{"id":"https://openalex.org/W4406461720","doi":"https://doi.org/10.1109/slt61566.2024.10832238","title":"Enhancing Low-Resource Spoken Language Identification Via Cross-Modality Retrieval and Cross-Lingual Text-to-Speech Synthesis","display_name":"Enhancing Low-Resource Spoken Language Identification Via Cross-Modality Retrieval and Cross-Lingual Text-to-Speech Synthesis","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461720","doi":"https://doi.org/10.1109/slt61566.2024.10832238"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5100782519","display_name":"Min Ma","orcid":"https://orcid.org/0009-0003-4466-4853"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Ma","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025935520","display_name":"Gary Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gary Wang","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037751863","display_name":"Kyle Kastner","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Kastner","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023109845","display_name":"Isaac Caswell","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Isaac Caswell","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017860475","display_name":"Charles H. Yoon","orcid":"https://orcid.org/0000-0003-1231-3840"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Yoon","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61428307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1193","last_page":"1200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T12031","display_name":"Speech and dialogue systems","score":0.9983000159263611,"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":0.796532928943634},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6300629377365112},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5869691371917725},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5353050827980042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4793868064880371},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4384925961494446},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4142889380455017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796532928943634},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6300629377365112},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5869691371917725},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5353050827980042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4793868064880371},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4384925961494446},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4142889380455017},{"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W2104457544","https://openalex.org/W2184343439","https://openalex.org/W2507923760","https://openalex.org/W2807627734","https://openalex.org/W2889169007","https://openalex.org/W2936774411","https://openalex.org/W2948978827","https://openalex.org/W2963604492","https://openalex.org/W2963846733","https://openalex.org/W2972473628","https://openalex.org/W2992384298","https://openalex.org/W3008480565","https://openalex.org/W3024464021","https://openalex.org/W3107298252","https://openalex.org/W3115778530","https://openalex.org/W3139918052","https://openalex.org/W3145003630","https://openalex.org/W3180180466","https://openalex.org/W3185627864","https://openalex.org/W3213618310","https://openalex.org/W4200475319","https://openalex.org/W4210327373","https://openalex.org/W4221155340","https://openalex.org/W4226033575","https://openalex.org/W4296068815","https://openalex.org/W4312095928","https://openalex.org/W4319862635","https://openalex.org/W4361194234","https://openalex.org/W4372259881","https://openalex.org/W4378105483","https://openalex.org/W4385822273","https://openalex.org/W4385822567","https://openalex.org/W4386825030","https://openalex.org/W4392903365","https://openalex.org/W4392909315","https://openalex.org/W6675409298","https://openalex.org/W6752688541","https://openalex.org/W6780218876","https://openalex.org/W6791904447","https://openalex.org/W6805710207","https://openalex.org/W6810259195","https://openalex.org/W6851468261","https://openalex.org/W6852391986","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762","https://openalex.org/W2793967660","https://openalex.org/W2361654993"],"abstract_inverted_index":{"Spoken":[0],"language":[1],"identification":[2],"(SLID)":[3],"for":[4,96],"low-resource":[5,53,108],"languages":[6,54],"remains":[7],"challenging":[8],"due":[9],"to":[10,22,99,103],"limited":[11],"data":[12,28,35,74,86,102],"availability.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17,48],"present":[18],"two":[19,46,90],"novel":[20],"approaches":[21],"address":[23],"the":[24,45,57],"issue:":[25],"cross-modality":[26],"retrieval-based":[27],"selection":[29],"and":[30,40,55,78],"cross-lingual":[31],"text-to-speech":[32],"(TTS)":[33],"based":[34],"augmentation.":[36],"Incorporating":[37],"semi-supervised":[38],"speech":[39,42],"synthetic":[41],"produced":[43],"by":[44,76],"methods,":[47],"successfully":[49],"enhance":[50,104],"SLID":[51,105],"on":[52,56],"full":[58],"set":[59],"of":[60,84],"target":[61],"languages,":[62],"at":[63],"a":[64,80],"publicly":[65],"available":[66],"YouTube-derived":[67],"dataset.":[68],"Our":[69],"best":[70],"recipe":[71],"reduces":[72],"training":[73,85],"amount":[75],"28%":[77],"ensures":[79],"more":[81],"balanced":[82],"distribution":[83],"across":[87],"languages.":[88],"The":[89],"general":[91],"frameworks":[92],"offer":[93],"innovative":[94],"strategies":[95],"leveraging":[97],"resources":[98],"add":[100],"valuable":[101],"in":[106],"extremely":[107],"scenarios.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}