{"id":"https://openalex.org/W4408355411","doi":"https://doi.org/10.1109/icassp49660.2025.10887651","title":"Large Language Model Should Understand Pinyin for Chinese ASR Error Correction","display_name":"Large Language Model Should Understand Pinyin for Chinese ASR Error Correction","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355411","doi":"https://doi.org/10.1109/icassp49660.2025.10887651"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5032504077","display_name":"Yuang Li","orcid":"https://orcid.org/0000-0002-2244-0184"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuang Li","raw_affiliation_strings":["Huawei Translation Services Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065926428","display_name":"Xiaosong Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaosong Qiao","raw_affiliation_strings":["Huawei Translation Services Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025545388","display_name":"Xiaofeng Zhao","orcid":"https://orcid.org/0000-0003-0316-7220"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Zhao","raw_affiliation_strings":["Huawei Translation Services Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101537292","display_name":"Huan Zhao","orcid":"https://orcid.org/0000-0002-2233-164X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Zhao","raw_affiliation_strings":["Huawei Translation Services Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669938","display_name":"Wei Tang","orcid":"https://orcid.org/0000-0002-9371-375X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Tang","raw_affiliation_strings":["Huawei Translation Services Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Huawei Translation Services Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038736812","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0001-8861-7010"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Huawei Translation Services Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5379999876022339,"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":0.5379999876022339,"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/pinyin","display_name":"Pinyin","score":0.9662773609161377},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8174457550048828},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6344050765037537},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5398305058479309},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48676395416259766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4539785087108612},{"id":"https://openalex.org/keywords/chinese-language","display_name":"Chinese language","score":0.4172631502151489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3392001688480377},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2073228359222412},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1761396825313568},{"id":"https://openalex.org/keywords/chinese-characters","display_name":"Chinese characters","score":0.15207034349441528}],"concepts":[{"id":"https://openalex.org/C2781095461","wikidata":"https://www.wikidata.org/wiki/Q42222","display_name":"Pinyin","level":3,"score":0.9662773609161377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8174457550048828},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6344050765037537},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5398305058479309},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48676395416259766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4539785087108612},{"id":"https://openalex.org/C3018428822","wikidata":"https://www.wikidata.org/wiki/Q7850","display_name":"Chinese language","level":2,"score":0.4172631502151489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3392001688480377},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2073228359222412},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1761396825313568},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.15207034349441528},{"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:10.1109/icassp49660.2025.10887651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1904457459","https://openalex.org/W2127141656","https://openalex.org/W2963242190","https://openalex.org/W3202576380","https://openalex.org/W4210423654","https://openalex.org/W4221139374","https://openalex.org/W4287887857","https://openalex.org/W4387426216","https://openalex.org/W4389518985","https://openalex.org/W4389520395","https://openalex.org/W4391021773","https://openalex.org/W4392904683","https://openalex.org/W4393147304","https://openalex.org/W4402112066","https://openalex.org/W4402112460","https://openalex.org/W4402667093","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6680129566","https://openalex.org/W6771467084","https://openalex.org/W6796581206","https://openalex.org/W6846002521","https://openalex.org/W6847363464","https://openalex.org/W6854445763","https://openalex.org/W6859099255"],"related_works":["https://openalex.org/W2169386488","https://openalex.org/W2398174936","https://openalex.org/W1991876791","https://openalex.org/W64654948","https://openalex.org/W2274846632","https://openalex.org/W2370124224","https://openalex.org/W2555798330","https://openalex.org/W2606156333","https://openalex.org/W2098748517","https://openalex.org/W2376259296"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"can":[4],"enhance":[5],"automatic":[6],"speech":[7],"recognition":[8],"(ASR)":[9],"systems":[10],"through":[11],"generative":[12],"error":[13,38],"correction":[14],"(GEC).":[15],"In":[16],"this":[17],"paper,":[18],"we":[19,56,95],"propose":[20],"Pinyin-enhanced":[21],"GEC":[22,89],"(PY-GEC),":[23],"which":[24],"leverages":[25],"Pinyin\u2014the":[26],"phonetic":[27],"representation":[28],"of":[29,102],"Mandarin":[30],"Chinese\u2014as":[31],"supplementary":[32],"information":[33],"to":[34,69],"improve":[35],"Chinese":[36],"ASR":[37],"correction.":[39],"Our":[40],"approach":[41,61,86],"only":[42],"utilizes":[43],"synthetic":[44],"errors":[45],"for":[46,99],"training":[47,60,106],"and":[48,67,78,104,117,124],"employs":[49],"the":[50,76,79,100],"one-best":[51],"hypothesis":[52],"during":[53],"inference.":[54],"Additionally,":[55],"introduce":[57],"a":[58],"multitask":[59,105],"involving":[62],"conversion":[63],"tasks":[64],"between":[65,122],"Pinyin":[66,115,123],"text":[68,125],"align":[70],"their":[71],"feature":[72,120],"spaces.":[73],"Experiments":[74],"on":[75,114],"Aishell-1":[77],"Common":[80],"Voice":[81],"datasets":[82],"demonstrate":[83],"that":[84],"our":[85],"consistently":[87],"outperforms":[88],"with":[90],"text-only":[91],"input.":[92],"More":[93],"importantly,":[94],"provide":[96],"intuitive":[97],"explanations":[98],"effectiveness":[101],"PY-GEC":[103],"from":[107],"two":[108],"aspects:":[109],"1)":[110],"increased":[111],"attention":[112],"weight":[113],"features;":[116],"2)":[118],"aligned":[119],"space":[121],"hidden":[126],"states.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}