{"id":"https://openalex.org/W2060052977","doi":"https://doi.org/10.1109/ncc.2015.7084869","title":"Speaker change detection using excitation source and vocal tract system information","display_name":"Speaker change detection using excitation source and vocal tract system information","publication_year":2015,"publication_date":"2015-02-01","ids":{"openalex":"https://openalex.org/W2060052977","doi":"https://doi.org/10.1109/ncc.2015.7084869","mag":"2060052977"},"language":"en","primary_location":{"id":"doi:10.1109/ncc.2015.7084869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2015.7084869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Twenty First National Conference on Communications (NCC)","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/A5074442858","display_name":"Mousmita Sarma","orcid":"https://orcid.org/0000-0003-1757-0328"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]},{"id":"https://openalex.org/I138537684","display_name":"Gauhati University","ror":"https://ror.org/01ppj9r51","country_code":"IN","type":"education","lineage":["https://openalex.org/I138537684"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Mousmita Sarma","raw_affiliation_strings":["Department of Electronics and Communication Engineering, Gauhati University, Guwahati, Assam, India","TIC IIT Guwahati, Speechwarnet (I) Pvt. Ltd, Guwahati, Assam, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, Gauhati University, Guwahati, Assam, India","institution_ids":["https://openalex.org/I138537684"]},{"raw_affiliation_string":"TIC IIT Guwahati, Speechwarnet (I) Pvt. Ltd, Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068787484","display_name":"Sree Nilendra Gadre","orcid":null},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sree Nilendra Gadre","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022002245","display_name":"Biswajit Dev Sarma","orcid":null},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Biswajit Dev Sarma","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052129812","display_name":"S. R. Mahadeva Prasanna","orcid":"https://orcid.org/0000-0002-8135-7938"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. R. Mahadeva Prasanna","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074442858"],"corresponding_institution_ids":["https://openalex.org/I1317621060","https://openalex.org/I138537684"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.07888753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9976999759674072,"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":0.9703999757766724,"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/vocal-tract","display_name":"Vocal tract","score":0.9158345460891724},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7177902460098267},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6936500668525696},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6528433561325073},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.577121376991272},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5733700394630432},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5717892646789551},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.554973840713501},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5450407266616821},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5050285458564758},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49437761306762695},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46666640043258667},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46029385924339294},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4131518006324768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3904903829097748},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05582264065742493}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.9158345460891724},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7177902460098267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6936500668525696},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6528433561325073},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.577121376991272},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5733700394630432},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5717892646789551},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.554973840713501},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5450407266616821},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5050285458564758},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49437761306762695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46666640043258667},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46029385924339294},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4131518006324768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3904903829097748},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05582264065742493},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ncc.2015.7084869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2015.7084869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Twenty First National Conference on Communications (NCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W125260059","https://openalex.org/W192559706","https://openalex.org/W200199050","https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W1635512741","https://openalex.org/W1904447473","https://openalex.org/W1968491588","https://openalex.org/W2038086080","https://openalex.org/W2044591814","https://openalex.org/W2052269122","https://openalex.org/W2074394031","https://openalex.org/W2075662881","https://openalex.org/W2081074144","https://openalex.org/W2112844139","https://openalex.org/W2115619557","https://openalex.org/W2145540416","https://openalex.org/W2161939451","https://openalex.org/W2166980079","https://openalex.org/W3127686677","https://openalex.org/W6607848239","https://openalex.org/W6608100561","https://openalex.org/W6628802092","https://openalex.org/W6628911050"],"related_works":["https://openalex.org/W2100012411","https://openalex.org/W1482212662","https://openalex.org/W3162157266","https://openalex.org/W2162084437","https://openalex.org/W1997579527","https://openalex.org/W2102353451","https://openalex.org/W3044927199","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097"],"abstract_inverted_index":{"The":[0,37,52,75,98],"speaker":[1,53,72,95],"change":[2,54,73,96],"information":[3,22,41,70],"in":[4],"speech":[5,34,50,112,142,165],"is":[6,23,42,113,118,172],"due":[7],"to":[8,92,132,157],"both":[9],"vocal":[10,38],"tract":[11,39],"and":[12,64,85,115,143,147,167],"excitation":[13,20,183],"source":[14,21,184],"information.":[15],"In":[16],"this":[17],"work,":[18],"the":[19,30,49,94,122,129,152,155,176,182],"extracted":[24,43],"by":[25,44],"computing":[26,45],"cepstral":[27,46,108,179],"features":[28,47,109,180],"from":[29,48,57,111,116,141,181],"zero":[31],"frequency":[32],"filtered":[33],"(ZFFS)":[35],"signal.":[36,51],"system":[40],"evidences":[55,126],"obtained":[56,110],"these":[58],"two":[59,123],"feature":[60],"sets":[61,124],"are":[62,90,127,145,160],"combined":[63],"observed":[65],"that":[66],"they":[67],"contain":[68],"complementary":[69],"for":[71,186],"detection.":[74],"popular":[76],"distance":[77],"metric":[78],"based":[79,105,139],"algorithms,":[80],"Bayesian":[81],"Information":[82],"Criteria":[83],"(BIC)":[84],"Kullback":[86],"Leibler":[87],"Divergence":[88],"(KLD)":[89],"used":[91],"detect":[93],"evidences.":[97],"Miss":[99],"Detection":[100],"Rate":[101],"(MDR)":[102],"of":[103,125,137,170,178],"BIC":[104],"algorithm":[106,140],"using":[107],"24.18%":[114],"ZFFS":[117,144],"25.92%,":[119],"respectively.":[120],"When":[121],"combined,":[128],"MDR":[130,136,156,171],"reduces":[131,154],"15.89%.":[133],"Similarly,":[134],"individual":[135],"KLD":[138],"32.24%":[146],"45.17%,":[148],"respectively,":[149],"where":[150],"as":[151],"combination":[153],"19.67%.":[158],"Experiments":[159],"also":[161],"performed":[162],"with":[163],"noisy":[164],"signal":[166,185],"similar":[168],"reduction":[169],"observed.":[173],"This":[174],"demonstrates":[175],"usefulness":[177],"reducing":[187],"MDR.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}