{"id":"https://openalex.org/W2742601054","doi":"https://doi.org/10.21437/interspeech.2017-421","title":"Improving Speaker-Independent Lipreading with Domain-Adversarial Training","display_name":"Improving Speaker-Independent Lipreading with Domain-Adversarial Training","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2742601054","doi":"https://doi.org/10.21437/interspeech.2017-421","mag":"2742601054"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-421","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1708.01565","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020719193","display_name":"Michael Wand","orcid":"https://orcid.org/0000-0003-0966-7824"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Michael Wand","raw_affiliation_strings":["Johannes Gutenberg University Mainz, Mainz, Germany"],"affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"last","author":{"id":null,"display_name":"J\u00fcrgen Schmidhuber","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Schmidhuber","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence Research, Lugano, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence Research, Lugano, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020719193"],"corresponding_institution_ids":["https://openalex.org/I197323543"],"apc_list":null,"apc_paid":null,"fwci":2.2385,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89388367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9983999729156494,"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":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.825416088104248},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7681387066841125},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6846423745155334},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4976983368396759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49115344882011414},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.49009740352630615},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4760594069957733},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45663928985595703},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3447626829147339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.825416088104248},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7681387066841125},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6846423745155334},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4976983368396759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49115344882011414},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.49009740352630615},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4760594069957733},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45663928985595703},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3447626829147339},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2017-421","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1708.01565","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.01565","pdf_url":"https://arxiv.org/pdf/1708.01565","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":"mag:2742601054","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1708.01565.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1708.01565","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1708.01565","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1708.01565","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.01565","pdf_url":"https://arxiv.org/pdf/1708.01565","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":"Quality Education","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2742601054.pdf","grobid_xml":"https://content.openalex.org/works/W2742601054.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W22517275","https://openalex.org/W1904365287","https://openalex.org/W1908325895","https://openalex.org/W1994618660","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2024490110","https://openalex.org/W2060756806","https://openalex.org/W2064675550","https://openalex.org/W2106137268","https://openalex.org/W2113814270","https://openalex.org/W2121822766","https://openalex.org/W2129160496","https://openalex.org/W2136155248","https://openalex.org/W2157190406","https://openalex.org/W2165698076","https://openalex.org/W2394613688","https://openalex.org/W2394855416","https://openalex.org/W2397635203","https://openalex.org/W2404704342","https://openalex.org/W2406255155","https://openalex.org/W2508171209","https://openalex.org/W2509591453","https://openalex.org/W2578229578","https://openalex.org/W2951015274","https://openalex.org/W2952746495","https://openalex.org/W2963826681"],"related_works":["https://openalex.org/W2594690981","https://openalex.org/W2015143272","https://openalex.org/W2952746495","https://openalex.org/W2556171197","https://openalex.org/W2113814270","https://openalex.org/W2060510034","https://openalex.org/W82494927","https://openalex.org/W2578229578","https://openalex.org/W2365880764","https://openalex.org/W3015371109","https://openalex.org/W3133917823","https://openalex.org/W3175000095","https://openalex.org/W2916058012","https://openalex.org/W3145709712","https://openalex.org/W2936780106","https://openalex.org/W3046998876","https://openalex.org/W3211614993","https://openalex.org/W3108184206","https://openalex.org/W3163929126","https://openalex.org/W3015737406"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,6,29,33,53,83],"Lipreading":[3],"system,":[4],"i.e.":[5],"speech":[7,99],"recognition":[8,67],"system":[9,49],"using":[10],"only":[11,51,91],"visual":[12],"features,":[13],"which":[14,50],"uses":[15],"domain-adversarial":[16],"training":[17,22,103],"for":[18],"speaker":[19],"independence.":[20],"Domain-adversarial":[21],"is":[23],"integrated":[24],"into":[25],"the":[26,66,70,105],"optimization":[27],"of":[28,35,57,59,75,87,96],"lipreader":[30],"based":[31],"on":[32,69],"stack":[34],"feedforward":[36],"and":[37,78],"LSTM":[38],"(Long":[39],"Short-Term":[40],"Memory)":[41],"recurrent":[42],"neural":[43],"networks,":[44],"yielding":[45],"an":[46],"end-to-end":[47],"trainable":[48],"requires":[52],"very":[54],"small":[55],"number":[56],"frames":[58],"untranscribed":[60,97],"target":[61,71,79,98],"data":[62],"to":[63,93],"substantially":[64],"improve":[65],"accuracy":[68,85,106],"speaker.":[72],"On":[73,101],"pairs":[74],"different":[76],"source":[77],"speakers,":[80],"we":[81],"achieve":[82],"relative":[84],"improvement":[86],"around":[88],"40%":[89],"with":[90],"15":[92],"20":[94],"seconds":[95],"data.":[100],"multi-speaker":[102],"setups,":[104],"improvements":[107],"are":[108],"smaller":[109],"but":[110],"still":[111],"substantial.":[112]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}