{"id":"https://openalex.org/W4285172509","doi":"https://doi.org/10.1109/taslp.2022.3178238","title":"Autosegmental Neural Nets 2.0: An Extensive Study of Training Synchronous and Asynchronous Phones and Tones for Under-Resourced Tonal Languages","display_name":"Autosegmental Neural Nets 2.0: An Extensive Study of Training Synchronous and Asynchronous Phones and Tones for Under-Resourced Tonal Languages","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285172509","doi":"https://doi.org/10.1109/taslp.2022.3178238"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3178238","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3178238","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09783062.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09783062.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100456945","display_name":"Jialu Li","orcid":"https://orcid.org/0000-0003-0092-8071"},"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":"Jialu Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Beckman Institute of Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-0092-8071","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Beckman Institute of Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"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":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Beckman Institute of Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-5631-2893","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Beckman Institute of Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100456945"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.1387,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53632736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"30","issue":null,"first_page":"1918","last_page":"1926"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/phone","display_name":"Phone","score":0.7673532366752625},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.74976646900177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7186319828033447},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7132229208946228},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.7006760239601135},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6580252647399902},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6456945538520813},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6073377132415771},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48779040575027466},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4105564057826996},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.2275172472000122},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09789061546325684},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08846575021743774},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08844220638275146},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07633832097053528}],"concepts":[{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7673532366752625},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.74976646900177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7186319828033447},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7132229208946228},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.7006760239601135},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6580252647399902},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6456945538520813},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6073377132415771},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48779040575027466},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4105564057826996},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2275172472000122},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09789061546325684},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08846575021743774},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08844220638275146},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07633832097053528},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3178238","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3178238","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09783062.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2022.3178238","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3178238","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09783062.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285172509.pdf","grobid_xml":"https://content.openalex.org/works/W4285172509.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W34698122","https://openalex.org/W162654330","https://openalex.org/W1533416326","https://openalex.org/W1846073453","https://openalex.org/W1922655562","https://openalex.org/W1932968309","https://openalex.org/W1970890968","https://openalex.org/W1989235927","https://openalex.org/W2019183077","https://openalex.org/W2029520813","https://openalex.org/W2034970380","https://openalex.org/W2041252889","https://openalex.org/W2048804461","https://openalex.org/W2054990196","https://openalex.org/W2084534958","https://openalex.org/W2087395764","https://openalex.org/W2091746061","https://openalex.org/W2120209245","https://openalex.org/W2127141656","https://openalex.org/W2172661905","https://openalex.org/W2216396205","https://openalex.org/W2270959238","https://openalex.org/W2333604076","https://openalex.org/W2395416438","https://openalex.org/W2405962136","https://openalex.org/W2532186569","https://openalex.org/W2739062870","https://openalex.org/W2749455670","https://openalex.org/W2767722243","https://openalex.org/W2786031273","https://openalex.org/W2888990920","https://openalex.org/W2891816510","https://openalex.org/W2894835365","https://openalex.org/W2896092870","https://openalex.org/W2962768833","https://openalex.org/W2963027641","https://openalex.org/W2972686346","https://openalex.org/W2973049979","https://openalex.org/W3015877095","https://openalex.org/W3095732712","https://openalex.org/W3096673492","https://openalex.org/W3197278374","https://openalex.org/W3210532662","https://openalex.org/W4213082806","https://openalex.org/W4236088841","https://openalex.org/W4238817290","https://openalex.org/W4253120335","https://openalex.org/W4297808394","https://openalex.org/W6635375606","https://openalex.org/W6640090968","https://openalex.org/W6741819855","https://openalex.org/W6745595462","https://openalex.org/W6746278969","https://openalex.org/W6749352598","https://openalex.org/W6781366975","https://openalex.org/W6807204625","https://openalex.org/W6844194202","https://openalex.org/W7062624456"],"related_works":["https://openalex.org/W2116677773","https://openalex.org/W156219719","https://openalex.org/W2037167586","https://openalex.org/W2380756737","https://openalex.org/W4312574128","https://openalex.org/W1975726333","https://openalex.org/W2391999660","https://openalex.org/W2751304088","https://openalex.org/W2351099216","https://openalex.org/W2061937230"],"abstract_inverted_index":{"Phones,":[0],"the":[1,5,16,60,82,109,156,177,197,227],"segmental":[2],"units":[3],"in":[4,69,111,196],"International":[6],"Phonetic":[7],"Alphabet":[8],"(IPA),":[9],"include":[10],"isolated":[11],"consonants":[12],"or":[13,50,55],"vowels;":[14],"tones,":[15,210],"suprasegemental":[17],"units,":[18],"represent":[19],"pitch":[20],"and":[21,34,87,105,128,134,182,209,224],"voice":[22],"quality":[23],"movements":[24],"that":[25,120,132,161,179,229],"may":[26,41],"span":[27],"many":[28],"phones.":[29,129],"The":[30],"timings":[31],"of":[32,53,124,149,155,164,176],"tones":[33,40,127,165,181],"phones":[35,167,183,204,208],"are":[36,194],"loosely":[37],"connected,":[38],"e.g.,":[39],"be":[42],"synchronized":[43],"with":[44,166,206],"their":[45],"associated":[46],"vowels,":[47],"syllable":[48],"finals,":[49],"a":[51,112,146,159,219],"sequence":[52],"two":[54],"three":[56,212],"syllables":[57],"depending":[58],"on":[59,101,108],"language.":[61],"Many":[62],"past":[63],"studies":[64],"have":[65],"investigated":[66],"cross-lingual":[67,85,106,135,186],"adaptation":[68,86,192],"an":[70,95],"automatic":[71],"speech":[72],"recognition":[73],"(ASR)":[74],"tone-marked":[75,203],"phone":[76],"model,":[77],"yet":[78],"very":[79],"few":[80],"studied":[81],"interaction":[83],"between":[84,126],"tone-phone":[88,231],"synchronization.":[89],"In":[90,142,185],"this":[91],"study,":[92],"we":[93],"perform":[94],"extensive":[96],"study":[97],"by":[98],"multilingual":[99,133,143],"training":[100,136,140,151,157,201],"four":[102,117],"tonal":[103],"languages":[104],"testing":[107],"fifth,":[110],"five-fold":[113],"cross-validation":[114],"framework,":[115,222],"using":[116,218],"CTC-based":[118],"systems":[119,178],"impose":[121],"different":[122,139],"degrees":[123],"synchronization":[125,163],"We":[130],"discover":[131],"benefit":[137],"from":[138],"architectures.":[141],"training,":[144,187],"when":[145,189],"large":[147],"corpus":[148],"test-language":[150],"data":[152,193],"is":[153],"part":[154],"corpus,":[158],"system":[160,214,228],"requires":[162,230],"produces":[168],"significantly":[169,225],"lower":[170],"tone":[171],"error":[172],"rates":[173],"than":[174],"any":[175],"score":[180],"asynchronously.":[184],"however,":[188],"only":[190],"limited":[191],"available":[195],"test":[198],"language,":[199],"jointly":[200,216],"synchronous":[202],"together":[205],"asynchronous":[207],"as":[211],"separate":[213],"outputs":[215],"optimized":[217],"multi-task":[220],"learning":[221],"consistently":[223],"outperforms":[226],"synchrony.":[232]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}