{"id":"https://openalex.org/W4402112557","doi":"https://doi.org/10.21437/interspeech.2024-19","title":"G2PA: G2P with Aligned Audio for Mandarin Chinese","display_name":"G2PA: G2P with Aligned Audio for Mandarin Chinese","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112557","doi":"https://doi.org/10.21437/interspeech.2024-19"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-19","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-19","pdf_url":"https://www.isca-archive.org/interspeech_2024/yang24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/yang24_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100442754","display_name":"Xingxing Yang","orcid":"https://orcid.org/0000-0001-7171-1617"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xingxing Yang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100442754"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3628,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5526135,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2800","last_page":"2804"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9550999999046326,"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/T10860","display_name":"Speech and Audio Processing","score":0.9143999814987183,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.9135228395462036},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6507390737533569},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4564956724643707},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12454617023468018}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.9135228395462036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6507390737533569},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4564956724643707},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12454617023468018},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-19","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-19","pdf_url":"https://www.isca-archive.org/interspeech_2024/yang24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-150001","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-150001","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-19","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-19","pdf_url":"https://www.isca-archive.org/interspeech_2024/yang24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402112557.pdf","grobid_xml":"https://content.openalex.org/works/W4402112557.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891"],"abstract_inverted_index":{"During":[0],"the":[1,15,49,61,86,96,129],"training":[2,16],"of":[3,22,64],"a":[4,104],"Mandarin":[5],"Chinese":[6,32],"Text-To-Speech":[7],"(TTS)":[8],"system,":[9],"it":[10],"is":[11],"necessary":[12],"to":[13,34,37,56,60,74,114],"preprocess":[14],"speech":[17],"data,":[18],"which":[19],"mainly":[20],"consists":[21],"audio":[23,88,110],"and":[24,111,119],"text":[25,50,112],"pairs.One":[26],"crucial":[27],"preprocessing":[28],"step":[29],"involves":[30],"converting":[31],"graphemes":[33],"phonemes":[35,43],"(G2P)":[36],"obtain":[38],"phoneme":[39],"representations":[40],"when":[41],"using":[42],"as":[44],"input.However,":[45],"relying":[46],"solely":[47,80],"on":[48,82],"for":[51,122],"G2P":[52,105],"conversion":[53],"may":[54],"lead":[55],"inaccurate":[57],"results":[58],"due":[59],"pronunciation":[62,116],"ambiguity":[63],"polyphones":[65],"-characters":[66],"with":[67],"multiple":[68],"pronunciations.Although":[69],"previous":[70],"research":[71],"has":[72],"attempted":[73],"address":[75],"this":[76,100],"issue,":[77],"most":[78],"approaches":[79],"rely":[81],"text-based":[83],"methods,":[84],"disregarding":[85],"valuable":[87],"information":[89],"that":[90,107],"can":[91],"only":[92],"be":[93],"captured":[94],"from":[95],"raw":[97],"audio.To":[98],"overcome":[99],"limitation,":[101],"we":[102],"propose":[103],"pipeline":[106],"leverages":[108],"both":[109],"inputs":[113],"resolve":[115],"ambiguity.The":[117],"code":[118],"model":[120],"weights":[121],"our":[123],"approach":[124],"are":[125],"publicly":[126],"available":[127],"at":[128],"following":[130],"GitHub":[131],"repository:":[132],"https://github.com/iooops/G2PA.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}
