{"id":"https://openalex.org/W1985261152","doi":"https://doi.org/10.1109/icassp.2014.6854660","title":"Impact of single-microphone dereverberation on DNN-based meeting transcription systems","display_name":"Impact of single-microphone dereverberation on DNN-based meeting transcription systems","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1985261152","doi":"https://doi.org/10.1109/icassp.2014.6854660","mag":"1985261152"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.repository.cam.ac.uk/bitstreams/78d0fc40-d5b0-4345-a77d-79fa32febc89/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["University of Cambridge, Cambridge, Cambridgeshire, GB","Engineering Department, Cambridge University, Cambridge, UK,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, Cambridgeshire, GB","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, UK,","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329117","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-5801-2571"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Engineering Department, Cambridge University, Cambridge, UK","Engineering Department, Cambridge University, Cambridge, UK,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, UK,","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark J. F. Gales","raw_affiliation_strings":["Engineering Department, Cambridge University, Cambridge, UK","Engineering Department, Cambridge University, Cambridge, UK,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, UK,","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5527","last_page":"5531"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9994000196456909,"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/reverberation","display_name":"Reverberation","score":0.8363523483276367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7907189130783081},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7487725019454956},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7181241512298584},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6807745695114136},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6025936007499695},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5174692273139954},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4873534142971039},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4765772819519043},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4266960024833679},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42206329107284546},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32575345039367676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31932926177978516},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18817603588104248},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0847526490688324}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8363523483276367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907189130783081},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7487725019454956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7181241512298584},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6807745695114136},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6025936007499695},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5174692273139954},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4873534142971039},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4765772819519043},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4266960024833679},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42206329107284546},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32575345039367676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31932926177978516},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18817603588104248},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0847526490688324},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2014.6854660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/247409","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/247409","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/78d0fc40-d5b0-4345-a77d-79fa32febc89/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.648.6125","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.648.6125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mi.eng.cam.ac.uk/~xc257/papers/Meeting_DNN.pdf","raw_type":"text"},{"id":"pmh:oai:generic.eprints.org:663759","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/663759/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":{"id":"pmh:oai:www.repository.cam.ac.uk:1810/247409","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/247409","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/78d0fc40-d5b0-4345-a77d-79fa32febc89/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1985261152.pdf","grobid_xml":"https://content.openalex.org/works/W1985261152.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1553154706","https://openalex.org/W1973669708","https://openalex.org/W1983812858","https://openalex.org/W1988843652","https://openalex.org/W2002342963","https://openalex.org/W2012897754","https://openalex.org/W2050091530","https://openalex.org/W2062164080","https://openalex.org/W2080400971","https://openalex.org/W2106554350","https://openalex.org/W2124611315","https://openalex.org/W2125336414","https://openalex.org/W2125610823","https://openalex.org/W2140571699","https://openalex.org/W2147768505","https://openalex.org/W2148613904","https://openalex.org/W2156744133","https://openalex.org/W2160306971","https://openalex.org/W2169189000","https://openalex.org/W2172097686","https://openalex.org/W2183182240","https://openalex.org/W3031363333"],"related_works":["https://openalex.org/W2556771176","https://openalex.org/W2640905660","https://openalex.org/W2402949781","https://openalex.org/W1955848339","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3143423642"],"abstract_inverted_index":{"Over":[0],"the":[1,15,77,85,116,121,126,129,134],"past":[2],"few":[3],"decades,":[4],"a":[5,43,57,71,100,106],"range":[6],"of":[7,17,34,73,87,90,120,128,141],"front-end":[8],"techniques":[9,27],"have":[10],"been":[11,49],"proposed":[12],"to":[13,79,145],"improve":[14,84],"robustness":[16],"automatic":[18],"speech":[19],"recognition":[20,117],"systems":[21],"against":[22],"environmental":[23],"distortion.":[24],"While":[25],"these":[26],"are":[28,54],"effective":[29],"for":[30,56],"small":[31],"tasks":[32],"consisting":[33],"carefully":[35],"designed":[36],"data":[37],"sets,":[38],"especially":[39],"when":[40],"used":[41],"with":[42,60],"classical":[44],"acoustic":[45,91,122],"model,":[46],"there":[47],"has":[48],"limited":[50],"evidence":[51],"that":[52,113],"they":[53],"useful":[55],"state-of-the-art":[58],"system":[59],"large":[61],"scale":[62],"realistic":[63],"data.":[64],"This":[65],"paper":[66],"focuses":[67],"on":[68,94],"reverberation":[69],"as":[70],"type":[72,127],"distortion":[74],"and":[75,125,143,150],"investigates":[76],"degree":[78],"which":[80],"dereverberation":[81,114],"processing":[82],"can":[83],"performance":[86,118],"various":[88],"forms":[89],"models":[92],"based":[93],"deep":[95],"neural":[96,135],"networks":[97],"(DNNs)":[98],"in":[99],"challenging":[101],"meeting":[102],"transcription":[103],"task":[104],"using":[105],"single":[107],"distant":[108],"microphone.":[109],"Experimental":[110],"results":[111],"show":[112],"improves":[115],"regardless":[119],"model":[123],"structure":[124],"feature":[130],"vectors":[131],"input":[132],"into":[133],"networks,":[136],"providing":[137],"additional":[138],"relative":[139],"improvements":[140],"4.7%":[142],"4.1%":[144],"our":[146],"best":[147],"configured":[148],"speaker-independent":[149],"speaker-adaptive":[151],"DNN-based":[152],"systems,":[153],"respectively.":[154]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
