{"id":"https://openalex.org/W4297841406","doi":"https://doi.org/10.21437/interspeech.2022-10964","title":"Transfer Learning for Robust Low-Resource Children's Speech ASR with Transformers and Source-Filter Warping","display_name":"Transfer Learning for Robust Low-Resource Children's Speech ASR with Transformers and Source-Filter Warping","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841406","doi":"https://doi.org/10.21437/interspeech.2022-10964"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10964","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10964","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/8772615/file/8772703.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022199264","display_name":"Jenthe Thienpondt","orcid":"https://orcid.org/0000-0001-5990-722X"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Jenthe Thienpondt","raw_affiliation_strings":["Department of Electronics and Information Systems, Ghent University -imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University -imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046536366","display_name":"Kris Demuynck","orcid":"https://orcid.org/0000-0001-8525-7160"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kris Demuynck","raw_affiliation_strings":["Department of Electronics and Information Systems, Ghent University -imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University -imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5022199264"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2213","last_page":"2217"},"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.9925000071525574,"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":0.8033341765403748},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6978765726089478},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6150593757629395},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.607831597328186},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.597140908241272},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5539577603340149},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4921643137931824},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45961496233940125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43445074558258057},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.42276108264923096},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4175108075141907},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36653614044189453},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.36632293462753296},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36219272017478943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8033341765403748},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6978765726089478},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6150593757629395},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.607831597328186},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.597140908241272},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5539577603340149},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4921643137931824},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45961496233940125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43445074558258057},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.42276108264923096},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4175108075141907},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36653614044189453},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.36632293462753296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36219272017478943},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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":2,"locations":[{"id":"doi:10.21437/interspeech.2022-10964","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10964","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:8772615","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-8772615","pdf_url":"https://biblio.ugent.be/publication/8772615/file/8772703.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISSN: 2308-457X","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:8772615","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-8772615","pdf_url":"https://biblio.ugent.be/publication/8772615/file/8772703.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISSN: 2308-457X","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297841406.pdf","grobid_xml":"https://content.openalex.org/works/W4297841406.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1540779870","https://openalex.org/W2046335163","https://openalex.org/W2066159843","https://openalex.org/W2099621636","https://openalex.org/W2100118853","https://openalex.org/W2120847449","https://openalex.org/W2130722890","https://openalex.org/W2152859600","https://openalex.org/W2160815625","https://openalex.org/W2181852881","https://openalex.org/W2193413348","https://openalex.org/W2511419867","https://openalex.org/W2514741789","https://openalex.org/W2899663614","https://openalex.org/W2908510526","https://openalex.org/W2936774411","https://openalex.org/W2941814890","https://openalex.org/W2973049979","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3093579165","https://openalex.org/W3094704668","https://openalex.org/W3097017391","https://openalex.org/W3097777922","https://openalex.org/W3174997050","https://openalex.org/W3198489108","https://openalex.org/W3213029956","https://openalex.org/W4206789583","https://openalex.org/W4210482569","https://openalex.org/W4244663218","https://openalex.org/W4287599777","https://openalex.org/W4287605195","https://openalex.org/W4302815339"],"related_works":["https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2152945827","https://openalex.org/W596245619","https://openalex.org/W114226241","https://openalex.org/W2015513221","https://openalex.org/W301864623","https://openalex.org/W2757826346","https://openalex.org/W2184371793"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1,183],"Recognition":[2],"(ASR)":[3],"systems":[4,42],"are":[5],"known":[6],"to":[7,19,27,54,72,85,100,139],"exhibit":[8],"difficulties":[9],"when":[10,37],"transcribing":[11],"children's":[12,24,39,80,101,170],"speech.":[13,81,102],"This":[14,82,120],"can":[15],"mainly":[16],"be":[17],"attributed":[18],"the":[20,33,67,74,87,123,151,159,178,190],"absence":[21],"of":[22,70,90,168],"large":[23],"speech":[25,40,71,92,137,171],"corpora":[26,93,138],"train":[28],"robust":[29,143],"ASR":[30,152],"models":[31],"and":[32,79,142,164],"resulting":[34],"domain":[35,75],"mismatch":[36],"decoding":[38],"with":[41,158,185],"trained":[43],"on":[44,66,112,117,133,177,189],"adult":[45,78,91,118,136,155],"data.":[46,119],"In":[47],"this":[48,105,148],"paper,":[49],"we":[50,59,108],"propose":[51,60],"multiple":[52],"enhancements":[53],"alleviate":[55],"these":[56,96],"issues.":[57],"First,":[58],"a":[61,113,128,165,186],"data":[62,88,156],"augmentation":[63,106],"technique":[64],"based":[65],"source-filter":[68,161],"model":[69,115,121,131,149],"close":[73],"gap":[76],"between":[77],"enables":[83],"us":[84],"leverage":[86],"availability":[89],"by":[94],"making":[95],"samples":[97],"perceptually":[98],"similar":[99],"Second,":[103],"using":[104,154],"strategy,":[107],"apply":[109],"transfer":[110],"learning":[111],"Transformer":[114],"pre-trained":[116,132],"follows":[122],"recently":[124],"introduced":[125],"XLS-R":[126],"architecture,":[127],"wav2vec":[129],"2.0":[130],"several":[134],"cross-lingual":[135],"learn":[140],"general":[141],"acoustic":[144],"frame-level":[145],"representations.":[146],"Adopting":[147],"for":[150],"task":[153],"augmented":[157],"proposed":[160],"warping":[162],"strategy":[163],"limited":[166],"amount":[167],"in-domain":[169],"significantly":[172],"outperforms":[173],"previous":[174],"state-of-the-art":[175],"results":[176],"PF-STAR":[179],"British":[180],"English":[181],"Children's":[182],"corpus":[184],"4.86%":[187],"WER":[188],"official":[191],"test":[192],"set.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}