{"id":"https://openalex.org/W3045876639","doi":"https://doi.org/10.21437/interspeech.2020-1834","title":"Autosegmental Neural Nets: Should Phones and Tones be Synchronous or Asynchronous?","display_name":"Autosegmental Neural Nets: Should Phones and Tones be Synchronous or Asynchronous?","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3045876639","doi":"https://doi.org/10.21437/interspeech.2020-1834","mag":"3045876639"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1834","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2007.14351","any_repository_has_fulltext":true},"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":false,"raw_author_name":"Jialu Li","raw_affiliation_strings":["***University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","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":["***University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1027","last_page":"1031"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.9983999729156494,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.7754151821136475},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7597347497940063},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7368085980415344},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7250684499740601},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.6027605533599854},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5534727573394775},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49018722772598267},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.46887683868408203},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.4335525929927826},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.42617255449295044},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42254722118377686},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.321109414100647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30463165044784546},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1234326958656311},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10200920701026917},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08022668957710266}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7754151821136475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7597347497940063},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7368085980415344},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7250684499740601},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.6027605533599854},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5534727573394775},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49018722772598267},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.46887683868408203},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.4335525929927826},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.42617255449295044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42254722118377686},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.321109414100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30463165044784546},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1234326958656311},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10200920701026917},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08022668957710266},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"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":3,"locations":[{"id":"doi:10.21437/interspeech.2020-1834","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"mag:3045876639","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2007.14351","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2007.14351","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.14351","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"mag:3045876639","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2007.14351","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W103244930","https://openalex.org/W1490144719","https://openalex.org/W1533416326","https://openalex.org/W1594337151","https://openalex.org/W1846073453","https://openalex.org/W1922655562","https://openalex.org/W1970890968","https://openalex.org/W1989235927","https://openalex.org/W2041252889","https://openalex.org/W2048804461","https://openalex.org/W2054990196","https://openalex.org/W2087395764","https://openalex.org/W2116952749","https://openalex.org/W2127141656","https://openalex.org/W2216396205","https://openalex.org/W2395416438","https://openalex.org/W2401720092","https://openalex.org/W2405962136","https://openalex.org/W2769437540","https://openalex.org/W2773798130","https://openalex.org/W2786031273","https://openalex.org/W2894835365","https://openalex.org/W2896092870","https://openalex.org/W2962768833","https://openalex.org/W2963027641","https://openalex.org/W2963260927","https://openalex.org/W2972686346","https://openalex.org/W3015877095","https://openalex.org/W3046810703"],"related_works":["https://openalex.org/W3096673492","https://openalex.org/W2752253036","https://openalex.org/W2050853835","https://openalex.org/W2112546487","https://openalex.org/W3195366621","https://openalex.org/W2606425707","https://openalex.org/W2587059930","https://openalex.org/W2012926658","https://openalex.org/W2803143571","https://openalex.org/W2972940133","https://openalex.org/W2149933119","https://openalex.org/W3020520193","https://openalex.org/W1977441313","https://openalex.org/W2988976008","https://openalex.org/W2097062477","https://openalex.org/W2792175982","https://openalex.org/W3014344307","https://openalex.org/W2282858960","https://openalex.org/W2109075312","https://openalex.org/W2523408806"],"abstract_inverted_index":{"Phones,":[0],"the":[1,5,20,24,49,74,121],"segmental":[2],"units":[3,22],"of":[4,23,38,54,76],"International":[6],"Phonetic":[7],"Alphabet":[8],"(IPA),":[9],"are":[10,26,85,106],"used":[11,27],"for":[12],"lexical":[13],"distinctions":[14],"in":[15,28,73,90,98,108,120,129],"most":[16],"human":[17],"languages;":[18],"Tones,":[19],"suprasegmental":[21],"IPA,":[25],"perhaps":[29],"70%.":[30],"Many":[31],"previous":[32],"studies":[33],"have":[34,47],"explored":[35,48],"cross-lingual":[36,52,112],"adaptation":[37],"automatic":[39],"speech":[40],"recognition":[41],"(ASR)":[42],"phone":[43],"models,":[44,71],"but":[45,125],"few":[46],"multilingual":[50,110],"and":[51,58,82,87,95,103,111],"transfer":[53],"synchronization":[55],"between":[56,80],"phones":[57,81],"tones.":[59,83],"In":[60],"this":[61],"paper,":[62],"we":[63],"test":[64],"four":[65],"Connectionist":[66],"Temporal":[67],"Classification":[68],"(CTC)-based":[69],"acoustic":[70],"differing":[72],"degree":[75],"synchrony":[77],"they":[78],"impose":[79],"Models":[84],"trained":[86],"tested":[88,96],"multilingually":[89],"three":[91],"languages,":[92],"then":[93],"adapted":[94],"cross-lingually":[97],"a":[99],"fourth.":[100],"Both":[101],"synchronous":[102],"asynchronous":[104,126],"models":[105,115],"effective":[107],"both":[109],"settings.":[113],"Synchronous":[114],"achieve":[116],"lower":[117,130],"error":[118,132],"rate":[119],"joint":[122],"phone+tone":[123],"tier,":[124],"training":[127],"results":[128],"tone":[131],"rate.":[133]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}