{"id":"https://openalex.org/W2900292050","doi":"https://doi.org/10.1109/icassp.2019.8682061","title":"Face Landmark-based Speaker-independent Audio-visual Speech Enhancement in Multi-talker Environments","display_name":"Face Landmark-based Speaker-independent Audio-visual Speech Enhancement in Multi-talker Environments","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2900292050","doi":"https://doi.org/10.1109/icassp.2019.8682061","mag":"2900292050"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.02480","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040930642","display_name":"Giovanni Morrone","orcid":"https://orcid.org/0000-0003-2163-1779"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Morrone","raw_affiliation_strings":["Department of Engineering \"Enzo Ferrari\", University of Modena and Reggio Emilia, Modena, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering \"Enzo Ferrari\", University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037830808","display_name":"Sonia Bergamaschi","orcid":"https://orcid.org/0000-0001-8087-6587"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sonia Bergamaschi","raw_affiliation_strings":["Department of Engineering \"Enzo Ferrari\", University of Modena and Reggio Emilia, Modena, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering \"Enzo Ferrari\", University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065003610","display_name":"Luca Pasa","orcid":"https://orcid.org/0000-0002-3023-3046"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Pasa","raw_affiliation_strings":["Istituto Italiano di Tecnologia, Ferrara, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia, Ferrara, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057942643","display_name":"Luciano Fadiga","orcid":"https://orcid.org/0000-0001-5691-5080"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luciano Fadiga","raw_affiliation_strings":["Istituto Italiano di Tecnologia, Ferrara, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia, Ferrara, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008949994","display_name":"Vadim Tikhanoff","orcid":"https://orcid.org/0000-0001-5295-3928"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Vadim Tikhanoff","raw_affiliation_strings":["Istituto Italiano di Tecnologia, Ferrara, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia, Ferrara, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063165262","display_name":"Leonardo Badino","orcid":"https://orcid.org/0000-0001-7037-5914"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Leonardo Badino","raw_affiliation_strings":["Istituto Italiano di Tecnologia, Ferrara, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia, Ferrara, Italy","institution_ids":["https://openalex.org/I30771326"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":58,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6900","last_page":"6904"},"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/T11448","display_name":"Face recognition and analysis","score":0.9972000122070312,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9865999817848206,"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/spectrogram","display_name":"Spectrogram","score":0.913811206817627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8342665433883667},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7646114230155945},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.7419816255569458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5093191862106323},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4503360092639923},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.44672688841819763},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.4260694980621338},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4134748578071594},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32702910900115967},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.320246160030365},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2919944226741791}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.913811206817627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8342665433883667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7646114230155945},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.7419816255569458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5093191862106323},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4503360092639923},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.44672688841819763},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.4260694980621338},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4134748578071594},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32702910900115967},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.320246160030365},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2919944226741791},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2019.8682061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.02480","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.02480","pdf_url":"https://arxiv.org/pdf/1811.02480","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:iris.unimore.it:11380/1170465","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1170465","pdf_url":"https://iris.unimore.it/bitstream/11380/1170465/11/Morrone_ICASSP_Poster.pdf","source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:iris.unife.it:11392/2413185","is_oa":false,"landing_page_url":"http://hdl.handle.net/11392/2413185","pdf_url":null,"source":{"id":"https://openalex.org/S4306400369","display_name":"Institutional Research Information System University of Ferrara (University of Ferrara)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201324441","host_organization_name":"University of Ferrara","host_organization_lineage":["https://openalex.org/I201324441"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:www.research.unipd.it:11577/3390308","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/abstract/document/8682061","pdf_url":null,"source":{"id":"https://openalex.org/S4377196283","display_name":"Research Padua  Archive (University of Padua)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.02480","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.02480","pdf_url":"https://arxiv.org/pdf/1811.02480","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1607435270","https://openalex.org/W1964538581","https://openalex.org/W1971168548","https://openalex.org/W1991139021","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2042750879","https://openalex.org/W2069681747","https://openalex.org/W2081144555","https://openalex.org/W2087126002","https://openalex.org/W2087681821","https://openalex.org/W2088079940","https://openalex.org/W2115252128","https://openalex.org/W2127851351","https://openalex.org/W2143612262","https://openalex.org/W2167734090","https://openalex.org/W2315268655","https://openalex.org/W2407685581","https://openalex.org/W2558649592","https://openalex.org/W2577762507","https://openalex.org/W2734774145","https://openalex.org/W2788241093","https://openalex.org/W2962715207","https://openalex.org/W2962960500","https://openalex.org/W2963019222","https://openalex.org/W2963082324","https://openalex.org/W2964171275","https://openalex.org/W2964207404","https://openalex.org/W3123318516","https://openalex.org/W4289665794","https://openalex.org/W6631190155","https://openalex.org/W6636170946","https://openalex.org/W6677618333","https://openalex.org/W6714030504","https://openalex.org/W6750591037"],"related_works":["https://openalex.org/W2056853153","https://openalex.org/W2057559274","https://openalex.org/W2026924879","https://openalex.org/W2005087563","https://openalex.org/W2378111931","https://openalex.org/W2052388267","https://openalex.org/W2950647290","https://openalex.org/W1968481813","https://openalex.org/W2620829895","https://openalex.org/W1980604799"],"abstract_inverted_index":{"In":[0],"this":[1,91],"paper,":[2],"we":[3,35],"address":[4],"the":[5,9,25,42,75,100,117,127,131,140,147],"problem":[6],"of":[7,11,14,24,27,99,133],"enhancing":[8],"speech":[10,157],"a":[12,17,57,160],"speaker":[13,26],"interest":[15,28],"in":[16,159],"cocktail":[18],"party":[19],"scenario":[20],"when":[21],"visual":[22,39],"information":[23],"is":[29,107],"available.Contrary":[30],"to":[31,67,74,95],"most":[32],"previous":[33,96],"studies,":[34],"do":[36],"not":[37],"learn":[38],"features":[40,85,89,125],"on":[41,56,121,146],"typically":[43],"small":[44],"audio-visual":[45],"datasets,":[46,153],"but":[47],"use":[48],"an":[49],"already":[50],"available":[51],"face":[52],"landmark":[53,124],"detector":[54],"(trained":[55],"separate":[58],"image":[59],"dataset).The":[60],"landmarks":[61],"are":[62,72,86,139],"used":[63],"by":[64,105],"LSTM-based":[65],"models":[66,138,142],"generate":[68],"time-frequency":[69],"masks":[70,119],"which":[71],"applied":[73],"acoustic":[76],"mixed-speech":[77,129],"spectrogram.":[78],"Results":[79],"show":[80],"that:":[81],"(i)":[82],"land-mark":[83],"motion":[84,123],"very":[87],"effective":[88],"for":[90],"task,":[92],"(ii)":[93],"similarly":[94],"work,":[97],"reconstruction":[98],"target":[101],"speaker's":[102],"spectrogram":[103,113],"mediated":[104],"masking":[106],"significantly":[108],"more":[109],"accurate":[110],"than":[111],"direct":[112],"reconstruction,":[114],"and":[115,126,144,151],"(iii)":[116],"best":[118,132],"depend":[120],"both":[122],"input":[128],"spectrogram.To":[130],"our":[134,136],"knowledge,":[135],"proposed":[137],"first":[141],"trained":[143],"evaluated":[145],"limited":[148],"size":[149],"GRID":[150],"TCD-TIMIT":[152],"that":[154],"achieve":[155],"speaker-independent":[156],"enhancement":[158],"multi-talker":[161],"setting.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
