{"id":"https://openalex.org/W1996198360","doi":"https://doi.org/10.1109/icassp.2014.6853568","title":"Filterbank slope based features for speaker diarization","display_name":"Filterbank slope based features for speaker diarization","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1996198360","doi":"https://doi.org/10.1109/icassp.2014.6853568","mag":"1996198360"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5084521938","display_name":"Srikanth Madikeri","orcid":"https://orcid.org/0000-0002-4361-784X"},"institutions":[{"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"],"is_corresponding":true,"raw_author_name":"Srikanth Madikeri","raw_affiliation_strings":["Idiap Research Institute, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"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"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herve Bourlard","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084521938"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":1.227,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83998686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"111","last_page":"115"},"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":0.9987999796867371,"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":0.9972000122070312,"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/filter-bank","display_name":"Filter bank","score":0.9245160818099976},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8200311660766602},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7239483594894409},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7168682813644409},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6485170125961304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6131700277328491},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5577495694160461},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.47250497341156006},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.43470993638038635},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.39878982305526733},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3848189115524292},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3489997386932373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.308435320854187},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08174967765808105},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.07838389277458191},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.058670997619628906}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.9245160818099976},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8200311660766602},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7239483594894409},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7168682813644409},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6485170125961304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6131700277328491},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5577495694160461},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.47250497341156006},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.43470993638038635},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39878982305526733},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3848189115524292},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3489997386932373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.308435320854187},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08174967765808105},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.07838389277458191},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.058670997619628906},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"},{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W187060452","https://openalex.org/W1595613095","https://openalex.org/W1787748203","https://openalex.org/W1963976507","https://openalex.org/W1980148047","https://openalex.org/W1992991228","https://openalex.org/W2034329102","https://openalex.org/W2069976350","https://openalex.org/W2081074144","https://openalex.org/W2098726438","https://openalex.org/W2099111195","https://openalex.org/W2106015547","https://openalex.org/W2106780157","https://openalex.org/W2125446021","https://openalex.org/W2148154194","https://openalex.org/W2153994037","https://openalex.org/W2154278880","https://openalex.org/W2156255174","https://openalex.org/W2170415762","https://openalex.org/W2210387432","https://openalex.org/W2338994564","https://openalex.org/W6635548358"],"related_works":["https://openalex.org/W2766680336","https://openalex.org/W2133320490","https://openalex.org/W4289830142","https://openalex.org/W3150393935","https://openalex.org/W1497065097","https://openalex.org/W2125446021","https://openalex.org/W1963976507","https://openalex.org/W2980055100","https://openalex.org/W2186790562","https://openalex.org/W2186375278"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"filterbank":[3,19,69],"slope":[4,20],"based":[5,13,21],"features":[6,22,145,161],"are":[7,89,108,152,162],"applied":[8],"to":[9,34,37,44,74,91],"the":[10,27,49,76,111,137,157],"Information":[11],"Bottleneck":[12],"system":[14],"for":[15,129],"speaker":[16,30,52,57,96],"diarization.":[17],"The":[18,62,105,140],"have":[23],"shown":[24,90],"promise":[25],"in":[26,48],"context":[28,50],"of":[29,51,123,159],"recognition":[31],"systems":[32],"owing":[33],"their":[35,46],"ability":[36],"emphasize":[38],"formants.":[39],"Hence,":[40],"it":[41],"is":[42,59,64,127,146],"proposed":[43],"study":[45],"use":[47],"diarization":[53],"as":[54],"well,":[55],"where":[56],"discrimination":[58,97],"equally":[60],"important.":[61],"feature":[63,106],"explored":[65],"using":[66],"two":[67],"different":[68],"arrangements,":[70],"linear":[71],"and":[72,81,115,125,131,149],"Mel,":[73],"form":[75],"Linear":[77],"Filterbank":[78,83],"Slope":[79,84],"(LFS)":[80],"Mel":[82],"(MFS),":[85],"respectively.":[86],"Both":[87],"arrangements":[88],"be":[92],"inherently":[93],"better":[94],"at":[95],"compared":[98,135],"with":[99,136,142],"MFCC":[100],"(Mel":[101],"Frequency":[102],"Cepstral":[103],"Co-efficients).":[104],"streams":[107],"tested":[109],"on":[110,156],"NIST":[112],"RT06,":[113],"07":[114],"09":[116],"datasets.":[117],"A":[118],"best":[119],"case":[120],"relative":[121],"improvement":[122],"22.1%":[124],"37.1%":[126],"observed":[128],"LFS":[130],"MFS,":[132],"respectively,":[133],"when":[134],"MFCC-based":[138],"baseline.":[139],"combination":[141],"time":[143],"domain":[144],"also":[147],"studied":[148],"further":[150],"improvements":[151],"observed.":[153],"Finally,":[154],"results":[155],"fusion":[158],"multiple":[160],"presented.":[163]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}