{"id":"https://openalex.org/W3163936458","doi":"https://doi.org/10.1109/icassp39728.2021.9413679","title":"Joint Alignment Learning-Attention Based Model for Grapheme-to-Phoneme Conversion","display_name":"Joint Alignment Learning-Attention Based Model for Grapheme-to-Phoneme Conversion","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163936458","doi":"https://doi.org/10.1109/icassp39728.2021.9413679","mag":"3163936458"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5008226894","display_name":"Yonghe Wang","orcid":"https://orcid.org/0000-0003-1647-1539"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghe Wang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103077057","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0002-5426-2140"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"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":"7788","last_page":"7792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9983999729156494,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"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/grapheme","display_name":"Grapheme","score":0.969364583492279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8291946649551392},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6384360194206238},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6158405542373657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6146090626716614},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5981618165969849},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.49691179394721985},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.49487632513046265},{"id":"https://openalex.org/keywords/polarity","display_name":"Polarity (international relations)","score":0.4684446156024933},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4465833306312561},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.422147274017334},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3859345614910126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3386920392513275},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06688699126243591}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.969364583492279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8291946649551392},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6384360194206238},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6158405542373657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6146090626716614},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5981618165969849},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.49691179394721985},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.49487632513046265},{"id":"https://openalex.org/C2777361361","wikidata":"https://www.wikidata.org/wiki/Q1112585","display_name":"Polarity (international relations)","level":3,"score":0.4684446156024933},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4465833306312561},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.422147274017334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3859345614910126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3386920392513275},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06688699126243591},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C1491633281","wikidata":"https://www.wikidata.org/wiki/Q7868","display_name":"Cell","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W312219375","https://openalex.org/W1779680350","https://openalex.org/W1815076433","https://openalex.org/W1916501714","https://openalex.org/W2090755665","https://openalex.org/W2102113734","https://openalex.org/W2104770448","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2327501763","https://openalex.org/W2525778437","https://openalex.org/W2526425061","https://openalex.org/W2538246917","https://openalex.org/W2748157908","https://openalex.org/W2884873108","https://openalex.org/W2889026195","https://openalex.org/W2899771611","https://openalex.org/W2920834369","https://openalex.org/W2962824709","https://openalex.org/W2963299674","https://openalex.org/W2963609956","https://openalex.org/W2964308564","https://openalex.org/W3016151052","https://openalex.org/W3048768961","https://openalex.org/W3049756574","https://openalex.org/W3106690208","https://openalex.org/W6610937042","https://openalex.org/W6638545294","https://openalex.org/W6639972086","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6736996214","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W2060656088","https://openalex.org/W4385893898","https://openalex.org/W4285757703","https://openalex.org/W2383836440","https://openalex.org/W2610662399","https://openalex.org/W2509341624","https://openalex.org/W2057468170","https://openalex.org/W112480583","https://openalex.org/W2460550122"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"attention-based":[1,12,140],"models":[2],"for":[3],"grapheme-to-phoneme":[4],"(G2P)":[5],"conversion":[6,48,62,125],"have":[7],"gained":[8],"significant":[9],"interests.":[10],"The":[11],"encoder-decoder":[13],"framework":[14],"learns":[15],"the":[16,36,60,74,96,102,118,135],"mapping":[17],"of":[18,104],"input":[19],"to":[20,58,94],"output":[21],"tokens":[22],"by":[23,68],"selectively":[24],"focusing":[25],"on":[26,108],"relevant":[27],"information,":[28],"and":[29,91,99,110,139],"has":[30],"been":[31],"shown":[32],"well":[33],"performance.":[34,49],"However,":[35],"attention":[37,92],"mechanism":[38],"can":[39,121,131],"result":[40],"in":[41,45],"non-monotonic":[42],"alignments,":[43],"resulting":[44],"poor":[46],"G2P":[47,61,105,124],"In":[50],"this":[51],"paper,":[52],"we":[53,78],"present":[54],"a":[55,80,86],"novel":[56],"approach":[57],"optimize":[59],"model":[63,90,93,138],"directly":[64],"alignment":[65,70,88,115,136],"grapheme-phoneme":[66],"sequence":[67],"using":[69],"learning":[71,82,89,116],"(AL)":[72],"as":[73,117],"loss":[75,119],"function.":[76],"Besides,":[77],"propose":[79],"multi-task":[81,129],"method":[83,130],"that":[84,114],"uses":[85],"joint":[87],"predict":[95],"proper":[97],"alignments":[98],"thus":[100],"improve":[101],"accuracy":[103],"conversion.":[106],"Evaluations":[107],"Mongolian":[109],"CMUDict":[111],"tasks":[112],"show":[113],"function":[120],"effectively":[122],"train":[123],"model.":[126,141],"Further,":[127],"our":[128],"significantly":[132],"outperform":[133],"both":[134],"learning-based":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}