{"id":"https://openalex.org/W2278884322","doi":"https://doi.org/10.1109/icassp.2002.5745030","title":"Noisy audio feature enhancement using audio-visual speech data","display_name":"Noisy audio feature enhancement using audio-visual speech data","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2278884322","doi":"https://doi.org/10.1109/icassp.2002.5745030","mag":"2278884322"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5745030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745030","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5046144886","display_name":"Roland Goecke","orcid":"https://orcid.org/0000-0003-2279-7041"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Roland Goecke","raw_affiliation_strings":["Computer Sciences Laboratory, Australian National University, Canberra ACT 0200, Australia"],"affiliations":[{"raw_affiliation_string":"Computer Sciences Laboratory, Australian National University, Canberra ACT 0200, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111579153","display_name":"C. Neti","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chalapathy Neti","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046144886"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":2.9695,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.91787853,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"II","last_page":"2025"},"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":0.9983999729156494,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8246433734893799},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8196394443511963},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5967375040054321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.532988965511322},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.528119683265686},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4949747920036316},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45887911319732666},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4337162971496582},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43216776847839355},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42298823595046997},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41084468364715576},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.31353676319122314},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3109009265899658},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.29134005308151245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246433734893799},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8196394443511963},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5967375040054321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.532988965511322},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.528119683265686},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4949747920036316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45887911319732666},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4337162971496582},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43216776847839355},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42298823595046997},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41084468364715576},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.31353676319122314},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3109009265899658},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29134005308151245},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5745030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745030","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.2650","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.2650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cslab.anu.edu.au/~rgoecke/Publications/goeckeIcassp02.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W33935026","https://openalex.org/W1275705376","https://openalex.org/W1488856050","https://openalex.org/W1493163583","https://openalex.org/W1929897159","https://openalex.org/W2038010270","https://openalex.org/W2051091181","https://openalex.org/W2064817422","https://openalex.org/W2127211243","https://openalex.org/W2139332492","https://openalex.org/W2153639013","https://openalex.org/W2487271655","https://openalex.org/W2796837256","https://openalex.org/W4231869218","https://openalex.org/W6601364879","https://openalex.org/W6628334182","https://openalex.org/W6629442188"],"related_works":["https://openalex.org/W2401089611","https://openalex.org/W2499802997","https://openalex.org/W4255044973","https://openalex.org/W2112059504","https://openalex.org/W2962707588","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2157598242","https://openalex.org/W2464377622","https://openalex.org/W4385611764"],"abstract_inverted_index":{"We":[0],"investigate":[1],"improving":[2],"automatic":[3],"speech":[4,17,78],"recognition":[5],"(ASR)":[6],"in":[7,53,112,148],"noisy":[8,12,37,103],"conditions":[9],"by":[10,27,43,139],"enhancing":[11],"audio":[13,38,51,62,95],"features":[14,52,63,96],"using":[15],"visual":[16,40,132],"captured":[18],"from":[19],"the":[20,33,49,60,93,102,117,125,130],"speaker's":[21],"face.":[22],"The":[23,57],"enhancement":[24],"is":[25,64],"achieved":[26],"applying":[28],"a":[29,54,108],"linear":[30],"filter":[31],"to":[32,128,135,142],"concatenated":[34],"vector":[35],"of":[36,48,59],"and":[39,74,83],"features,":[41],"obtained":[42],"mean":[44],"square":[45],"error":[46,114],"estimation":[47],"clean":[50],"training":[55],"stage.":[56],"performance":[58],"enhanced":[61,94],"evaluated":[65],"on":[66,92,101,116],"two":[67],"ASR":[68,90,99],"tasks:":[69],"A":[70],"connected":[71],"digits":[72,118],"task":[73,119],"speaker-independent,":[75],"large-vocabulary,":[76],"continuous":[77],"recognition.":[79],"In":[80],"both":[81],"cases":[82],"at":[84,120],"sufficiently":[85],"low":[86],"signal-to-noise":[87],"ratios":[88],"(SNRs),":[89],"trained":[91,100],"significantly":[97],"outperforms":[98],"audio,":[104],"achieving":[105],"for":[106],"example":[107],"46%":[109],"relative":[110],"reduction":[111],"word":[113],"rate":[115],"\u22123.5":[121],"dB":[122],"SNR.":[123],"However,":[124],"method":[126],"fails":[127],"capture":[129],"full":[131],"modality":[133],"benefit":[134],"ASR,":[136],"as":[137],"demonstrated":[138],"its":[140],"comparison":[141],"discriminant":[143],"audio-visual":[144],"feature":[145],"fusion":[146],"introduced":[147],"previous":[149],"work.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}