{"id":"https://openalex.org/W4413553891","doi":"https://doi.org/10.1109/lsp.2025.3602636","title":"Can Layer-Wise SSL Features Improve Zero-Shot ASR Performance for Children\u2019s Speech?","display_name":"Can Layer-Wise SSL Features Improve Zero-Shot ASR Performance for Children\u2019s Speech?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413553891","doi":"https://doi.org/10.1109/lsp.2025.3602636"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3602636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3602636","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.21225","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101748731","display_name":"Abhijit Sinha","orcid":"https://orcid.org/0000-0003-3264-6319"},"institutions":[{"id":"https://openalex.org/I101326570","display_name":"National Institute of Technology Sikkim","ror":"https://ror.org/04pam3b03","country_code":"IN","type":"education","lineage":["https://openalex.org/I101326570"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhijit Sinha","raw_affiliation_strings":["Department of ECE, NIT Sikkim, Ravangla, India","Department of ECE, NIT, Sikkim, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of ECE, NIT Sikkim, Ravangla, India","institution_ids":["https://openalex.org/I101326570"]},{"raw_affiliation_string":"Department of ECE, NIT, Sikkim, India","institution_ids":["https://openalex.org/I101326570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003438160","display_name":"Hemant Kumar Kathania","orcid":"https://orcid.org/0000-0002-6367-5203"},"institutions":[{"id":"https://openalex.org/I101326570","display_name":"National Institute of Technology Sikkim","ror":"https://ror.org/04pam3b03","country_code":"IN","type":"education","lineage":["https://openalex.org/I101326570"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant Kumar Kathania","raw_affiliation_strings":["Department of ECE, NIT Sikkim, Ravangla, India","Department of ECE, NIT, Sikkim, India"],"raw_orcid":"https://orcid.org/0000-0002-6367-5203","affiliations":[{"raw_affiliation_string":"Department of ECE, NIT Sikkim, Ravangla, India","institution_ids":["https://openalex.org/I101326570"]},{"raw_affiliation_string":"Department of ECE, NIT, Sikkim, India","institution_ids":["https://openalex.org/I101326570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080870546","display_name":"Sudarsana Reddy Kadiri","orcid":"https://orcid.org/0000-0001-5806-3053"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210124484","display_name":"Directorate-General for Interpretation","ror":"https://ror.org/03728bb41","country_code":"BE","type":"government","lineage":["https://openalex.org/I1320481043","https://openalex.org/I2800387288","https://openalex.org/I4210124484"]}],"countries":["BE","US"],"is_corresponding":false,"raw_author_name":"Sudarsana Reddy Kadiri","raw_affiliation_strings":["Signal Analysis and Interpretation Lab (SAIL), University of Southern California, Los Angeles, CA, USA","Signal Analysis and Interpretation Lab (SAIL), University of Southern California, USA"],"raw_orcid":"https://orcid.org/0000-0001-5806-3053","affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Lab (SAIL), University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal Analysis and Interpretation Lab (SAIL), University of Southern California, USA","institution_ids":["https://openalex.org/I4210124484"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104114055","display_name":"Shrikanth Narayanan","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210124484","display_name":"Directorate-General for Interpretation","ror":"https://ror.org/03728bb41","country_code":"BE","type":"government","lineage":["https://openalex.org/I1320481043","https://openalex.org/I2800387288","https://openalex.org/I4210124484"]}],"countries":["BE","US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Signal Analysis and Interpretation Lab (SAIL), University of Southern California, Los Angeles, CA, USA","Signal Analysis and Interpretation Lab (SAIL), University of Southern California, USA"],"raw_orcid":"https://orcid.org/0000-0002-1052-6204","affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Lab (SAIL), University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal Analysis and Interpretation Lab (SAIL), University of Southern California, USA","institution_ids":["https://openalex.org/I4210124484"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6124,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93109323,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"3759","last_page":"3763"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9900000095367432,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9667999744415283,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6709244251251221},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5711656808853149},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5131722092628479},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.47463902831077576},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4126729965209961},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3322816491127014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31758642196655273},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07118883728981018}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6709244251251221},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5711656808853149},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5131722092628479},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.47463902831077576},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4126729965209961},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3322816491127014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31758642196655273},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07118883728981018},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2025.3602636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3602636","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2508.21225","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.21225","pdf_url":"https://arxiv.org/pdf/2508.21225","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.21225","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.21225","pdf_url":"https://arxiv.org/pdf/2508.21225","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W4411535265","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"systems":[4],"often":[5],"struggle":[6],"to":[7,13],"accurately":[8,39],"process":[9],"children's":[10,41,75,115],"speech":[11,42,76,116,124,132],"due":[12],"its":[14],"distinct":[15],"and":[16,20,66,129],"highly":[17],"variable":[18],"acoustic":[19],"linguistic":[21],"characteristics.":[22],"While":[23],"recent":[24],"advancements":[25],"in":[26,68,77,117,186],"self-supervised":[27],"learning":[28],"(SSL)":[29],"models":[30,60,88],"have":[31],"greatly":[32],"enhanced":[33],"the":[34,50,70,100,106,142,146,160,191,197,205,208],"transcription":[35],"of":[36,52,72,83,141,152,167,207],"adult":[37,123],"speech,":[38],"transcribing":[40],"remains":[43],"a":[44,94,118,155],"significant":[45,182],"challenge.":[46],"This":[47],"study":[48],"investigates":[49],"effectiveness":[51],"layer-wise":[53],"features":[54,84],"extracted":[55,85],"from":[56,86],"state-of-the-art":[57],"SSL":[58,192],"pre-trained":[59],"-":[61],"specifically,":[62],"Wav2Vec2,":[63],"HuBERT,":[64],"Data2Vec,":[65],"WavLM":[67],"improving":[69],"performance":[71,113,175],"ASR":[73,97,112],"for":[74,110,127,133],"zero-shot":[78,119,162],"scenarios.":[79],"A":[80],"detailed":[81],"analysis":[82,104,172],"these":[87],"was":[89,125],"conducted,":[90],"integrating":[91],"them":[92],"into":[93],"simplified":[95],"DNN-based":[96],"system":[98],"using":[99,164,190],"Kaldi":[101],"toolkit.":[102],"The":[103],"identified":[105],"most":[107],"effective":[108],"layers":[109],"enhancing":[111],"on":[114,196],"scenario,":[120],"where":[121],"WSJCAM0":[122],"used":[126],"training":[128],"PFSTAR":[130],"children":[131],"testing.":[134],"Experimental":[135],"results":[136],"indicated":[137],"that":[138],"Layer":[139],"22":[140],"Wav2Vec2":[143,165],"model":[144],"achieved":[145],"lowest":[147],"Word":[148],"Error":[149],"Rate":[150],"(WER)":[151],"5.15%,":[153],"representing":[154],"51.64%":[156],"relative":[157],"improvement":[158],"over":[159],"direct":[161],"decoding":[163],"(WER":[166],"10.65%).":[168],"Additionally,":[169],"age":[170,188],"group-wise":[171],"demonstrated":[173],"consistent":[174],"improvements":[176],"with":[177,181],"increasing":[178],"age,":[179],"along":[180],"gains":[183],"observed":[184],"even":[185],"younger":[187],"groups":[189],"features.":[193],"Further":[194],"experiments":[195],"CMU":[198],"Kids":[199],"dataset":[200],"confirmed":[201],"similar":[202],"trends,":[203],"highlighting":[204],"generalizability":[206],"proposed":[209],"approach.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}