{"id":"https://openalex.org/W2295778365","doi":"https://doi.org/10.21437/interspeech.2013-694","title":"Improving robustness to compressed speech in speaker recognition","display_name":"Improving robustness to compressed speech in speaker recognition","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2295778365","doi":"https://doi.org/10.21437/interspeech.2013-694","mag":"2295778365"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-694","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5060382325","display_name":"Mitchell McLaren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mitchell McLaren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016431949","display_name":"Victor Abrash","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Victor Abrash","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025265147","display_name":"Martin Graciarena","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Graciarena","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101648572","display_name":"Yun Lei","orcid":"https://orcid.org/0000-0003-4572-6078"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034181217","display_name":"Jan Pe\u0161\u00e1n","orcid":"https://orcid.org/0000-0002-9655-1143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Pe\u0161\u00e1n","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4706,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90937634,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3698","last_page":"3702"},"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":0.9886999726295471,"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/computer-science","display_name":"Computer science","score":0.8299692273139954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8232780694961548},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7961151599884033},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7223321199417114},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.557889997959137},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5451913475990295},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4880332052707672},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46900081634521484},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4350980520248413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35936659574508667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3558896780014038},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2551552951335907},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08315977454185486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299692273139954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8232780694961548},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7961151599884033},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7223321199417114},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.557889997959137},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5451913475990295},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4880332052707672},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46900081634521484},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4350980520248413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35936659574508667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3558896780014038},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2551552951335907},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08315977454185486},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2013-694","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1491931445","https://openalex.org/W1543789168","https://openalex.org/W1610279035","https://openalex.org/W2012269826","https://openalex.org/W2014181881","https://openalex.org/W2067232657","https://openalex.org/W2088489891","https://openalex.org/W2104862801","https://openalex.org/W2107508685","https://openalex.org/W2121812409","https://openalex.org/W2140979961","https://openalex.org/W2150769028","https://openalex.org/W2151626637","https://openalex.org/W2294730941"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2363301696","https://openalex.org/W2140099343"],"abstract_inverted_index":{"The":[0,82],"goal":[1],"of":[2,10,158],"this":[3],"paper":[4],"is":[5],"to":[6,52,56,59,104,115,123,132,149,160,197],"analyze":[7],"the":[8,29,39,90,105,109,116,150,172,175,184],"impact":[9],"codecdegraded":[11],"speech":[12,113,125,142,162,204],"on":[13,68,87,146],"a":[14,63,98,156],"state-of-the-art":[15],"speaker":[16,64,202,208],"recognition":[17,65],"system":[18,66,190],"and":[19,46,70,95,108,134],"propose":[20],"mitigation":[21],"techniques.":[22],"Several":[23],"acoustic":[24],"features":[25,154],"are":[26],"analyzed,":[27],"including":[28],"standard":[30],"Mel":[31],"filterbank":[32],"cepstral":[33,49],"coefficients":[34,50],"(MFCC),":[35],"as":[36,38],"well":[37],"noise-robust":[40],"medium":[41],"duration":[42],"modulation":[43],"cepstrum":[44],"(MDMC)":[45],"power":[47],"normalized":[48],"(PNCC),":[51],"determine":[53],"whether":[54],"robustness":[55,122,159,196],"noise":[57],"generalizes":[58],"audio":[60],"compression.":[61],"Using":[62],"based":[67,145],"i-vectors":[69],"probabilistic":[71],"linear":[72],"discriminant":[73],"analysis":[74],"(PLDA),":[75],"we":[76,179],"compared":[77],"four":[78],"PLDA":[79,86,131,144,169],"training":[80,85],"scenarios.":[81],"first":[83],"involves":[84],"clean":[88],"data,":[89],"second":[91],"included":[92],"additional":[93],"noisy":[94,133],"reverberant":[96,135],"speech,":[97,136],"third":[99],"introduces":[100],"transcoded":[101],"data":[102],"matched":[103],"evaluation":[106,117,151,176],"conditions":[107],"fourth,":[110],"using":[111,140],"codec-degraded":[112,198],"mismatched":[114,148],"conditions.":[118,152,177],"We":[119],"found":[120],"that":[121],"compressed":[124,161],"was":[126],"marginally":[127],"improved":[128],"by":[129],"exposing":[130],"with":[137],"little":[138],"improvement":[139],"trancoded":[141],"in":[143],"codecs":[147],"Noise-robust":[153],"offered":[155],"degree":[157],"while":[163],"more":[164],"significant":[165],"improvements":[166],"occurred":[167],"when":[168],"had":[170],"observed":[171],"codec":[173,206],"matching":[174],"Finally,":[178],"tested":[180],"i-vector":[181],"fusion":[182],"from":[183],"different":[185],"features,":[186],"which":[187],"increased":[188],"overall":[189],"performance":[191],"but":[192],"did":[193],"not":[194],"improve":[195],"speech.":[199],"Index":[200],"Terms:":[201],"recognition,":[203],"coding,":[205],"degradation,":[207],"verification.":[209]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}