{"id":"https://openalex.org/W3083533149","doi":"https://doi.org/10.21437/interspeech.2020-1563","title":"SEANet: A Multi-Modal Speech Enhancement Network","display_name":"SEANet: A Multi-Modal Speech Enhancement Network","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3083533149","doi":"https://doi.org/10.21437/interspeech.2020-1563","mag":"3083533149"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1563","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.02095","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033341878","display_name":"Marco Tagliasacchi","orcid":"https://orcid.org/0000-0002-7682-6795"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Tagliasacchi","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331862","display_name":"Yunpeng Li","orcid":"https://orcid.org/0000-0003-4798-541X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunpeng Li","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045012886","display_name":"Karolis Misiunas","orcid":"https://orcid.org/0000-0002-2236-6244"},"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":"Karolis Misiunas","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011258273","display_name":"Dominik Roblek","orcid":"https://orcid.org/0000-0002-2155-450X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dominik Roblek","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.655,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66370348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1126","last_page":"1130"},"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7538931369781494},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6217185258865356},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.6215606331825256},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6091001033782959},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5909539461135864},{"id":"https://openalex.org/keywords/accelerometer","display_name":"Accelerometer","score":0.5665984749794006},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5660267472267151},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5390820503234863},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5173013210296631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3698732554912567},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3057198226451874},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07178378105163574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7538931369781494},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6217185258865356},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.6215606331825256},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6091001033782959},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5909539461135864},{"id":"https://openalex.org/C89805583","wikidata":"https://www.wikidata.org/wiki/Q192940","display_name":"Accelerometer","level":2,"score":0.5665984749794006},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5660267472267151},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5390820503234863},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5173013210296631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3698732554912567},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3057198226451874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07178378105163574},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1563","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2009.02095","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.02095","pdf_url":"https://arxiv.org/pdf/2009.02095","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3083533149","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2009.02095","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2009.02095","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2009.02095","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2009.02095","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.02095","pdf_url":"https://arxiv.org/pdf/2009.02095","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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":0.5}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3083533149.pdf","grobid_xml":"https://content.openalex.org/works/W3083533149.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W68329929","https://openalex.org/W1438441013","https://openalex.org/W1494198834","https://openalex.org/W1897240248","https://openalex.org/W1973681148","https://openalex.org/W2033875152","https://openalex.org/W2051057783","https://openalex.org/W2101042021","https://openalex.org/W2119901478","https://openalex.org/W2133908567","https://openalex.org/W2146544734","https://openalex.org/W2149535104","https://openalex.org/W2153894152","https://openalex.org/W2163605009","https://openalex.org/W2734774145","https://openalex.org/W2788241093","https://openalex.org/W2809941692","https://openalex.org/W2917987043","https://openalex.org/W2939397531","https://openalex.org/W2962935966","https://openalex.org/W2963103134","https://openalex.org/W2963189033","https://openalex.org/W2963285578","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963685250","https://openalex.org/W2970006822","https://openalex.org/W2972568703","https://openalex.org/W2998657200","https://openalex.org/W3008880747","https://openalex.org/W3123318516"],"related_works":["https://openalex.org/W3095095816","https://openalex.org/W3153611253","https://openalex.org/W330644844","https://openalex.org/W885884664","https://openalex.org/W2481669541","https://openalex.org/W2107690418","https://openalex.org/W2892743843","https://openalex.org/W1758561146","https://openalex.org/W2739535714","https://openalex.org/W2737870520","https://openalex.org/W2184670865","https://openalex.org/W3015527782","https://openalex.org/W2146442351","https://openalex.org/W2473236733","https://openalex.org/W3086073551","https://openalex.org/W3179030250","https://openalex.org/W2407427738","https://openalex.org/W3005665731","https://openalex.org/W1994582139","https://openalex.org/W2617657420"],"abstract_inverted_index":{"We":[0,83],"explore":[1],"the":[2,27,29,44,107,126,132,140],"possibility":[3],"of":[4,69,80,103,128,135,139],"leveraging":[5],"accelerometer":[6],"data":[7,88],"to":[8,20,55,75,106,118],"perform":[9],"speech":[10,25,130],"enhancement":[11],"in":[12,43,125],"very":[13,120],"noisy":[14],"conditions.":[15],"Although":[16],"it":[17,115],"is":[18,37,116,146],"possible":[19,117],"only":[21],"partially":[22],"reconstruct":[23,76],"user's":[24,81],"from":[26,40],"accelerometer,":[28],"latter":[30],"provides":[31],"a":[32,52,60,67],"strong":[33],"conditioning":[34],"signal":[35],"that":[36,114],"not":[38],"influenced":[39],"noise":[41,104],"sources":[42,105],"environment.":[45],"Based":[46],"on":[47,93],"this":[48],"observation,":[49],"we":[50],"feed":[51],"multi-modal":[53],"input":[54],"SEANet":[56],"(Sound":[57],"EnhAncement":[58],"Network),":[59],"wave-to-wave":[61],"fully":[62],"convolutional":[63],"model,":[64],"which":[65],"adopts":[66],"combination":[68],"feature":[70],"losses":[71,74],"and":[72,96],"adversarial":[73],"an":[77,94],"enhanced":[78],"version":[79],"speech.":[82],"trained":[84],"our":[85,144],"model":[86,145],"with":[87],"collected":[89],"by":[90,99,143],"sensors":[91],"mounted":[92],"earbud":[95],"synthetically":[97],"corrupted":[98],"adding":[100],"different":[101],"kinds":[102],"audio":[108],"signal.":[109],"Our":[110],"experimental":[111],"results":[112],"demonstrate":[113],"achieve":[119],"high":[121],"quality":[122],"results,":[123],"even":[124],"case":[127],"interfering":[129],"at":[131,148],"same":[133],"level":[134],"loudness.":[136],"A":[137],"sample":[138],"output":[141],"produced":[142],"available":[147],"https://google-research.github.io/seanet/multimodal/speech.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}