{"id":"https://openalex.org/W106565655","doi":"https://doi.org/10.21437/eurospeech.2003-231","title":"Enhancement of speech in multispeaker environment","display_name":"Enhancement of speech in multispeaker environment","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W106565655","doi":"https://doi.org/10.21437/eurospeech.2003-231","mag":"106565655"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-231","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5079329589","display_name":"B. Yegnanarayana","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"B. Yegnanarayana","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","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/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":"S.R. Mahadeva Prasanna","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathew Magimai Doss","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079329589"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.01102525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"581","last_page":"584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11447","display_name":"Blind Source Separation Techniques","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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7739576697349548},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7613701224327087},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6485830545425415},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.6252360939979553},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5735753178596497},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5694030523300171},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.541549026966095},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.5169162750244141},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5131946206092834},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44772061705589294},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.39896661043167114},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.2941027283668518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21660113334655762},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10450035333633423}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7739576697349548},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7613701224327087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6485830545425415},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.6252360939979553},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5735753178596497},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5694030523300171},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.541549026966095},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.5169162750244141},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5131946206092834},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44772061705589294},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.39896661043167114},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.2941027283668518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21660113334655762},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10450035333633423},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"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":2,"locations":[{"id":"doi:10.21437/eurospeech.2003-231","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.11.365","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://speech.cs.iitm.ernet.in/~prasanna/papers/BYSRMPEURO.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1966264494","https://openalex.org/W2089654451","https://openalex.org/W2100971813","https://openalex.org/W2102072896","https://openalex.org/W2119647652","https://openalex.org/W2126127391","https://openalex.org/W2139819017","https://openalex.org/W2152728141","https://openalex.org/W2159524087","https://openalex.org/W2170491071","https://openalex.org/W2172230732"],"related_works":["https://openalex.org/W2363056088","https://openalex.org/W2365133740","https://openalex.org/W2438418151","https://openalex.org/W2808395304","https://openalex.org/W3211091508","https://openalex.org/W2363301696","https://openalex.org/W2109543333","https://openalex.org/W2141143576","https://openalex.org/W1994313308","https://openalex.org/W4312036005"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"a":[3],"method":[4],"based":[5],"on":[6],"the":[7,42,48,61,64,67,76,83,91,121,132],"excitation":[8,49,68],"source":[9,50,69],"information":[10],"is":[11,27,45,55,99],"proposed":[12],"for":[13,57],"enhancement":[14,119],"of":[15,36,63,75,109,120,123],"speech,":[16],"degraded":[17],"by":[18],"speech":[19,95,107,122],"from":[20,24,90,101,131],"other":[21,128],"speakers.":[22],"Speech":[23,86],"multiple":[25],"speakers":[26],"simultaneously":[28],"collected":[29],"over":[30],"two":[31,43],"spatially":[32],"distributed":[33],"microphones.":[34],"Time-delay":[35],"each":[37,58,102,110],"speaker":[38,59,98,111,125],"with":[39],"respect":[40],"to":[41,114,127],"microphones":[44],"estimated":[46],"using":[47,60,82],"information.":[51,70],"A":[52],"weight":[53,84],"function":[54],"derived":[56,100],"knowledge":[62],"timedelay":[65],"and":[66],"Linear":[71],"prediction":[72],"(LP)":[73],"residuals":[74],"microphone":[77,103],"signals":[78,87,108],"are":[79,88,112],"processed":[80],"separately":[81],"functions.":[85],"synthesized":[89,106],"modified":[92],"residuals.":[93],"One":[94],"signal":[96],"per":[97],"signal.":[104,134],"The":[105],"combined":[113,133],"produce":[115],"enhanced":[116],"speech.":[117],"Significant":[118],"one":[124],"relative":[126],"was":[129],"observed":[130]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}