{"id":"https://openalex.org/W2516756629","doi":"https://doi.org/10.21437/interspeech.2016-544","title":"Speaker Recognition Using Real vs Synthetic Parallel Data for DNN Channel Compensation","display_name":"Speaker Recognition Using Real vs Synthetic Parallel Data for DNN Channel Compensation","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2516756629","doi":"https://doi.org/10.21437/interspeech.2016-544","mag":"2516756629"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-544","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","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/A5111923912","display_name":"Fred Richardson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fred Richardson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086705866","display_name":"M.S. Brandstein","orcid":"https://orcid.org/0009-0008-7883-3658"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Brandstein","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077989079","display_name":"Jennifer Melot","orcid":"https://orcid.org/0000-0002-3772-6097"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jennifer Melot","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112042504","display_name":"Douglas A. Reynolds","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Douglas Reynolds","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5105,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64807974,"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":"2796","last_page":"2800"},"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":0.9990000128746033,"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/microphone","display_name":"Microphone","score":0.8132145404815674},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7182843685150146},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.7091552019119263},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6963258385658264},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6838342547416687},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5605244636535645},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4737951159477234},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.410381019115448},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32930707931518555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3203601837158203},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15036550164222717}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.8132145404815674},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7182843685150146},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.7091552019119263},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6963258385658264},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6838342547416687},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5605244636535645},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4737951159477234},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.410381019115448},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32930707931518555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3203601837158203},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15036550164222717},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"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":1,"locations":[{"id":"doi:10.21437/interspeech.2016-544","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W134766468","https://openalex.org/W208690272","https://openalex.org/W306992701","https://openalex.org/W1504755800","https://openalex.org/W1578000412","https://openalex.org/W1973681148","https://openalex.org/W2124248639","https://openalex.org/W2242685705","https://openalex.org/W2245569228","https://openalex.org/W2288817436","https://openalex.org/W2289441404","https://openalex.org/W2395750323","https://openalex.org/W2398163098","https://openalex.org/W2404568753","https://openalex.org/W2407204023"],"related_works":["https://openalex.org/W2357191878","https://openalex.org/W1997078944","https://openalex.org/W1968065688","https://openalex.org/W1552846815","https://openalex.org/W2142945567","https://openalex.org/W4289829835","https://openalex.org/W2030332364","https://openalex.org/W2005459225","https://openalex.org/W4220830676","https://openalex.org/W2146197305"],"abstract_inverted_index":{"Abstract":[0],":":[1],"The":[2],"effective":[3],"use":[4,30],"of":[5,31],"synthetic":[6,34],"multi-channel":[7],"data":[8,35,75,82,111],"for":[9,16,36,40,52,62],"training":[10,37],"denoising":[11,38,86,176],"DNNs":[12,39,177],"has":[13],"been":[14],"demonstrated":[15],"several":[17],"speech":[18],"technologies":[19],"such":[20],"as":[21],"ASR":[22],"and":[23,33,50,55,58,60,65,79,101,112,142,148,151,153,159,183,191],"speaker":[24,42],"recognition.":[25,43],"This":[26],"paper":[27],"compares":[28],"the":[29,53,63,89,107,116,128,166,175,179],"real":[32,180],"multi-microphone":[41,81],"Large":[44],"reductions":[45,137],"in":[46,92,127,138,146,157],"error":[47,93,139],"rates":[48],"(37%":[49],"50%":[51],"AVG":[54,64,147,158],"POOL":[56,66,149,160],"EERs":[57],"20%":[59],"30%":[61],"min":[67,161,192],"DCFs)":[68],"are":[69],"attained":[70],"on":[71,170],"Mixer":[72,77,108,181],"6":[73],"microphone":[74],"using":[76,97],"1":[78,182],"2":[80,110,184],"to":[83,114],"train":[84],"a":[85],"DNN.":[87],"Nearly":[88],"same":[90],"reduction":[91],"rate":[94,140],"is":[95,172],"realized":[96],"room":[98],"impulse":[99],"response":[100],"noise":[102],"estimates":[103],"(RIRs)":[104],"derived":[105],"from":[106,121],"1and":[109],"applied":[113],"just":[115],"telephone":[117,167],"channel.":[118],"Applying":[119],"RIRs":[120],"three":[122],"publicly":[123],"available":[124],"databases":[125],"used":[126],"Kaldi":[129],"Aspire":[130],"evaluation":[131],"system":[132],"yields":[133],"lower":[134],"but":[135],"significant":[136],"(16%":[141],"34%":[143],"relative":[144,155],"improvement":[145,156],"EER":[150,188],"13%":[152],"25%":[154],"DCFs).":[162],"In":[163],"all":[164],"cases,":[165],"channel":[168],"performance":[169],"SRE10":[171],"improved":[173],"by":[174,189,194],"with":[178],"trained":[185],"DNN":[186],"reducing":[187],"12%":[190],"DCF":[193],"8.9%.":[195]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}