{"id":"https://openalex.org/W3025823805","doi":"https://doi.org/10.1109/icassp39728.2021.9413806","title":"Reducing Spelling Inconsistencies in Code-Switching ASR Using Contextualized CTC Loss","display_name":"Reducing Spelling Inconsistencies in Code-Switching ASR Using Contextualized CTC Loss","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3025823805","doi":"https://doi.org/10.1109/icassp39728.2021.9413806","mag":"3025823805"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413806","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.07920","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012815898","display_name":"Burin Naowarat","orcid":"https://orcid.org/0000-0002-9327-5630"},"institutions":[{"id":"https://openalex.org/I158708052","display_name":"Chulalongkorn University","ror":"https://ror.org/028wp3y58","country_code":"TH","type":"education","lineage":["https://openalex.org/I158708052"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Burin Naowarat","raw_affiliation_strings":["Chulalongkorn University, Thailand","Chulalongkorn University,Department of Computer Engineering,Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chulalongkorn University, Thailand","institution_ids":["https://openalex.org/I158708052"]},{"raw_affiliation_string":"Chulalongkorn University,Department of Computer Engineering,Thailand","institution_ids":["https://openalex.org/I158708052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075394553","display_name":"Thananchai Kongthaworn","orcid":null},"institutions":[{"id":"https://openalex.org/I158708052","display_name":"Chulalongkorn University","ror":"https://ror.org/028wp3y58","country_code":"TH","type":"education","lineage":["https://openalex.org/I158708052"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Thananchai Kongthaworn","raw_affiliation_strings":["Chulalongkorn University, Thailand","Chulalongkorn University,Department of Computer Engineering,Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chulalongkorn University, Thailand","institution_ids":["https://openalex.org/I158708052"]},{"raw_affiliation_string":"Chulalongkorn University,Department of Computer Engineering,Thailand","institution_ids":["https://openalex.org/I158708052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033672325","display_name":"Korrawe Karunratanakul","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Korrawe Karunratanakul","raw_affiliation_strings":["ETH, Zurich, Switzerland","ETH Zurich, SWITZERLAND"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Zurich, SWITZERLAND","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074034864","display_name":"Sheng Hui Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Hui Wu","raw_affiliation_strings":["NewEra AI Robotics, Taiwan","NewEra AI Robotics,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NewEra AI Robotics, Taiwan","institution_ids":[]},{"raw_affiliation_string":"NewEra AI Robotics,Taiwan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030009288","display_name":"Ekapol Chuangsuwanich","orcid":"https://orcid.org/0000-0001-6104-4857"},"institutions":[{"id":"https://openalex.org/I158708052","display_name":"Chulalongkorn University","ror":"https://ror.org/028wp3y58","country_code":"TH","type":"education","lineage":["https://openalex.org/I158708052"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Ekapol Chuangsuwanich","raw_affiliation_strings":["Chulalongkorn University, Thailand","Chulalongkorn University,Department of Computer Engineering,Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chulalongkorn University, Thailand","institution_ids":["https://openalex.org/I158708052"]},{"raw_affiliation_string":"Chulalongkorn University,Department of Computer Engineering,Thailand","institution_ids":["https://openalex.org/I158708052"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6239","last_page":"6243"},"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":0.9988999962806702,"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/T12031","display_name":"Speech and dialogue systems","score":0.9986000061035156,"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":0.7989563941955566},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.6920510530471802},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5986277461051941},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5853379368782043},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5546746850013733},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5333858132362366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5232973694801331},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5152847766876221},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4796779155731201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4635407626628876},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45548903942108154},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.272175669670105},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21185585856437683},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1255410611629486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989563941955566},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.6920510530471802},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5986277461051941},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5853379368782043},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