{"id":"https://openalex.org/W2111479516","doi":"https://doi.org/10.1109/tasl.2008.2011534","title":"Energetic and Informational Masking Effects in an Audiovisual Speech Recognition System","display_name":"Energetic and Informational Masking Effects in an Audiovisual Speech Recognition System","publication_year":2009,"publication_date":"2009-02-13","ids":{"openalex":"https://openalex.org/W2111479516","doi":"https://doi.org/10.1109/tasl.2008.2011534","mag":"2111479516"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2008.2011534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2011534","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5074458312","display_name":"Jon Barker","orcid":"https://orcid.org/0000-0002-1684-5660"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jon Barker","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK","Department of Computer Science, University of Sheffield, Sheffield,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield,","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110379443","display_name":"Xu Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]},{"id":"https://openalex.org/I4210142256","display_name":"Nuance Communications (United Kingdom)","ror":"https://ror.org/03ae66d75","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210125787","https://openalex.org/I4210142256"]},{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["AT","GB"],"is_corresponding":false,"raw_author_name":"Xu Shao","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK","Nuance Communications, Inc., Berkshire, UK","Department of Computer Science, University of Sheffield, Sheffield,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Nuance Communications, Inc., Berkshire, UK","institution_ids":["https://openalex.org/I1292318990","https://openalex.org/I4210142256"]},{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield,","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0793,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.78871285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"17","issue":"3","first_page":"446","last_page":"458"},"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/T11309","display_name":"Music 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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6584095358848572},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5892683863639832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5314143300056458},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4665021300315857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3556448519229889}],"concepts":[{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6584095358848572},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5892683863639832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5314143300056458},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4665021300315857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3556448519229889},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2008.2011534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2011534","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W15147940","https://openalex.org/W26845451","https://openalex.org/W135040384","https://openalex.org/W196088823","https://openalex.org/W196476531","https://openalex.org/W1275705376","https://openalex.org/W1502024436","https://openalex.org/W1533162639","https://openalex.org/W1544889373","https://openalex.org/W1571194703","https://openalex.org/W1575829986","https://openalex.org/W1991112797","https://openalex.org/W1993829942","https://openalex.org/W2002322356","https://openalex.org/W2004143321","https://openalex.org/W2015143272","https://openalex.org/W2023055982","https://openalex.org/W2049059635","https://openalex.org/W2050758723","https://openalex.org/W2065428732","https://openalex.org/W2070729651","https://openalex.org/W2074354966","https://openalex.org/W2075076415","https://openalex.org/W2096391593","https://openalex.org/W2098717567","https://openalex.org/W2102865113","https://openalex.org/W2103941300","https://openalex.org/W2106603795","https://openalex.org/W2114125447","https://openalex.org/W2114793178","https://openalex.org/W2115560299","https://openalex.org/W2120535071","https://openalex.org/W2127211243","https://openalex.org/W2150269104","https://openalex.org/W2168744723","https://openalex.org/W2278884322","https://openalex.org/W2405594332","https://openalex.org/W2561557072","https://openalex.org/W2793908218","https://openalex.org/W4250500702","https://openalex.org/W4256399001","https://openalex.org/W6601095907","https://openalex.org/W6607899525","https://openalex.org/W6628334182","https://openalex.org/W6682080839","https://openalex.org/W6713838268"],"related_works":["https://openalex.org/W1596769518","https://openalex.org/W2886693075","https://openalex.org/W3198503472","https://openalex.org/W1566274093","https://openalex.org/W4307784074","https://openalex.org/W4200114095","https://openalex.org/W3197849864","https://openalex.org/W2096480681","https://openalex.org/W3142067363","https://openalex.org/W2134930863"],"abstract_inverted_index":{"The":[0,14,63],"paper":[1],"presents":[2],"a":[3,43,68],"robust":[4],"audiovisual":[5,10,49],"speech":[6,11,21,50,61,72],"recognition":[7,73],"technique":[8,15],"called":[9],"fragment":[12],"decoding.":[13],"addresses":[16],"the":[17,23,39,59,85,88,94,101,112,118,124,129,164],"challenge":[18],"of":[19,25,45,82,87,93,131,134,166],"recognizing":[20],"in":[22,75],"presence":[24],"competing":[26],"nonstationary":[27],"noise":[28],"sources.":[29],"It":[30],"employs":[31],"two":[32,79],"stages.":[33],"First,":[34],"an":[35],"acoustic":[36,40],"analysis":[37],"decomposes":[38],"signal":[41],"into":[42],"number":[44],"spectro-temporall":[46],"fragments.":[47],"Second,":[48],"models":[51],"are":[52],"used":[53],"to":[54,58,108,111,122,127,146],"select":[55],"fragments":[56],"belonging":[57],"target":[60,102],"source.":[62,114],"approach":[64],"is":[65,120],"evaluated":[66],"on":[67],"small":[69],"vocabulary":[70],"simultaneous":[71],"task":[74],"conditions":[76],"that":[77,92,117,159],"promote":[78],"contrasting":[80],"types":[81,133],"masking:energeticmaskingcaused":[83],"by":[84,98],"energy":[86],"masker":[89,104],"utterance":[90],"swamping":[91],"target,":[95],"andinformationalmasking,":[96],"caused":[97],"similarity":[99],"between":[100],"and":[103,169],"making":[105],"it":[106],"difficult":[107],"selectively":[109],"attend":[110],"correct":[113],"Results":[115],"show":[116],"system":[119],"able":[121],"use":[123],"visual":[125,142,157],"cues":[126],"reduce":[128],"effects":[130],"both":[132],"masking.":[135],"Further,":[136],"whereas":[137],"recovery":[138],"fromenergeticmaskingmay":[139],"require":[140],"detailed":[141],"information":[143],"(i.e.,":[144],"sufficient":[145],"carry":[147],"phonetic":[148],"content),":[149],"release":[150],"frominformationalmaskingcan":[151],"be":[152],"achieved":[153],"using":[154],"very":[155],"crude":[156],"representations":[158],"encode":[160],"little":[161],"more":[162],"than":[163],"timing":[165],"mouth":[167],"opening":[168],"closure.":[170]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}