{"id":"https://openalex.org/W2922328259","doi":"https://doi.org/10.1109/icassp.2019.8683225","title":"Phoneme Level Language Models for Sequence Based Low Resource ASR","display_name":"Phoneme Level Language Models for Sequence Based Low Resource ASR","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2922328259","doi":"https://doi.org/10.1109/icassp.2019.8683225","mag":"2922328259"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":true,"raw_author_name":"Siddharth Dalmia","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100660610","display_name":"Xinjian Li","orcid":"https://orcid.org/0000-0003-4585-159X"},"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":"Xinjian Li","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"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":"Alan W Black","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","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, Pittsburgh, PA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068873086"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.867,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80290718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6091","last_page":"6095"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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/T10028","display_name":"Topic Modeling","score":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8519114255905151},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6347715258598328},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5953370332717896},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5789780616760254},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.5566730499267578},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5519767999649048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5502219796180725},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5088622570037842},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49677664041519165},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4594475030899048},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.44280049204826355},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4231258034706116},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3579941987991333},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.27910393476486206},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.138838529586792},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13300469517707825},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12084603309631348},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.11679166555404663}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519114255905151},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6347715258598328},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5953370332717896},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5789780616760254},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.5566730499267578},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5519767999649048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5502219796180725},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5088622570037842},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49677664041519165},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4594475030899048},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.44280049204826355},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4231258034706116},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3579941987991333},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27910393476486206},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.138838529586792},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13300469517707825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12084603309631348},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.11679166555404663},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2229577770","display_name":null,"funder_award_id":"OCI-105357","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2922803762","display_name":null,"funder_award_id":"45606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6524269621","display_name":null,"funder_award_id":"OCI-1053575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6778350887","display_name":null,"funder_award_id":"1053575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"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/G8016956108","display_name":null,"funder_award_id":"HR0011-15-C-0114","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"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/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"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"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W160224403","https://openalex.org/W196214544","https://openalex.org/W1501286448","https://openalex.org/W1710082047","https://openalex.org/W1951216520","https://openalex.org/W1970890968","https://openalex.org/W1978660892","https://openalex.org/W2095650036","https://openalex.org/W2102113734","https://openalex.org/W2106440210","https://openalex.org/W2107223151","https://openalex.org/W2127141656","https://openalex.org/W2131042651","https://openalex.org/W2134054733","https://openalex.org/W2252095989","https://openalex.org/W2263232528","https://openalex.org/W2293858598","https://openalex.org/W2346660049","https://openalex.org/W2351252181","https://openalex.org/W2493916176","https://openalex.org/W2633221078","https://openalex.org/W2805993470","https://openalex.org/W2963211739","https://openalex.org/W2963292011","https://openalex.org/W2963537349","https://openalex.org/W2963946371","https://openalex.org/W2964170290","https://openalex.org/W6606555386","https://openalex.org/W6607974698","https://openalex.org/W6630162575","https://openalex.org/W6640820311","https://openalex.org/W6674357483","https://openalex.org/W6675365184","https://openalex.org/W6691537765","https://openalex.org/W6723250868","https://openalex.org/W6752124048"],"related_works":["https://openalex.org/W4255155614","https://openalex.org/W2394860946","https://openalex.org/W761725120","https://openalex.org/W2009170886","https://openalex.org/W2897427480","https://openalex.org/W2787311093","https://openalex.org/W2071315630","https://openalex.org/W1508853749","https://openalex.org/W1745277","https://openalex.org/W2147766635"],"abstract_inverted_index":{"Building":[0],"multilingual":[1],"and":[2,21,28,58,85,161,166],"crosslingual":[3,60],"models":[4,17,78,108,147],"help":[5],"bring":[6],"different":[7],"languages":[8,92],"together":[9],"in":[10,97,137,151],"a":[11,32,49,63,98,158],"language":[12,51,107,146,160],"universal":[13],"space.":[14],"It":[15],"allows":[16],"to":[18,31,62,91,112,123,157],"share":[19],"parameters":[20],"transfer":[22],"knowledge":[23],"across":[24],"languages,":[25],"enabling":[26],"faster":[27],"better":[29,89],"adaptation":[30,61,90],"new":[33,159],"language.":[34,65],"These":[35],"approaches":[36],"are":[37],"particularly":[38],"useful":[39],"for":[40,59],"low":[41,99],"resource":[42,100],"languages.":[43,139],"In":[44],"this":[45],"paper,":[46],"we":[47],"propose":[48],"phoneme-level":[50,106,145],"model":[52,70,121],"that":[53,68,104,143],"can":[54,109],"be":[55,110],"used":[56,111],"multilingually":[57],"target":[64],"We":[66,102,140],"show":[67,103,142],"our":[69],"performs":[71],"almost":[72],"as":[73,75],"well":[74],"the":[76],"monolingual":[77],"by":[79],"using":[80],"six":[81],"times":[82],"fewer":[83],"parameters,":[84],"is":[86],"capable":[87],"of":[88],"not":[93],"seen":[94],"during":[95],"training":[96,165],"scenario.":[101],"these":[105,144],"decode":[113],"sequence":[114],"based":[115,135],"Connectionist":[116],"Temporal":[117],"Classification":[118],"(CTC)":[119],"acoustic":[120],"outputs":[122],"obtain":[124],"comparable":[125],"word":[126],"error":[127],"rates":[128],"with":[129],"Weighted":[130],"Finite":[131],"State":[132],"Transducer":[133],"(WFST)":[134],"decoding":[136,150],"Babel":[138],"also":[141],"outperform":[148],"WFST":[149],"various":[152],"low-resource":[153],"conditions":[154],"like":[155],"adapting":[156],"domain":[162],"mismatch":[163],"between":[164],"testing":[167],"data.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}