{"id":"https://openalex.org/W7148284156","doi":"https://doi.org/10.1109/asru65441.2025.11434768","title":"Graph Connectionist Temporal Classification for Phoneme Recognition","display_name":"Graph Connectionist Temporal Classification for Phoneme Recognition","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148284156","doi":"https://doi.org/10.1109/asru65441.2025.11434768"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5119946754","display_name":"Henry Graf\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Henry Graf\u00e9","raw_affiliation_strings":["KU Leuven,Department of Electrical Engineering-ESAT,Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven,Department of Electrical Engineering-ESAT,Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124184730","display_name":"Hugo Van hamme","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hugo Van Hamme","raw_affiliation_strings":["KU Leuven,Department of Electrical Engineering-ESAT,Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven,Department of Electrical Engineering-ESAT,Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5119946754"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87549716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6258000135421753,"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":0.6258000135421753,"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":0.05310000106692314,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.03519999980926514,"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/connectionism","display_name":"Connectionism","score":0.8115000128746033},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7778000235557556},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.572700023651123},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5583999752998352},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5493000149726868},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5214999914169312},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4293000102043152},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4020000100135803}],"concepts":[{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.8115000128746033},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7778000235557556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745199978351593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6096000075340271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5853000283241272},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.572700023651123},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5583999752998352},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5493000149726868},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5214999914169312},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4129999876022339},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C13460635","wikidata":"https://www.wikidata.org/wiki/Q85753676","display_name":"Classification scheme","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8076944351196289,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2001800583","https://openalex.org/W2046932483","https://openalex.org/W2090755665","https://openalex.org/W2158791054","https://openalex.org/W2296417358","https://openalex.org/W2514741789","https://openalex.org/W2962780374","https://openalex.org/W3131881088","https://openalex.org/W3162833755","https://openalex.org/W4254960454","https://openalex.org/W4283025370","https://openalex.org/W4375869165","https://openalex.org/W4385822648","https://openalex.org/W4386025763","https://openalex.org/W4391021555"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"Phoneme":[1],"Recognition":[2],"(APR)":[3],"systems":[4,21,128],"are":[5],"often":[6],"trained":[7,107],"using":[8],"pseudo":[9],"phoneme-level":[10],"annotations":[11],"generated":[12],"from":[13,60,129],"text":[14],"through":[15],"Grapheme-to-Phoneme":[16],"(G2P)":[17],"systems.":[18],"These":[19,110],"G2P":[20],"frequently":[22],"output":[23],"multiple":[24,72,90],"possible":[25],"pronunciations":[26,73,91],"per":[27,74,92],"word,":[28],"but":[29],"the":[30,54,68,95,118],"standard":[31],"Connectionist":[32],"Temporal":[33,50],"Classification":[34,51],"(CTC)":[35],"loss":[36,97,119],"cannot":[37],"account":[38],"for":[39,125],"such":[40],"ambiguity":[41],"during":[42],"training.":[43],"In":[44],"this":[45],"work,":[46],"we":[47],"adapt":[48],"Graph":[49],"(GTC)":[52],"to":[53,70,104],"APR":[55,127],"setting.":[56],"GTC":[57],"enables":[58],"training":[59,96,126],"a":[61,105,122],"graph":[62],"of":[63],"alternative":[64],"phoneme":[65,100],"sequences,":[66],"allowing":[67],"model":[69],"consider":[71],"word":[75,93],"as":[76],"valid":[77],"supervision.":[78,132],"Our":[79],"experiments":[80],"on":[81],"English":[82],"and":[83],"Dutch":[84],"data":[85],"sets":[86],"show":[87],"that":[88,113],"incorporating":[89],"into":[94,117],"consistently":[98],"improves":[99],"error":[101],"rates":[102],"compared":[103],"baseline":[106],"with":[108],"CTC.":[109],"results":[111],"suggest":[112],"integrating":[114],"pronunciation":[115],"variation":[116],"function":[120],"is":[121],"promising":[123],"strategy":[124],"noisy":[130],"G2P-based":[131]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}