speech-recognition","display_name":"Speech recognition","score":0.7019846439361572},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.6556891798973083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5905412435531616},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5779067277908325},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5415765047073364},{"id":"https://openalex.org/keywords/spectral-density","display_name":"Spectral density","score":0.4976668655872345},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.4847835898399353},{"id":"https://openalex.org/keywords/correlation-coefficient","display_name":"Correlation coefficient","score":0.47980883717536926},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.46086132526397705},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45776039361953735},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45645448565483093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39284464716911316},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3926772475242615},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36399808526039124},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25401008129119873},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.09485495090484619},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0814841091632843}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7019846439361572},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.6556891798973083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5905412435531616},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5779067277908325},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5415765047073364},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.4976668655872345},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.4847835898399353},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.47980883717536926},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.46086132526397705},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45776039361953735},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45645448565483093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39284464716911316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3926772475242615},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36399808526039124},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25401008129119873},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.09485495090484619},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0814841091632843},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-424","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50186482","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100644510","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100644510/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:t2r2.star.titech.ac.jp:50186482","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100644510","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100644510/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2394778886.pdf","grobid_xml":"https://content.openalex.org/works/W2394778886.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2020150184","https://openalex.org/W2098441927","https://openalex.org/W2111057910","https://openalex.org/W2119223798","https://openalex.org/W2128653836","https://openalex.org/W2139301611","https://openalex.org/W2162158162"],"related_works":["https://openalex.org/W2122030153","https://openalex.org/W2162449135","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2,49],"overlapped":[3],"speech":[4,8,33,74,98],"detection":[5],"method":[6,70],"for":[7,28],"recognition":[9],"and":[10,100],"speaker":[11,17],"diarization":[12],"of":[13,60,76,80,90],"meetings,":[14],"where":[15],"each":[16],"wears":[18],"a":[19,29,64,72],"lapel":[20],"microphone.Two":[21],"novel":[22],"features":[23],"are":[24],"utilized":[25],"as":[26],"inputs":[27],"GMM-based":[30],"detector.One":[31],"is":[32,48],"power":[34,42,99,101],"after":[35],"cross-channel":[36],"spectral":[37,51,61,102],"subtraction":[38],"which":[39,55,95],"reduces":[40],"the":[41,44,58,91],"from":[43],"other":[45,47],"speakers.The":[46,78],"amplitude":[50],"cosine":[52],"correlation":[53,59,104],"coefficient":[54],"effectively":[56],"extracts":[57],"components":[62],"in":[63],"rather":[65],"quiet":[66],"condition.We":[67],"evaluated":[68],"our":[69,81],"using":[71],"meeting":[73],"corpus":[75],"four":[77],"accuracy":[79],"proposed":[82],"method,":[83,93],"74.1%,":[84],"was":[85],"significantly":[86],"better":[87],"than":[88],"that":[89],"conventional":[92],"67.0%,":[94],"uses":[96],"raw":[97],"Pearson's":[103],"coefficient.":[105]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}