{"id":"https://openalex.org/W4406461612","doi":"https://doi.org/10.1109/slt61566.2024.10832291","title":"Massively Multilingual Forced Aligner Leveraging Self-Supervised Discrete Units","display_name":"Massively Multilingual Forced Aligner Leveraging Self-Supervised Discrete Units","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461612","doi":"https://doi.org/10.1109/slt61566.2024.10832291"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Meta,USA"],"affiliations":[{"raw_affiliation_string":"Meta,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103110668","display_name":"Ilia Kulikov","orcid":"https://orcid.org/0000-0001-5989-9733"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilia Kulikov","raw_affiliation_strings":["Meta,USA"],"affiliations":[{"raw_affiliation_string":"Meta,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031088292","display_name":"Zhaoheng Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoheng Ni","raw_affiliation_strings":["Meta,USA"],"affiliations":[{"raw_affiliation_string":"Meta,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024195206","display_name":"Sravya Popuri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sravya Popuri","raw_affiliation_strings":["Meta,USA"],"affiliations":[{"raw_affiliation_string":"Meta,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027043104","display_name":"Paden Tomasello","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paden Tomasello","raw_affiliation_strings":["Meta,USA"],"affiliations":[{"raw_affiliation_string":"Meta,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040282669"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23803101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"899","last_page":"905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9800000190734863,"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":0.9800000190734863,"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":0.9596999883651733,"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/T11394","display_name":"Dynamics and Control of Mechanical Systems","score":0.9430000185966492,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.766568124294281},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5780025720596313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33636215329170227},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2581685185432434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766568124294281},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5780025720596313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33636215329170227},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2581685185432434}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1533416326","https://openalex.org/W2127141656","https://openalex.org/W2145410271","https://openalex.org/W2747874407","https://openalex.org/W2963250244","https://openalex.org/W3043783436","https://openalex.org/W3096524176","https://openalex.org/W3097945073","https://openalex.org/W3127686677","https://openalex.org/W3140429000","https://openalex.org/W3162249256","https://openalex.org/W3167895882","https://openalex.org/W3175665465","https://openalex.org/W3194000401","https://openalex.org/W3196001064","https://openalex.org/W3196294373","https://openalex.org/W3197777440","https://openalex.org/W3198270377","https://openalex.org/W3207272747","https://openalex.org/W3213029956","https://openalex.org/W4221163209","https://openalex.org/W4225956675","https://openalex.org/W4252812408","https://openalex.org/W4297727296","https://openalex.org/W4297841727","https://openalex.org/W4307933289","https://openalex.org/W4319862635","https://openalex.org/W4372260612","https://openalex.org/W4378105483","https://openalex.org/W4385245566","https://openalex.org/W4385570757","https://openalex.org/W4385822293","https://openalex.org/W4385823130","https://openalex.org/W4386908267","https://openalex.org/W4389600306","https://openalex.org/W4391272929","https://openalex.org/W4391673489","https://openalex.org/W4392902865","https://openalex.org/W4402111636","https://openalex.org/W4402301063","https://openalex.org/W6631362777","https://openalex.org/W6754747464","https://openalex.org/W6757817989","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6796656850","https://openalex.org/W6804030475","https://openalex.org/W6846355846","https://openalex.org/W6847363464","https://openalex.org/W6852909395","https://openalex.org/W6856887557","https://openalex.org/W6860417749","https://openalex.org/W6861267420","https://openalex.org/W6861618871"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W1970433854","https://openalex.org/W4396701345","https://openalex.org/W2023867642","https://openalex.org/W2376932109"],"abstract_inverted_index":{"We":[0,32,84],"propose":[1],"a":[2,14,37,40,87],"massively":[3],"multilingual":[4],"speech-to-text":[5],"neural":[6],"forced":[7,89],"aligner":[8,18,35,71],"that":[9,67],"supports":[10],"98":[11],"languages":[12],"with":[13],"single":[15],"architecture.":[16],"The":[17,49],"takes":[19],"self-supervised":[20],"discrete":[21],"acoustic":[22],"units":[23],"and":[24,61],"unnormalized":[25],"characters":[26],"including":[27],"punctuation":[28],"marks":[29],"as":[30,36],"inputs.":[31],"train":[33],"the":[34,68],"part":[38],"of":[39],"non-autoregressive":[41],"text-to-unit":[42],"(T2U)":[43],"model":[44,51],"without":[45],"any":[46],"external":[47],"aligner.":[48],"T2U":[50,70],"is":[52],"trained":[53],"on":[54,92],"speech-text":[55],"paired":[56],"data":[57],"in":[58],"various":[59],"domains":[60],"recording":[62],"conditions.":[63],"Experimental":[64],"evaluation":[65],"demonstrates":[66],"proposed":[69],"achieves":[72],"competitive":[73],"quality":[74],"to":[75],"existing":[76],"monolingual":[77],"aligners":[78],"while":[79],"supporting":[80],"much":[81],"more":[82],"languages.":[83,94],"also":[85],"showcase":[86],"zero-shot":[88],"alignment":[90],"capability":[91],"unseen":[93]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
