{"id":"https://openalex.org/W2792175982","doi":"https://doi.org/10.1109/ialp.2017.8300540","title":"Transfer learning for children's speech recognition","display_name":"Transfer learning for children's speech recognition","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2792175982","doi":"https://doi.org/10.1109/ialp.2017.8300540","mag":"2792175982"},"language":"en","primary_location":{"id":"doi:10.1109/ialp.2017.8300540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2017.8300540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Asian Language Processing (IALP)","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/A5055221016","display_name":"Rong Tong","orcid":"https://orcid.org/0000-0003-3410-8354"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rong Tong","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107094040","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0001-8085-2374"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2392,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.85954478,"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":"36","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983000159263611,"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":0.9966999888420105,"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":0.7838033437728882},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.736835777759552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6858990788459778},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6587419509887695},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6238811612129211},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5266599059104919},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5106757283210754},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49810290336608887},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4541964828968048},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4432377219200134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4331710934638977},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3726131319999695},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10235735774040222}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838033437728882},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.736835777759552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6858990788459778},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6587419509887695},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6238811612129211},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5266599059104919},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5106757283210754},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49810290336608887},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4541964828968048},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4432377219200134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4331710934638977},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3726131319999695},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10235735774040222},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp.2017.8300540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2017.8300540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W88545716","https://openalex.org/W434092020","https://openalex.org/W2056914870","https://openalex.org/W2066972841","https://openalex.org/W2278264165","https://openalex.org/W2295983515","https://openalex.org/W2484174190","https://openalex.org/W2511419867","https://openalex.org/W2514528237","https://openalex.org/W2520176975","https://openalex.org/W2576204408","https://openalex.org/W2620869433","https://openalex.org/W2747764356","https://openalex.org/W2914746235","https://openalex.org/W2963303951","https://openalex.org/W2963522845","https://openalex.org/W6615059388","https://openalex.org/W6732026357"],"related_works":["https://openalex.org/W4206357785","https://openalex.org/W4281381188","https://openalex.org/W3192840557","https://openalex.org/W2951211570","https://openalex.org/W4375928479","https://openalex.org/W3167935049","https://openalex.org/W3023427754","https://openalex.org/W3131673289","https://openalex.org/W4393011546","https://openalex.org/W2821676139"],"abstract_inverted_index":{"Children's":[0],"speech":[1,17,25,71,87],"processing":[2],"is":[3,47,60,96,109],"more":[4],"challenging":[5],"than":[6],"that":[7,150,182],"of":[8,13,22],"adults":[9],"due":[10],"to":[11,67,97,110,167],"lacking":[12],"large":[14],"scale":[15],"children's":[16,37,69,86,125],"corpora.":[18],"With":[19],"the":[20,23,40,103,122,132,137,175,183,192,196],"developing":[21],"physical":[24],"organ,":[26],"high":[27],"inter":[28],"speaker":[29,32,144],"and":[30,56,124,161],"intra":[31],"variabilities":[33],"are":[34,128,140,155],"observed":[35],"in":[36,84,131,157,187],"speech.":[38],"On":[39],"other":[41],"hand,":[42],"data":[43],"collection":[44],"on":[45,102],"children":[46,50,168],"difficult":[48],"as":[49],"usually":[51],"have":[52],"short":[53],"attention":[54],"span":[55],"their":[57],"language":[58,194],"proficiency":[59],"limited.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"propose":[66],"improve":[68],"automatic":[70],"recognition":[72,88],"performance":[73,89],"with":[74,90,114,142],"transfer":[75,81,152],"learning":[76,82,120,153,172,198],"technique.":[77],"We":[78,179],"compare":[79],"two":[80],"approaches":[83,154],"enhancing":[85],"adults'":[91,123,165],"data.":[92],"The":[93,107,170],"first":[94],"method":[95],"perform":[98],"acoustic":[99,112,126,162,176,185],"model":[100,113,166],"adaptation":[101,177],"pre-trained":[104],"adult":[105],"model.":[106,169],"second":[108],"train":[111],"deep":[115],"neural":[116],"network":[117],"based":[118],"multi-task":[119,171,197],"approach:":[121],"characteristics":[127,186],"learnt":[129],"jointly":[130],"shared":[133],"hidden":[134],"layers,":[135],"while":[136],"output":[138],"layers":[139],"optimized":[141],"different":[143],"groups.":[145],"Our":[146],"experiment":[147],"results":[148],"show":[149,181],"both":[151],"effective":[156],"transferring":[158],"rich":[159],"phonetic":[160],"information":[163],"from":[164],"approach":[173],"outperforms":[174],"approach.":[178],"further":[180],"speakers'":[184],"languages":[188],"can":[189],"also":[190],"benefit":[191],"target":[193],"under":[195],"framework.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}