5546746850013733},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5333858132362366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5232973694801331},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5152847766876221},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4796779155731201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4635407626628876},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45548903942108154},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.272175669670105},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21185585856437683},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1255410611629486},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413806","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"},{"id":"pmh:oai:arXiv.org:2005.07920","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.07920","pdf_url":"https://arxiv.org/pdf/2005.07920","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2005.07920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.07920","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":"Preprint"},{"id":"doi:10.17023/wefv-v454","is_oa":true,"landing_page_url":"https://doi.org/10.17023/wefv-v454","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},{"id":"mag:3025823805","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.07920","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.07920","pdf_url":"https://arxiv.org/pdf/2005.07920","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3025823805.pdf","grobid_xml":"https://content.openalex.org/works/W3025823805.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1603614877","https://openalex.org/W2127141656","https://openalex.org/W2134800885","https://openalex.org/W2294692935","https://openalex.org/W2327501763","https://openalex.org/W2520160253","https://openalex.org/W2757910899","https://openalex.org/W2766219058","https://openalex.org/W2781384251","https://openalex.org/W2785450052","https://openalex.org/W2891816510","https://openalex.org/W2899073901","https://openalex.org/W2901739041","https://openalex.org/W2914699162","https://openalex.org/W2939069254","https://openalex.org/W2939757332","https://openalex.org/W2940180244","https://openalex.org/W2944150351","https://openalex.org/W2953190524","https://openalex.org/W2963336460","https://openalex.org/W2963946371","https://openalex.org/W2964121744","https://openalex.org/W2964139918","https://openalex.org/W2972417954","https://openalex.org/W2973170025","https://openalex.org/W3007376164","https://openalex.org/W3016108605","https://openalex.org/W3016240723","https://openalex.org/W3210505626","https://openalex.org/W6631190155","https://openalex.org/W6679855610","https://openalex.org/W6697843868","https://openalex.org/W6727336983","https://openalex.org/W6744513255","https://openalex.org/W6747270024","https://openalex.org/W6755461288","https://openalex.org/W6756104738","https://openalex.org/W6769143317","https://openalex.org/W6802928570"],"related_works":["https://openalex.org/W3137608412","https://openalex.org/W3011026370","https://openalex.org/W2096044632","https://openalex.org/W2981736866","https://openalex.org/W2759178327","https://openalex.org/W3171141812","https://openalex.org/W2131154411","https://openalex.org/W2897360952","https://openalex.org/W1589436371","https://openalex.org/W3037140546","https://openalex.org/W2916997151","https://openalex.org/W2803399609","https://openalex.org/W2901265786","https://openalex.org/W2396872757","https://openalex.org/W2029306354","https://openalex.org/W2963306023","https://openalex.org/W201413586","https://openalex.org/W3016199006","https://openalex.org/W3137599438","https://openalex.org/W3204996224"],"abstract_inverted_index":{"Code-Switching":[0],"(CS)":[1],"remains":[2],"a":[3,48,78],"challenge":[4],"for":[5,54],"Automatic":[6],"Speech":[7],"Recognition":[8],"(ASR),":[9],"especially":[10],"character-based":[11,25,49],"models.":[12],"With":[13],"the":[14,22,95,102,108,120],"combined":[15],"choice":[16],"of":[17,47,65],"characters":[18],"from":[19,24,28,101],"multiple":[20],"languages,":[21],"out-come":[23],"models":[26],"suffers":[27],"phoneme":[29],"duplication,":[30],"resulting":[31],"in":[32,77],"language-inconsistent":[33],"spellings.":[34],"We":[35],"propose":[36],"Contextualized":[37],"Connectionist":[38],"Temporal":[39],"Classification":[40],"(CCTC)":[41],"loss":[42,62,88],"to":[43,70,83,107],"encourage":[44],"spelling":[45],"consistencies":[46],"non-autoregressive":[50],"ASR":[51,121],"which":[52],"allows":[53],"faster":[55],"inference.":[56],"The":[57],"model":[58,110],"trained":[59,111],"by":[60],"CCTC":[61,87],"is":[63,99],"aware":[64],"contexts":[66],"since":[67,94],"it":[68],"learns":[69],"predict":[71],"both":[72,124],"center":[73],"and":[74,126],"surrounding":[75],"letters":[76],"multi-task":[79],"manner.":[80],"In":[81],"contrast":[82],"existing":[84],"CTC-based":[85],"approaches,":[86],"does":[89],"not":[90],"require":[91],"frame-level":[92],"alignments,":[93],"context":[96],"ground":[97],"truth":[98],"obtained":[100],"model\u2019s":[103],"estimated":[104],"path.":[105],"Compared":[106],"same":[109],"with":[112],"regular":[113],"CTC":[114],"loss,":[115],"our":[116],"method":[117],"consistently":[118],"improved":[119],"performance":[122],"on":[123],"CS":[125],"monolingual":[127],"corpora.":[128]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}