{"id":"https://openalex.org/W4387294077","doi":"https://doi.org/10.48550/arxiv.2309.17020","title":"Low-Resource Self-Supervised Learning with SSL-Enhanced TTS","display_name":"Low-Resource Self-Supervised Learning with SSL-Enhanced TTS","publication_year":2023,"publication_date":"2023-09-29","ids":{"openalex":"https://openalex.org/W4387294077","doi":"https://doi.org/10.48550/arxiv.2309.17020"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.17020","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.17020","pdf_url":"https://arxiv.org/pdf/2309.17020","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.17020","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034235870","display_name":"Po\u2010Chun Hsu","orcid":"https://orcid.org/0000-0002-6509-9377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsu, Po-chun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091764449","display_name":"Ali Elkahky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elkahky, Ali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsu, Wei-Ning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adi, Yossi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091817823","display_name":"Tu Anh Nguyen","orcid":"https://orcid.org/0000-0002-9623-042X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Tu Anh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020182193","display_name":"Jade Copet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Copet, Jade","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007620149","display_name":"Emmanuel Dupoux","orcid":"https://orcid.org/0000-0002-7814-2952"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dupoux, Emmanuel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Hung-yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101170706","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamed, Abdelrahman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9812999963760376,"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/T10028","display_name":"Topic Modeling","score":0.9606000185012817,"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":0.7673916816711426},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6481582522392273},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5232105255126953},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.45894280076026917},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4424494504928589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42503437399864197},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4217797517776489},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4207732081413269},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4164770245552063},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35254019498825073},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.348807156085968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7673916816711426},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6481582522392273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5232105255126953},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.45894280076026917},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4424494504928589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42503437399864197},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4217797517776489},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4207732081413269},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4164770245552063},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35254019498825073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.348807156085968},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.17020","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.17020","pdf_url":"https://arxiv.org/pdf/2309.17020","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":"doi:10.48550/arxiv.2309.17020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.17020","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:2309.17020","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.17020","pdf_url":"https://arxiv.org/pdf/2309.17020","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":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387294077.pdf","grobid_xml":"https://content.openalex.org/works/W4387294077.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2377717868","https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W2087783760","https://openalex.org/W2033364610","https://openalex.org/W3163689946","https://openalex.org/W2797776314","https://openalex.org/W2153927146","https://openalex.org/W2091066410"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,105],"(SSL)":[2],"techniques":[3],"have":[4],"achieved":[5],"remarkable":[6],"results":[7,69],"in":[8,18,106],"various":[9],"speech":[10,26,40,80,107],"processing":[11],"tasks.":[12],"Nonetheless,":[13],"a":[14,43,49,62],"significant":[15],"challenge":[16,36],"remains":[17],"reducing":[19],"the":[20,77,90,97],"reliance":[21],"on":[22],"vast":[23],"amounts":[24],"of":[25,92],"data":[27,81],"for":[28,66,79],"pre-training.":[29,67],"This":[30],"paper":[31],"proposes":[32],"to":[33,41,101],"address":[34],"this":[35,95],"by":[37,82],"leveraging":[38],"synthetic":[39,64],"augment":[42],"low-resource":[44,103],"pre-training":[45],"corpus.":[46],"We":[47],"construct":[48],"high-quality":[50],"text-to-speech":[51],"(TTS)":[52],"system":[53],"with":[54,84],"limited":[55],"resources":[56],"using":[57],"SSL":[58],"features":[59],"and":[60],"generate":[61],"large":[63],"corpus":[65],"Experimental":[68],"demonstrate":[70],"that":[71],"our":[72,93],"proposed":[73],"approach":[74],"effectively":[75],"reduces":[76],"demand":[78],"90%":[83],"only":[85],"slight":[86],"performance":[87],"degradation.":[88],"To":[89],"best":[91],"knowledge,":[94],"is":[96],"first":[98],"work":[99],"aiming":[100],"enhance":[102],"self-supervised":[104],"processing.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}