{"id":"https://openalex.org/W2803405196","doi":"https://doi.org/10.21437/interspeech.2018-1124","title":"Improved ASR for Under-resourced Languages through Multi-task Learning with Acoustic Landmarks","display_name":"Improved ASR for Under-resourced Languages through Multi-task Learning with Acoustic Landmarks","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2803405196","doi":"https://doi.org/10.21437/interspeech.2018-1124","mag":"2803405196"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5102958744","display_name":"Di He","orcid":"https://orcid.org/0000-0001-5185-7408"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Di He","raw_affiliation_strings":["***University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026225097","display_name":"Boon Pang Lim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boon Pang Lim","raw_affiliation_strings":["NovuMind Inc"],"affiliations":[{"raw_affiliation_string":"NovuMind Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059726557","display_name":"Xuesong Yang","orcid":"https://orcid.org/0000-0001-8625-5044"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuesong Yang","raw_affiliation_strings":["***University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056321228","display_name":"Deming Chen","orcid":"https://orcid.org/0000-0002-3016-0270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deming Chen","raw_affiliation_strings":["Information Trust Institute"],"affiliations":[{"raw_affiliation_string":"Information Trust Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102958744"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.4886,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71964822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2618","last_page":"2622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.998199999332428,"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":0.9950000047683716,"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":0.9836000204086304,"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/landmark","display_name":"Landmark","score":0.7778233885765076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7379008531570435},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7048435211181641},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5885549783706665},{"id":"https://openalex.org/keywords/articulator","display_name":"Articulator","score":0.5718992352485657},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5648433566093445},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5231978893280029},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.4190848469734192},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4188162386417389},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.41482013463974},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41021326184272766},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3519905209541321},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15774953365325928}],"concepts":[{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.7778233885765076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379008531570435},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7048435211181641},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5885549783706665},{"id":"https://openalex.org/C2778415344","wikidata":"https://www.wikidata.org/wiki/Q443216","display_name":"Articulator","level":2,"score":0.5718992352485657},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5648433566093445},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5231978893280029},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.4190848469734192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4188162386417389},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.41482013463974},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41021326184272766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3519905209541321},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15774953365325928},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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},{"id":"https://openalex.org/C29694066","wikidata":"https://www.wikidata.org/wiki/Q118301","display_name":"Orthodontics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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:10.21437/interspeech.2018-1124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2034310431","https://openalex.org/W2724655958","https://openalex.org/W2033140727","https://openalex.org/W4250529536","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"Furui":[0],"first":[1],"demonstrated":[2,55],"that":[3,21,32,56,180,190],"the":[4,15,25,59,66,70,105,116,171,184],"identity":[5],"of":[6,58,69,108,173],"both":[7,133],"consonant":[8],"and":[9,31,51,94,135,161],"vowel":[10],"can":[11,61,84],"be":[12,86],"perceived":[13],"from":[14,89],"C-V":[16],"transition;":[17],"later,":[18],"Stevens":[19],"proposed":[20],"acoustic":[22],"landmarks":[23,40,83,114],"are":[24,35,41,191],"primary":[26,67],"cues":[27],"for":[28,77,193],"speech":[29,81],"perception,":[30],"steady-state":[33],"regions":[34],"secondary":[36,117],"or":[37],"supplemental.":[38],"Acoustic":[39],"perceptually":[42],"salient,":[43],"even":[44],"in":[45,119,127],"a":[46,75,90,109,128],"language":[47,60,131,145],"one":[48],"doesn't":[49],"speak,":[50],"it":[52],"has":[53],"been":[54],"non-speakers":[57],"identify":[62],"features":[63,189],"such":[64],"as":[65,115],"articulator":[68],"landmark.":[71],"These":[72,177],"factors":[73],"suggest":[74,179],"strategy":[76],"developing":[78],"language-independent":[79],"automatic":[80],"recognition:":[82],"potentially":[85],"learned":[87],"once":[88],"suitably":[91],"labeled":[92],"corpus":[93],"rapidly":[95],"applied":[96],"to":[97,141,186],"many":[98],"other":[99],"languages.":[100],"This":[101],"paper":[102],"proposes":[103],"enhancing":[104],"cross-lingual":[106,194],"portability":[107],"neural":[110],"network":[111,124],"by":[112,158,167],"using":[113],"task":[118],"multi-task":[120],"learning":[121],"(MTL).":[122],"The":[123],"is":[125],"trained":[126],"well-resourced":[129],"source":[130],"with":[132,146],"phone":[134,155],"landmark":[136],"labels":[137,149],"(English),":[138],"then":[139],"adapted":[140],"an":[142],"under-resourced":[143],"target":[144],"only":[147],"word":[148,164],"(Iban).":[150],"Landmark-tasked":[151],"MTL":[152,182],"reduces":[153,162],"source-language":[154],"error":[156,165],"rate":[157,166],"2.9%":[159],"relative,":[160],"target-language":[163,174],"1.9%-5.9%":[168],"depending":[169],"on":[170],"amount":[172],"training":[175],"data.":[176],"results":[178],"landmark-tasked":[181],"causes":[183],"DNN":[185],"learn":[187],"hidden-node":[188],"useful":[192],"adaptation.":[195]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}