{"id":"https://openalex.org/W4388821341","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317357","title":"RobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting Self-Supervised Representations","display_name":"RobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting Self-Supervised Representations","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388821341","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317357"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","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/A5092418416","display_name":"Neha Sahipjohn","orcid":"https://orcid.org/0009-0009-1101-8701"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neha Sahipjohn","raw_affiliation_strings":["CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad,India","CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad,India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101799872","display_name":"Neil Shah","orcid":"https://orcid.org/0000-0003-3261-8430"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]},{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neil Shah","raw_affiliation_strings":["CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad,India","TCS Research, Pune, India","CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad,India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"TCS Research, Pune, India","institution_ids":["https://openalex.org/I55215948"]},{"raw_affiliation_string":"CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088806439","display_name":"Vishal Tambrahalli","orcid":"https://orcid.org/0009-0008-1396-1106"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vishal Tambrahalli","raw_affiliation_strings":["CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad,India","CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad,India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067298540","display_name":"Vineet Gandhi","orcid":"https://orcid.org/0000-0001-8861-7731"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vineet Gandhi","raw_affiliation_strings":["CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad,India","CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad,India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5543,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65494614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1492","last_page":"1499"},"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":0.9955999851226807,"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":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8126342296600342},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7830724716186523},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7519124746322632},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7371698021888733},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6088886260986328},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5581164956092834},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5540652275085449},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5090200901031494},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42142045497894287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41895967721939087},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.35757607221603394},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06962165236473083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126342296600342},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7830724716186523},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7519124746322632},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7371698021888733},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6088886260986328},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5581164956092834},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5540652275085449},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5090200901031494},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42142045497894287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41895967721939087},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.35757607221603394},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06962165236473083},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W2014621385","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2141998673","https://openalex.org/W2194775991","https://openalex.org/W2516001803","https://openalex.org/W2585824449","https://openalex.org/W2898035430","https://openalex.org/W2949662773","https://openalex.org/W2963019222","https://openalex.org/W2963785710","https://openalex.org/W2964243274","https://openalex.org/W2964352155","https://openalex.org/W2972563022","https://openalex.org/W2981905048","https://openalex.org/W3033411150","https://openalex.org/W3035626590","https://openalex.org/W3092028330","https://openalex.org/W3096650361","https://openalex.org/W3104792420","https://openalex.org/W3140429000","https://openalex.org/W3157840621","https://openalex.org/W3160305627","https://openalex.org/W3180374548","https://openalex.org/W3203789665","https://openalex.org/W3209059054","https://openalex.org/W3211862173","https://openalex.org/W3213322812","https://openalex.org/W4200635083","https://openalex.org/W4220668493","https://openalex.org/W4221153068","https://openalex.org/W4224926225","https://openalex.org/W4225511340","https://openalex.org/W4226132755","https://openalex.org/W4283809657","https://openalex.org/W4285019302","https://openalex.org/W4289761690","https://openalex.org/W4292266560","https://openalex.org/W4296069328","https://openalex.org/W4311000453","https://openalex.org/W4312433898","https://openalex.org/W4321009928","https://openalex.org/W4372348072","https://openalex.org/W4375868850","https://openalex.org/W4385245566","https://openalex.org/W4385823403","https://openalex.org/W4386057728","https://openalex.org/W4386076005","https://openalex.org/W6752910514","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6803359641","https://openalex.org/W6810168380","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W1980604799","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2998781440"],"abstract_inverted_index":{"Significant":[0],"progress":[1],"has":[2],"been":[3],"made":[4],"in":[5],"speaker-dependent":[6],"Lip-to-Speech":[7,70],"synthesis,":[8],"which":[9],"aims":[10],"to":[11,28,48,81],"generate":[12],"speech":[13,52,86,93],"from":[14,35,123],"silent":[15],"videos":[16],"of":[17,51,84,103],"talking":[18],"faces.":[19],"Current":[20],"state-of-the-art":[21,107],"approaches":[22],"primarily":[23],"employ":[24],"non-autoregressive":[25,74],"sequence-to-sequence":[26,75],"architectures":[27],"directly":[29],"predict":[30],"mel-spectrograms":[31],"or":[32],"audio":[33],"waveforms":[34],"lip":[36],"representations.":[37],"We":[38],"hypothesize":[39],"that":[40],"the":[41,49,92,101,110,115],"direct":[42],"mel-prediction":[43],"hampers":[44],"training/model":[45],"efficiency":[46],"due":[47],"entanglement":[50],"content":[53],"with":[54],"ambient":[55],"information":[56],"and":[57,114,118],"speaker":[58],"characteristics.":[59],"To":[60],"this":[61],"end,":[62],"we":[63],"propose":[64],"RobustL2S,":[65],"a":[66,73,82],"modularized":[67],"framework":[68],"for":[69],"synthesis.":[71],"First,":[72],"model":[76],"maps":[77],"self-supervised":[78],"visual":[79],"features":[80,94],"representation":[83],"disentangled":[85],"content.":[87],"A":[88],"vocoder":[89],"then":[90],"converts":[91],"into":[95],"raw":[96],"waveforms.":[97],"Extensive":[98],"evaluations":[99],"confirm":[100],"effectiveness":[102],"our":[104],"setup,":[105],"achieving":[106],"performance":[108],"on":[109],"unconstrained":[111],"Lip2Wav":[112],"dataset":[113],"constrained":[116],"GRID":[117],"TCD-TIMIT":[119],"datasets.":[120],"Speech":[121],"samples":[122],"RobustL2S":[124],"can":[125],"be":[126],"found":[127],"at":[128],"https://neha-sherin.github.io/RobustL2S/":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}