{"id":"https://openalex.org/W3023351797","doi":"https://doi.org/10.21437/interspeech.2020-1113","title":"Seeing Voices and Hearing Voices: Learning Discriminative Embeddings Using Cross-Modal Self-Supervision","display_name":"Seeing Voices and Hearing Voices: Learning Discriminative Embeddings Using Cross-Modal Self-Supervision","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3023351797","doi":"https://doi.org/10.21437/interspeech.2020-1113","mag":"3023351797"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1113","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1113","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.14326","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046276512","display_name":"Soo-Whan Chung","orcid":"https://orcid.org/0000-0001-6529-2196"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Soo-Whan Chung","raw_affiliation_strings":["Department of Electrical & Electronic Engineering, Yonsei University, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & Electronic Engineering, Yonsei University, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Department of Electrical & Electronic Engineering, Yonsei University, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & Electronic Engineering, Yonsei University, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046276512"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":5.1809,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.96499378,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"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":0.9990000128746033,"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":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8843874931335449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7803149819374084},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7796244621276855},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6947067379951477},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6332377195358276},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.609869122505188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5573778748512268},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5135076642036438},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.481370747089386},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47903671860694885},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4768194556236267},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4414719343185425},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42010512948036194},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3811100125312805}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8843874931335449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803149819374084},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7796244621276855},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6947067379951477},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6332377195358276},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.609869122505188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5573778748512268},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5135076642036438},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.481370747089386},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47903671860694885},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4768194556236267},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4414719343185425},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42010512948036194},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3811100125312805},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1113","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1113","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:2004.14326","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.14326","pdf_url":"https://arxiv.org/pdf/2004.14326","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.14326","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.14326","pdf_url":"https://arxiv.org/pdf/2004.14326","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":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1686810756","https://openalex.org/W1934184906","https://openalex.org/W1974783905","https://openalex.org/W1983685275","https://openalex.org/W2068678037","https://openalex.org/W2070176749","https://openalex.org/W2100495367","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2157331557","https://openalex.org/W2166563626","https://openalex.org/W2326925005","https://openalex.org/W2327501763","https://openalex.org/W2479368705","https://openalex.org/W2555897561","https://openalex.org/W2598915960","https://openalex.org/W2604379605","https://openalex.org/W2726515241","https://openalex.org/W2793493229","https://openalex.org/W2796992393","https://openalex.org/W2803113447","https://openalex.org/W2808631503","https://openalex.org/W2809716557","https://openalex.org/W2949517790","https://openalex.org/W2952746495","https://openalex.org/W2962788625","https://openalex.org/W2962824366","https://openalex.org/W2962898354","https://openalex.org/W2962918445","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963173190","https://openalex.org/W2963420272","https://openalex.org/W2963680395","https://openalex.org/W2963801643","https://openalex.org/W2963887950","https://openalex.org/W2964048159","https://openalex.org/W2964308564","https://openalex.org/W2969985801","https://openalex.org/W2979157532","https://openalex.org/W3013020904","https://openalex.org/W3015734344","https://openalex.org/W3016663370","https://openalex.org/W3043075211","https://openalex.org/W3108655343","https://openalex.org/W3116298410"],"related_works":["https://openalex.org/W2811048914","https://openalex.org/W1982479144","https://openalex.org/W1995633573","https://openalex.org/W2767198796","https://openalex.org/W3208297503","https://openalex.org/W3119773509","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353"],"abstract_inverted_index":{"The":[0,77,108],"goal":[1],"of":[2,74,79],"this":[3,51],"work":[4,38],"is":[5,82],"to":[6,13,39],"train":[7,40],"discriminative":[8,45],"cross-modal":[9,32,105],"embeddings":[10,41],"without":[11],"access":[12],"manually":[14],"annotated":[15],"data.":[16],"Recent":[17],"advances":[18],"in":[19],"self-supervised":[20,113],"learning":[21],"have":[22],"shown":[23],"that":[24,42,59],"effective":[25],"representations":[26],"can":[27],"be":[28],"learnt":[29],"from":[30],"natural":[31],"synchrony.":[33],"We":[34],"build":[35],"on":[36,84,94],"earlier":[37],"are":[43],"more":[44],"for":[46,104],"uni-modal":[47],"downstream":[48,86],"tasks.":[49],"To":[50],"end,":[52],"we":[53],"propose":[54],"a":[55,116],"novel":[56],"training":[57],"strategy":[58],"not":[60],"only":[61],"optimises":[62],"metrics":[63],"across":[64],"modalities,":[65],"but":[66],"also":[67],"enforces":[68],"intra-class":[69],"feature":[70],"separation":[71],"within":[72],"each":[73],"the":[75,80,91,101],"modalities.":[76],"effectiveness":[78],"method":[81,110],"demonstrated":[83],"two":[85],"tasks:":[87],"lip":[88],"reading":[89],"using":[90,100],"features":[92,102],"trained":[93,103],"audio-visual":[95],"synchronisation,":[96],"and":[97],"speaker":[98],"recognition":[99],"biometric":[106],"matching.":[107],"proposed":[109],"outperforms":[111],"state-of-the-art":[112],"baselines":[114],"by":[115],"signficant":[117],"margin.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}