{"id":"https://openalex.org/W4391307834","doi":"https://doi.org/10.1109/icspcc59353.2023.10400287","title":"Unsupervised Forced Alignment on Syllable and Phoneme with Universal Phonetics Transcriptions","display_name":"Unsupervised Forced Alignment on Syllable and Phoneme with Universal Phonetics Transcriptions","publication_year":2023,"publication_date":"2023-11-14","ids":{"openalex":"https://openalex.org/W4391307834","doi":"https://doi.org/10.1109/icspcc59353.2023.10400287"},"language":"en","primary_location":{"id":"doi:10.1109/icspcc59353.2023.10400287","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icspcc59353.2023.10400287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","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/A5102405587","display_name":"Linjia Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linjia Sun","raw_affiliation_strings":["Beijing Language and Culture University,Faculty of Linguistic Sciences,Beijing,China","Faculty of Linguistic Sciences, Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University,Faculty of Linguistic Sciences,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"Faculty of Linguistic Sciences, Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5102405587"],"corresponding_institution_ids":["https://openalex.org/I115212828"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59877196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.964900016784668,"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":0.964900016784668,"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/syllable","display_name":"Syllable","score":0.7531394958496094},{"id":"https://openalex.org/keywords/phonetics","display_name":"Phonetics","score":0.7409558296203613},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6603843569755554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6205086708068848},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.53965824842453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46812477707862854},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.45910122990608215},{"id":"https://openalex.org/keywords/coda","display_name":"Coda","score":0.4323720932006836},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21193432807922363},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11525952816009521},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08661532402038574}],"concepts":[{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7531394958496094},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.7409558296203613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6603843569755554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6205086708068848},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.53965824842453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46812477707862854},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.45910122990608215},{"id":"https://openalex.org/C3962253","wikidata":"https://www.wikidata.org/wiki/Q852466","display_name":"Coda","level":2,"score":0.4323720932006836},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21193432807922363},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11525952816009521},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08661532402038574}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icspcc59353.2023.10400287","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icspcc59353.2023.10400287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W207695133","https://openalex.org/W239563548","https://openalex.org/W1556470778","https://openalex.org/W1998616086","https://openalex.org/W2075329984","https://openalex.org/W2097998348","https://openalex.org/W2284628133","https://openalex.org/W2345980057","https://openalex.org/W2747874407","https://openalex.org/W2808743435","https://openalex.org/W2917340025","https://openalex.org/W2963403664","https://openalex.org/W3127686677","https://openalex.org/W3146516924","https://openalex.org/W3196294373","https://openalex.org/W3216401400","https://openalex.org/W4205706554","https://openalex.org/W4224935349","https://openalex.org/W6674385629"],"related_works":["https://openalex.org/W2990721472","https://openalex.org/W2514064218","https://openalex.org/W2094188777","https://openalex.org/W2112609279","https://openalex.org/W2132658536","https://openalex.org/W1581825163","https://openalex.org/W2399404538","https://openalex.org/W2366310385","https://openalex.org/W2061937230","https://openalex.org/W1840920724"],"abstract_inverted_index":{"Forced":[0],"alignment":[1,87,108],"inputs":[2],"the":[3,11,20,30,35,49,55,60,67,82,86,110,117],"sound":[4],"recordings":[5],"and":[6,34,81,106],"transcription":[7],"texts,":[8],"then":[9],"outputs":[10],"temporal":[12],"boundaries":[13],"for":[14],"each":[15],"speech":[16],"unit.":[17],"Instead":[18],"of":[19,69,96,119],"special":[21],"phonemes":[22],"belong":[23],"to":[24,43,92,102],"specific":[25],"language,":[26,45],"this":[27],"work":[28],"uses":[29],"basic":[31],"syllable":[32],"types":[33],"broad":[36],"phonetic":[37],"classes":[38],"which":[39],"can":[40,89],"be":[41,90],"generalized":[42],"any":[44],"so":[46],"called":[47],"as":[48,66],"universal":[50],"phonetics":[51],"transcriptions.":[52],"We":[53],"adopt":[54],"Deep":[56],"Neural":[57],"Networks":[58],"with":[59],"Connectionist":[61],"Temporal":[62],"Classification":[63],"cost":[64],"function":[65],"solution":[68],"achieving":[70],"alignment.":[71,121],"The":[72],"evaluations":[73],"are":[74],"carried":[75],"out":[76],"on":[77],"six":[78],"different":[79],"languages":[80,97],"results":[83],"demonstrate":[84],"that":[85],"system":[88,112],"applied":[91],"a":[93],"wide":[94],"range":[95],"once":[98],"training":[99],"successful.":[100],"Compared":[101],"existing":[103],"state-of-the-art":[104],"supervised":[105],"unsupervised":[107],"system,":[109],"proposed":[111],"provides":[113],"competitive":[114],"performance":[115],"in":[116],"task":[118],"forced":[120]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}