{"id":"https://openalex.org/W2032595071","doi":"https://doi.org/10.1109/icassp.2013.6639033","title":"Recognition of overlapping speech using digital MEMS microphone arrays","display_name":"Recognition of overlapping speech using digital MEMS microphone arrays","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2032595071","doi":"https://doi.org/10.1109/icassp.2013.6639033","mag":"2032595071"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5080148886","display_name":"Erich Zwyssig","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Erich Zwyssig","raw_affiliation_strings":["The University of Edinburgh, Edinburgh, Edinburgh, GB","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, Edinburgh, GB","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051588436","display_name":"Friedrich Faubel","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Friedrich Faubel","raw_affiliation_strings":["Spoken Language Systems, Saarland University, Saarbrucken, Germany","Spoken Language Systems, Saarland University, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Systems, Saarland University, Saarbrucken, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Spoken Language Systems, Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110108257","display_name":"Mike Lincoln","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mike Lincoln","raw_affiliation_strings":["Quorate Technology, Edinburgh, UK","Quorate Technol., Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quorate Technology, Edinburgh, UK","institution_ids":[]},{"raw_affiliation_string":"Quorate Technol., Edinburgh, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7068","last_page":"7072"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.7756112813949585},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7190237045288086},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7111670970916748},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5880618691444397},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5346004366874695},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5239560604095459},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.509601354598999},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4443766474723816},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42642492055892944},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.42456692457199097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.381043016910553},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06452801823616028}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756112813949585},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7190237045288086},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7111670970916748},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5880618691444397},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5346004366874695},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5239560604095459},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.509601354598999},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4443766474723816},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42642492055892944},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.42456692457199097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.381043016910553},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06452801823616028},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W7575313","https://openalex.org/W126779258","https://openalex.org/W258638584","https://openalex.org/W1524333225","https://openalex.org/W1555217905","https://openalex.org/W1576049859","https://openalex.org/W1596692493","https://openalex.org/W1931312565","https://openalex.org/W1982728343","https://openalex.org/W1987906574","https://openalex.org/W2002299243","https://openalex.org/W2002342963","https://openalex.org/W2014121075","https://openalex.org/W2070707809","https://openalex.org/W2078020518","https://openalex.org/W2083751884","https://openalex.org/W2099655464","https://openalex.org/W2105317065","https://openalex.org/W2117518720","https://openalex.org/W2130722890","https://openalex.org/W2147166770","https://openalex.org/W2400445407","https://openalex.org/W3105118415","https://openalex.org/W3144370979","https://openalex.org/W4285719527","https://openalex.org/W6609694752","https://openalex.org/W6668103105","https://openalex.org/W6712515473"],"related_works":["https://openalex.org/W2324276190","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W3036714475","https://openalex.org/W2149163000","https://openalex.org/W2052688117","https://openalex.org/W1987896763","https://openalex.org/W2552102772"],"abstract_inverted_index":{"This":[0],"paper":[1,24],"presents":[2,25],"a":[3,39,55],"new":[4],"corpus":[5,37,48,125],"comprising":[6],"single":[7,115],"and":[8,15,30,58,77,89,98,118],"overlapping":[9,122],"speech":[10,28,52,75,78],"recorded":[11,51],"using":[12,62,83],"digital":[13],"MEMS":[14],"analogue":[16],"microphone":[17,65],"arrays.":[18],"In":[19],"addition":[20],"to":[21],"this,":[22],"the":[23,42,107,114,132],"results":[26],"from":[27],"separation":[29,76],"recognition":[31,79,104],"experiments":[32,80],"on":[33,113,121],"this":[34],"data.":[35],"The":[36,74,124],"is":[38],"reproduction":[40],"of":[41,109],"multi-channel":[43],"Wall":[44],"Street":[45],"Journal":[46],"audio-visual":[47],"(MC-WSJAV),":[49],"containing":[50],"in":[53,134],"both":[54],"meeting":[56],"room":[57],"an":[59],"anechoic":[60],"chamber":[61],"two":[63,70],"different":[64,71],"types":[66],"as":[67,69,94],"well":[68],"array":[72],"geometries.":[73],"were":[81],"performed":[82],"SRP-PHAT-based":[84],"speaker":[85,116],"localisation,":[86],"superdirective":[87],"beamforming":[88],"multiple":[90],"post-processing":[91],"schemes,":[92],"such":[93],"residual":[95],"echo":[96],"suppression":[97],"binary":[99],"masking.":[100],"Our":[101],"simple,":[102],"cMLLR-based":[103],"system":[105],"matches":[106],"performance":[108],"state-of-the-art":[110],"ASR":[111],"systems":[112],"task":[117],"outperforms":[119],"them":[120],"speech.":[123],"will":[126],"be":[127],"made":[128],"publicly":[129],"available":[130],"via":[131],"LDC":[133],"spring":[135],"2013.":[136]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}