{"id":"https://openalex.org/W1493299544","doi":"https://doi.org/10.1109/icassp.2003.1202312","title":"Phase autocorrelation (PAC) derived robust speech features","display_name":"Phase autocorrelation (PAC) derived robust speech features","publication_year":2003,"publication_date":"2003-12-22","ids":{"openalex":"https://openalex.org/W1493299544","doi":"https://doi.org/10.1109/icassp.2003.1202312","mag":"1493299544"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1202312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202312","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/82801","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053319645","display_name":"Shajith Ikbal","orcid":null},"institutions":[{"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"]},{"id":"https://openalex.org/I4210158120","display_name":"Swiss Epilepsy Center","ror":"https://ror.org/05xnnea38","country_code":"CH","type":"other","lineage":["https://openalex.org/I4210158120"]},{"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":"S. Ikbal","raw_affiliation_strings":["EPF Lausanne, Lausanne, Switzerland","IDIAP, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"EPF Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I4210158120","https://openalex.org/I5124864"]},{"raw_affiliation_string":"IDIAP, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017720802","display_name":"Hemant Misra","orcid":"https://orcid.org/0000-0002-8179-4441"},"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":false,"raw_author_name":"H. Misra","raw_affiliation_strings":["IDIAP, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"IDIAP, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108291827","display_name":"H. Bourlard","orcid":null},"institutions":[{"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"]},{"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/I4210158120","display_name":"Swiss Epilepsy Center","ror":"https://ror.org/05xnnea38","country_code":"CH","type":"other","lineage":["https://openalex.org/I4210158120"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"H. Bourlard","raw_affiliation_strings":["EPF Lausanne, Lausanne, Switzerland","IDIAP, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"EPF Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I4210158120","https://openalex.org/I5124864"]},{"raw_affiliation_string":"IDIAP, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053319645"],"corresponding_institution_ids":["https://openalex.org/I4210158120","https://openalex.org/I5124864","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":9.3279,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.98956781,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2","issue":null,"first_page":"II","last_page":"133"},"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":0.9969000220298767,"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/autocorrelation","display_name":"Autocorrelation","score":0.9234359264373779},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7846107482910156},{"id":"https://openalex.org/keywords/autocorrelation-technique","display_name":"Autocorrelation technique","score":0.7058665752410889},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6208468079566956},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5720668435096741},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5623431205749512},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5468366742134094},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5149832367897034},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4901922345161438},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4853338301181793},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.41580063104629517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35469692945480347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33766812086105347},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.23282268643379211},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.23124510049819946},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09280511736869812},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.08446434140205383}],"concepts":[{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.9234359264373779},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7846107482910156},{"id":"https://openalex.org/C183223151","wikidata":"https://www.wikidata.org/wiki/Q4826228","display_name":"Autocorrelation technique","level":3,"score":0.7058665752410889},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6208468079566956},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5720668435096741},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5623431205749512},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5468366742134094},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5149832367897034},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4901922345161438},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4853338301181793},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.41580063104629517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35469692945480347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33766812086105347},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.23282268643379211},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.23124510049819946},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09280511736869812},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.08446434140205383},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":5,"locations":[{"id":"doi:10.1109/icassp.2003.1202312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202312","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.5699","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.5699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/~ikbal/LATEST/PUB/ikbal_pac_icassp03.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.7.4882","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.7.4882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.idiap.ch/pub/reports/2002/rr02-38.ps.gz","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:82801","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82801","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:82948","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82948","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:82801","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82801","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W204308143","https://openalex.org/W1553004968","https://openalex.org/W1560013842","https://openalex.org/W2069501481","https://openalex.org/W2128653836","https://openalex.org/W2137075158","https://openalex.org/W3094114204","https://openalex.org/W4249058433","https://openalex.org/W6608245754","https://openalex.org/W6632891567"],"related_works":["https://openalex.org/W174653542","https://openalex.org/W2181440403","https://openalex.org/W2060952610","https://openalex.org/W1976500589","https://openalex.org/W2060141217","https://openalex.org/W1986851479","https://openalex.org/W2014157823","https://openalex.org/W2128717546","https://openalex.org/W2085876421","https://openalex.org/W2130417215"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,12,67,75,96],"new":[3,13],"class":[4],"of":[5,15,23,32,78,98,158],"noise":[6,108],"robust":[7,118],"acoustic":[8],"features":[9,166],"derived":[10],"from":[11],"measure":[14,97],"autocorrelation,":[16],"and":[17,44,144],"explicitly":[18],"exploiting":[19],"the":[20,24,57,87,90,110,127,136,159],"phase":[21],"variation":[22],"speech":[25],"signal":[26,61],"frame":[27],"over":[28],"time.":[29],"This":[30,121],"family":[31],"features,":[33,40,56],"referred":[34],"to":[35,115,119],"as":[36,74,95],"\"phase":[37],"autocorrelation\"":[38],"(PAC)":[39],"include":[41],"PAC":[42,45,85],"spectrum":[43],"MFCC":[46],"(Mel-frequency":[47],"cepstral":[48],"coefficient),":[49],"among":[50],"others.":[51],"In":[52,82,156],"regular":[53],"autocorrelation":[54],"based":[55],"correlation":[58],"between":[59,89],"two":[60,80,91],"segments":[62],"(signal":[63],"vectors),":[64],"separated":[65],"by":[66,107,126],"particular":[68],"time":[69],"interval":[70],"k,":[71],"is":[72,93,103,122],"calculated":[73],"dot":[76,101],"product":[77,102],"these":[79],"vectors.":[81],"our":[83],"proposed":[84],"approach,":[86],"angle":[88],"vectors":[92],"used":[94],"correlation.":[99],"Since":[100],"usually":[104],"more":[105,117],"affected":[106],"than":[109],"angle,":[111],"PAC-features":[112],"are":[113],"expected":[114],"be":[116],"noise.":[120],"indeed":[123],"significantly":[124],"confirmed":[125],"presented":[128],"experimental":[129],"results.":[130],"The":[131],"experiments":[132],"were":[133,151],"conducted":[134],"on":[135,140],"Numbers":[137],"95":[138],"database,":[139],"which":[141],"\"stationary\"":[142],"(car)":[143],"\"non":[145],"-stationary\"":[146],"(factory)":[147],"Noisex":[148],"92":[149],"noises":[150],"added":[152],"with":[153],"varying":[154],"SNR.":[155],"most":[157],"cases,":[160],"without":[161],"any":[162],"specific":[163],"tuning,":[164],"PAC-MFCC":[165],"perform":[167],"better.":[168]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
