{"id":"https://openalex.org/W4392908960","doi":"https://doi.org/10.1109/icassp48485.2024.10446275","title":"Data Driven Grapheme-to-Phoneme Representations for a Lexicon-Free Text-to-Speech","display_name":"Data Driven Grapheme-to-Phoneme Representations for a Lexicon-Free Text-to-Speech","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908960","doi":"https://doi.org/10.1109/icassp48485.2024.10446275"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5043920881","display_name":"Abhinav Garg","orcid":"https://orcid.org/0000-0001-5082-5500"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abhinav Garg","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396580","display_name":"Jiyeon Kim","orcid":"https://orcid.org/0000-0001-7964-5060"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiyeon Kim","raw_affiliation_strings":["Samsung Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000241755","display_name":"Sushil Khyalia","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sushil Khyalia","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100684422","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-0193-8167"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113125574","display_name":"Dhananjaya Gowda","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhananjaya Gowda","raw_affiliation_strings":["Samsung Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5043920881"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.9878,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78310247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"11091","last_page":"11095"},"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":0.996999979019165,"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":0.9965000152587891,"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":0.9572042226791382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7685607671737671},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7683838605880737},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6564793586730957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5683156847953796},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5163689851760864}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.9572042226791382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7685607671737671},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7683838605880737},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6564793586730957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5683156847953796},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5163689851760864},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1593247906","https://openalex.org/W2262393948","https://openalex.org/W2519091744","https://openalex.org/W2892009249","https://openalex.org/W2903739847","https://openalex.org/W2920834369","https://openalex.org/W2963299674","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972426539","https://openalex.org/W2972437137","https://openalex.org/W2997454826","https://openalex.org/W3095867028","https://openalex.org/W3096758108","https://openalex.org/W3162308011","https://openalex.org/W3198848374","https://openalex.org/W3209059054","https://openalex.org/W4212774754","https://openalex.org/W4224629880","https://openalex.org/W4226052192","https://openalex.org/W6778083308","https://openalex.org/W6780218876","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W2060656088","https://openalex.org/W4385893898","https://openalex.org/W4285757703","https://openalex.org/W2383836440","https://openalex.org/W2610662399","https://openalex.org/W4391124013","https://openalex.org/W1831473261","https://openalex.org/W4293870971","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Grapheme-to-Phoneme":[0],"(G2P)":[1],"is":[2],"an":[3,68],"essential":[4],"first":[5],"step":[6],"in":[7,87,135],"any":[8],"modern,":[9],"high-quality":[10],"Text-to-Speech":[11],"(TTS)":[12],"system.":[13],"Most":[14],"of":[15,80,96,137],"the":[16,34,51,62,128],"current":[17],"G2P":[18],"systems":[19],"rely":[20],"on":[21],"carefully":[22],"hand-crafted":[23],"lexicons":[24,35],"developed":[25],"by":[26,83],"experts.":[27],"This":[28],"poses":[29],"a":[30,39,109],"two-fold":[31],"problem.":[32],"Firstly,":[33],"are":[36,71],"generated":[37],"using":[38,84,143],"fixed":[40,97],"phoneme":[41,93,149],"set,":[42,150],"usually,":[43],"ARPABET":[44],"or":[45,123,131,148],"IPA,":[46],"which":[47],"might":[48],"not":[49],"be":[50],"most":[52],"optimal":[53],"way":[54],"to":[55,65,90],"represent":[56],"phonemes":[57],"for":[58],"all":[59],"languages.":[60],"Secondly,":[61],"man-hours":[63],"required":[64],"produce":[66],"such":[67],"expert":[69],"lexicon":[70,147],"very":[72],"high.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77,113],"eliminate":[78],"both":[79],"these":[81],"issues":[82],"recent":[85],"advances":[86],"self-supervised":[88],"learning":[89],"obtain":[91],"data-driven":[92,117],"representations":[94],"instead":[95],"representations.":[98],"We":[99],"compare":[100],"our":[101,116],"lexicon-free":[102,118],"approach":[103],"against":[104],"strong":[105],"baselines":[106],"that":[107,115],"utilize":[108],"well-crafted":[110],"lexicon.":[111],"Furthermore,":[112],"show":[114],"method":[119],"performs":[120],"as":[121],"good":[122],"even":[124],"marginally":[125],"better":[126],"than":[127],"conventional":[129],"rule-based":[130],"lexicon-based":[132],"neural":[133],"G2Ps":[134],"terms":[136],"Mean":[138],"Opinion":[139],"Score":[140],"(MOS)":[141],"while":[142],"no":[144,152],"prior":[145],"language":[146],"i.e.":[151],"linguistic":[153],"expertise.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}