{"id":"https://openalex.org/W3196485121","doi":"https://doi.org/10.21437/interspeech.2021-1944","title":"Differentiable Allophone Graphs for Language-Universal Speech Recognition","display_name":"Differentiable Allophone Graphs for Language-Universal Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196485121","doi":"https://doi.org/10.21437/interspeech.2021-1944","mag":"3196485121"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1944","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021201726","display_name":"Brian Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Yan","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068873086","display_name":"Siddharth Dalmia","orcid":"https://orcid.org/0000-0003-0437-5988"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Dalmia","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059859009","display_name":"David R. Mortensen","orcid":"https://orcid.org/0000-0002-3927-6851"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David R. Mortensen","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2471","last_page":"2475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983999729156494,"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":0.9976999759674072,"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":0.8644336462020874},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.801882803440094},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7302543520927429},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5423153638839722},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4951900541782379},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.45712441205978394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45582661032676697},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14365434646606445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8644336462020874},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.801882803440094},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7302543520927429},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5423153638839722},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4951900541782379},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.45712441205978394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45582661032676697},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14365434646606445},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1944","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G367708065","display_name":null,"funder_award_id":"ACI-1548562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3709464396","display_name":null,"funder_award_id":"-1548562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3730782400","display_name":"XSEDE 2.0:  Integrating, Enabling and Enhancing National Cyberinfrastructure with Expanding Community Involvement","funder_award_id":"1548562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3760515176","display_name":null,"funder_award_id":"ACI-1548562","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7404166632","display_name":"Bridges: From Communities and Data to Workflows and Insight","funder_award_id":"1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8293170275","display_name":null,"funder_award_id":"ACI-1445606","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8729765517","display_name":null,"funder_award_id":"ACI-1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W63916190","https://openalex.org/W66627554","https://openalex.org/W1006203101","https://openalex.org/W1583636673","https://openalex.org/W1820426696","https://openalex.org/W1970890968","https://openalex.org/W2018466475","https://openalex.org/W2033436836","https://openalex.org/W2046932483","https://openalex.org/W2131042651","https://openalex.org/W2572670101","https://openalex.org/W2805993470","https://openalex.org/W2922328259","https://openalex.org/W2936774411","https://openalex.org/W2939069254","https://openalex.org/W2962684181","https://openalex.org/W2962728618","https://openalex.org/W2962780374","https://openalex.org/W2963211739","https://openalex.org/W2963292011","https://openalex.org/W2963431393","https://openalex.org/W2964002616","https://openalex.org/W2972741966","https://openalex.org/W2972830686","https://openalex.org/W2973094925","https://openalex.org/W2998284473","https://openalex.org/W3015877095","https://openalex.org/W3017568157","https://openalex.org/W3094197178","https://openalex.org/W3096032230","https://openalex.org/W3162833755","https://openalex.org/W3198165100","https://openalex.org/W4287647128","https://openalex.org/W4301037946"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W1607396156","https://openalex.org/W2776838583","https://openalex.org/W2114089658","https://openalex.org/W2061937230"],"abstract_inverted_index":{"Building":[0],"language-universal":[1],"speech":[2,18,82],"recognition":[3,83],"systems":[4,94],"entails":[5],"producing":[6],"phonological":[7],"units":[8],"of":[9,121,128],"spoken":[10],"sound":[11],"that":[12,111],"can":[13,99],"be":[14,100],"shared":[15],"across":[16],"languages.While":[17],"annotations":[19,30],"at":[20,31],"the":[21,118,125],"language-specific":[22],"phoneme":[23],"or":[24],"surface":[25],"levels":[26],"are":[27,36],"readily":[28],"available,":[29],"a":[32,47,79,133],"universal":[33,80],"phone":[34],"level":[35],"relatively":[37],"rare":[38],"and":[39,58,116],"difficult":[40],"to":[41,50,104],"produce.In":[42],"this":[43],"work,":[44],"we":[45,70,77],"present":[46],"general":[48],"framework":[49,131],"derive":[51],"phone-level":[52],"supervision":[53],"from":[54],"only":[55],"phonemic":[56],"transcriptions":[57],"phone-to-phoneme":[59,88],"mappings":[60,89,120],"with":[61,85,95,132],"learnable":[62],"weights":[63],"represented":[64],"using":[65],"weighted":[66],"finite-state":[67],"transducers,":[68],"which":[69],"call":[71],"differentiable":[72],"allophone":[73,97,119],"graphs.By":[74],"training":[75],"multilingually,":[76],"build":[78,108],"phone-based":[81,93,109],"model":[84],"interpretable":[86],"probabilistic":[87],"for":[90],"each":[91],"language.These":[92],"learned":[96],"graphs":[98],"used":[101],"by":[102],"linguists":[103],"document":[105],"new":[106],"languages,":[107],"lexicons":[110],"capture":[112],"rich":[113],"pronunciation":[114],"variations,":[115],"re-evaluate":[117],"seen":[122],"language.We":[123],"demonstrate":[124],"aforementioned":[126],"benefits":[127],"our":[129],"proposed":[130],"system":[134],"trained":[135],"on":[136],"7":[137],"diverse":[138],"languages.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}