{"id":"https://openalex.org/W4319586124","doi":"https://doi.org/10.1109/iscslp57327.2022.10038220","title":"Improving Rare Words Recognition through Homophone Extension and Unified Writing for Low-resource Cantonese Speech Recognition","display_name":"Improving Rare Words Recognition through Homophone Extension and Unified Writing for Low-resource Cantonese Speech Recognition","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586124","doi":"https://doi.org/10.1109/iscslp57327.2022.10038220"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038220","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10038220","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5111114748","display_name":"Ho-Lam Chung","orcid":"https://orcid.org/0000-0003-3847-0166"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210159835","display_name":"Perceptive Engineering (United Kingdom)","ror":"https://ror.org/05qep9y26","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210159835"]}],"countries":["GB","TW"],"is_corresponding":false,"raw_author_name":"HoLam Chung","raw_affiliation_strings":["Centre for Perceptual and Interactive Intelligence (CPII),Hong Kong","Centre for Perceptual and Interactive Intelligence (CPII), Hong Kong","Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence (CPII),Hong Kong","institution_ids":["https://openalex.org/I4210159835"]},{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence (CPII), Hong Kong","institution_ids":[]},{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050398177","display_name":"Junan Li","orcid":"https://orcid.org/0009-0005-8133-7151"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4210159835","display_name":"Perceptive Engineering (United Kingdom)","ror":"https://ror.org/05qep9y26","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210159835"]}],"countries":["GB","HK"],"is_corresponding":false,"raw_author_name":"Junan Li","raw_affiliation_strings":["Centre for Perceptual and Interactive Intelligence (CPII),Hong Kong","Centre for Perceptual and Interactive Intelligence (CPII), Hong Kong","The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence (CPII),Hong Kong","institution_ids":["https://openalex.org/I4210159835"]},{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence (CPII), Hong Kong","institution_ids":[]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355025","display_name":"Pengfei Liu","orcid":"https://orcid.org/0009-0008-6932-7091"},"institutions":[{"id":"https://openalex.org/I4210159835","display_name":"Perceptive Engineering (United Kingdom)","ror":"https://ror.org/05qep9y26","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210159835"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pengfei Liu","raw_affiliation_strings":["Centre for Perceptual and Interactive Intelligence (CPII),Hong Kong","Centre for Perceptual and Interactive Intelligence (CPII), Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence (CPII),Hong Kong","institution_ids":["https://openalex.org/I4210159835"]},{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence (CPII), Hong Kong","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078785570","display_name":"Wai-Kim Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159835","display_name":"Perceptive Engineering (United Kingdom)","ror":"https://ror.org/05qep9y26","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210159835"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wai-Kim Leung","raw_affiliation_strings":["Centre for Perceptual and Interactive Intelligence (CPII),Hong Kong","Centre for Perceptual and Interactive Intelligence (CPII), Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence (CPII),Hong Kong","institution_ids":["https://openalex.org/I4210159835"]},{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence (CPII), Hong Kong","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4210159835","display_name":"Perceptive Engineering (United Kingdom)","ror":"https://ror.org/05qep9y26","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210159835"]}],"countries":["GB","HK"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["Centre for Perceptual and Interactive Intelligence (CPII),Hong Kong","Centre for Perceptual and Interactive Intelligence (CPII), Hong Kong","The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence (CPII),Hong Kong","institution_ids":["https://openalex.org/I4210159835"]},{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence (CPII), Hong Kong","institution_ids":[]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4210159835","display_name":"Perceptive Engineering (United Kingdom)","ror":"https://ror.org/05qep9y26","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210159835"]}],"countries":["GB","HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Centre for Perceptual and Interactive Intelligence (CPII),Hong Kong","Centre for Perceptual and Interactive Intelligence (CPII), Hong Kong","The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence (CPII),Hong Kong","institution_ids":["https://openalex.org/I4210159835"]},{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence (CPII), Hong Kong","institution_ids":[]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1687,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47197156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.998199999332428,"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/homophone","display_name":"Homophone","score":0.9641939401626587},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8179323673248291},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6941218376159668},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5459139347076416},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5354779958724976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5135335922241211},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.47913452982902527},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1576908826828003}],"concepts":[{"id":"https://openalex.org/C160253069","wikidata":"https://www.wikidata.org/wiki/Q221079","display_name":"Homophone","level":2,"score":0.9641939401626587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8179323673248291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6941218376159668},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5459139347076416},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5354779958724976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5135335922241211},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.47913452982902527},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1576908826828003},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10038220","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10038220","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2493916176","https://openalex.org/W2766219058","https://openalex.org/W2936695845","https://openalex.org/W2937402758","https://openalex.org/W2963240019","https://openalex.org/W2963626623","https://openalex.org/W2963827914","https://openalex.org/W3015927303","https://openalex.org/W3036601975","https://openalex.org/W3109311991","https://openalex.org/W3162244132","https://openalex.org/W3198442913","https://openalex.org/W3213029956","https://openalex.org/W4223954171","https://openalex.org/W4226316089","https://openalex.org/W4226495108","https://openalex.org/W6675365184","https://openalex.org/W6687566353","https://openalex.org/W6761205521","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6786752982","https://openalex.org/W6811717302","https://openalex.org/W6847376785"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1769849273","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W1967477266","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817"],"abstract_inverted_index":{"Homophone":[0],"characters":[1,27,82],"are":[2,21],"common":[3],"in":[4],"tonal":[5],"syllable-based":[6],"languages,":[7],"such":[8],"as":[9],"Mandarin":[10],"and":[11,28,83,111,122,137],"Cantonese.":[12],"The":[13],"data-intensive":[14],"end-to-end":[15],"Automatic":[16],"Speech":[17],"Recognition":[18],"(ASR)":[19],"systems":[20],"more":[22,90,98],"likely":[23],"to":[24,50,76],"mis-recognize":[25],"homophone":[26,47,56,109],"rare":[29],"words":[30],"under":[31],"low-resource":[32,38],"settings.":[33],"For":[34],"the":[35,55,59,78,101,115],"problem":[36],"of":[37,54,80,93,134],"Cantonese":[39,81],"speech":[40,85],"recognition,":[41],"this":[42],"paper":[43],"presents":[44],"a":[45],"novel":[46],"extension":[48,110],"method":[49,75],"integrate":[51],"human":[52],"knowledge":[53],"lexicon":[57],"into":[58],"beam":[60],"search":[61],"decoding":[62],"process":[63],"with":[64,126],"language":[65],"model":[66],"re-scoring.":[67],"Besides,":[68],"we":[69],"propose":[70],"an":[71,127],"automatic":[72],"unified":[73,112],"writing":[74,113],"merge":[77],"variants":[79],"standardize":[84],"annotation":[86],"guidelines,":[87],"which":[88],"enables":[89],"efficient":[91],"utilization":[92],"labeled":[94],"utterances":[95],"by":[96],"providing":[97],"samples":[99],"for":[100],"merged":[102],"characters.":[103],"We":[104],"empirically":[105],"show":[106],"that":[107],"both":[108,120],"improve":[114],"recognition":[116],"performance":[117],"significantly":[118],"on":[119],"in-domain":[121],"out-of-domain":[123],"test":[124],"sets,":[125],"absolute":[128],"Character":[129],"Error":[130],"Rate":[131],"(CER)":[132],"decrease":[133],"around":[135],"5%":[136],"18%.":[138]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}