{"id":"https://openalex.org/W4385807478","doi":"https://doi.org/10.21437/interspeech.2023-2031","title":"Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition","display_name":"Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385807478","doi":"https://doi.org/10.21437/interspeech.2023-2031"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2031","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"conference-paper","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/A5014918159","display_name":"Saurabh Kataria","orcid":"https://orcid.org/0000-0001-6311-2155"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Saurabh Kataria","raw_affiliation_strings":["Center for Language and Speech Processing,","Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Villalba","raw_affiliation_strings":["Center for Language and Speech Processing,","Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069488212","display_name":"Laureano Moro-Vel\u00e1zquez","orcid":"https://orcid.org/0000-0002-3033-7005"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Laureano Moro-Velazquez","raw_affiliation_strings":["Center for Language and Speech Processing,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040324682","display_name":"Thomas Thebaud","orcid":"https://orcid.org/0000-0001-8953-7872"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Thomas Thebaud","raw_affiliation_strings":["Center for Language and Speech Processing,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA","Center for Language and Speech Processing,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4688","last_page":"4692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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":0.9923999905586243,"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":0.8023276925086975},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.5418781042098999},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5028538107872009},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4907432794570923},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.4653637409210205},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4588497281074524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45702052116394043},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44758880138397217},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.4213706851005554},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37860649824142456},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.16149267554283142},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11521828174591064},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.10045665502548218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8023276925086975},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.5418781042098999},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5028538107872009},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4907432794570923},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4653637409210205},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4588497281074524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45702052116394043},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44758880138397217},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.4213706851005554},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37860649824142456},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.16149267554283142},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11521828174591064},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.10045665502548218},{"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/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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":1,"locations":[{"id":"doi:10.21437/interspeech.2023-2031","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2125389028","https://openalex.org/W2292087804","https://openalex.org/W2593414223","https://openalex.org/W2734498959","https://openalex.org/W2952218014","https://openalex.org/W2963371159","https://openalex.org/W2972369255","https://openalex.org/W2981087920","https://openalex.org/W2982037672","https://openalex.org/W3024301174","https://openalex.org/W3025443576","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3095410713","https://openalex.org/W3160972914","https://openalex.org/W3163827866","https://openalex.org/W3198429080","https://openalex.org/W3198771897","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211264909","https://openalex.org/W4221145109","https://openalex.org/W4226380987","https://openalex.org/W4283010431","https://openalex.org/W4283067253","https://openalex.org/W4283215837","https://openalex.org/W4297632162","https://openalex.org/W4297841594","https://openalex.org/W4297841773","https://openalex.org/W4319862462","https://openalex.org/W4385245566","https://openalex.org/W4385489023"],"related_works":["https://openalex.org/W2059847929","https://openalex.org/W2089600072","https://openalex.org/W2152250293","https://openalex.org/W2005289539","https://openalex.org/W2069820990","https://openalex.org/W2046937923","https://openalex.org/W2031518249","https://openalex.org/W4319862422","https://openalex.org/W3007114974","https://openalex.org/W2526308500"],"abstract_inverted_index":{"Speech":[0],"super-resolution/Bandwidth":[1],"Extension":[2],"(BWE)":[3],"can":[4,39],"improve":[5],"downstream":[6],"tasks":[7],"like":[8],"Automatic":[9],"Speaker":[10],"Verification":[11],"(ASV).We":[12],"introduce":[13],"a":[14,101],"simple":[15],"novel":[16],"technique":[17],"called":[18],"Self-FiLM":[19],"to":[20,99],"inject":[21],"self-supervision":[22],"into":[23],"existing":[24],"BWE":[25],"models":[26,76,83],"via":[27],"Feature-wise":[28],"Linear":[29],"Modulation.We":[30],"hypothesize":[31],"that":[32,105],"such":[33],"information":[34],"captures":[35],"domain/environment":[36],"information,":[37],"which":[38],"give":[40],"zero-shot":[41],"generalization.Self-FiLM":[42],"Conditional":[43],"GAN":[44],"(CGAN)":[45],"gives":[46],"18%":[47],"relative":[48],"improvement":[49],"in":[50,56],"Equal":[51],"Error":[52],"Rate":[53],"and":[54,77,88],"8.5%":[55],"minimum":[57],"Decision":[58],"Cost":[59],"Function":[60],"using":[61],"state-ofthe-art":[62],"ASV":[63],"system":[64],"on":[65,84],"SRE21":[66],"test.We":[67],"further":[68],"by":[69],"1)":[70],"deep":[71],"feature":[72],"loss":[73],"from":[74],"time-domain":[75],"2)":[78],"re-training":[79],"of":[80],"data2vec":[81],"2.0":[82],"naturalistic":[85],"wideband":[86],"(VoxCeleb)":[87],"telephone":[89],"data":[90],"(SRE":[91],"Superset":[92],"etc.).Lastly,":[93],"we":[94],"integrate":[95],"selfsupervision":[96],"with":[97],"CycleGAN":[98],"present":[100],"completely":[102],"unsupervised":[103],"solution":[104],"matches":[106],"the":[107],"semi-supervised":[108],"performance.":[109]},"counts_by_year":[],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}
