{"id":"https://openalex.org/W4221160950","doi":"https://doi.org/10.1109/icassp43922.2022.9746051","title":"r-G2P: Evaluating and Enhancing Robustness of Grapheme to Phoneme Conversion by Controlled Noise Introducing and Contextual Information Incorporation","display_name":"r-G2P: Evaluating and Enhancing Robustness of Grapheme to Phoneme Conversion by Controlled Noise Introducing and Contextual Information Incorporation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221160950","doi":"https://doi.org/10.1109/icassp43922.2022.9746051"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746051","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5068186778","display_name":"Chendong Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chendong Zhao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd","The Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"The Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100940847","display_name":"Xiaoyang Qu","orcid":"https://orcid.org/0009-0009-6311-4332"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyang Qu","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028229824","display_name":"Haoqian Wang","orcid":"https://orcid.org/0000-0003-2792-8469"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqian Wang","raw_affiliation_strings":["Tsinghua University,The Shenzhen International Graduate School,China","The Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,The Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6869,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86069834,"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":"6197","last_page":"6201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9990000128746033,"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":0.8896289467811584},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7955566644668579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7751784324645996},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6534636616706848},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.5802475214004517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5494949817657471},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5039462447166443},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4441063404083252},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42339611053466797},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.42257726192474365},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41698700189590454},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33347928524017334},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09219980239868164}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.8896289467811584},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7955566644668579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751784324645996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6534636616706848},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.5802475214004517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5494949817657471},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5039462447166443},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4441063404083252},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42339611053466797},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42257726192474365},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41698700189590454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33347928524017334},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09219980239868164},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746051","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"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":17,"referenced_works":["https://openalex.org/W2038110455","https://openalex.org/W2538246917","https://openalex.org/W2786672397","https://openalex.org/W2884873108","https://openalex.org/W2920834369","https://openalex.org/W2970279348","https://openalex.org/W2972437137","https://openalex.org/W3031895630","https://openalex.org/W3037167856","https://openalex.org/W3037474895","https://openalex.org/W3037485209","https://openalex.org/W3115229845","https://openalex.org/W3163936458","https://openalex.org/W3196787717","https://openalex.org/W4300996741","https://openalex.org/W6730161283","https://openalex.org/W6778966245"],"related_works":["https://openalex.org/W2100413842","https://openalex.org/W2382288502","https://openalex.org/W1562748605","https://openalex.org/W1598269872","https://openalex.org/W2501294752","https://openalex.org/W1983908775","https://openalex.org/W2758964148","https://openalex.org/W3206503703","https://openalex.org/W4296069123","https://openalex.org/W2123003832"],"abstract_inverted_index":{"Grapheme-to-phoneme":[0],"(G2P)":[1],"conversion":[2],"is":[3],"the":[4,8,40,81,85,95,110],"process":[5],"of":[6,11,42],"converting":[7],"written":[9],"form":[10],"words":[12],"to":[13,36,54,73,93],"their":[14],"pronunciations.":[15],"It":[16],"has":[17],"an":[18],"important":[19],"role":[20],"for":[21],"text-to-speech":[22],"(TTS)":[23],"synthesis":[24],"and":[25,38,87,118],"automatic":[26],"speech":[27],"recognition":[28],"(ASR)":[29],"systems.":[30],"In":[31],"this":[32,64],"paper,":[33],"we":[34,66,79],"aim":[35],"evaluate":[37],"enhance":[39],"robustness":[41],"G2P":[43,49,106],"models.":[44],"We":[45],"show":[46],"that":[47,102],"neural":[48],"models":[50],"are":[51],"extremely":[52],"sensitive":[53],"orthographical":[55],"variations":[56],"in":[57],"graphemes":[58],"like":[59],"spelling":[60],"mistakes.":[61],"To":[62],"solve":[63],"problem,":[65],"propose":[67,88],"three":[68],"controlled":[69],"noise":[70],"introducing":[71],"methods":[72],"synthesize":[74],"noisy":[75],"training":[76,91,96],"data.":[77],"Moreover,":[78],"incorporate":[80],"contextual":[82],"information":[83],"with":[84],"baseline":[86,111],"a":[89],"robust":[90,105],"strategy":[92],"stabilize":[94],"process.":[97],"The":[98],"experimental":[99],"results":[100],"demonstrate":[101],"our":[103],"proposed":[104],"model":[107],"(r-G2P)":[108],"outperforms":[109],"significantly":[112],"(-2.73%":[113],"WER":[114,120],"on":[115,121],"Dict-based":[116],"benchmarks":[117],"-9.09%":[119],"Real-world":[122],"sources).":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}