{"id":"https://openalex.org/W4392908955","doi":"https://doi.org/10.1109/icassp48485.2024.10446327","title":"Unsupervised Speech Recognition with N-skipgram and Positional Unigram Matching","display_name":"Unsupervised Speech Recognition with N-skipgram and Positional Unigram Matching","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908955","doi":"https://doi.org/10.1109/icassp48485.2024.10446327"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446327","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/A5058722770","display_name":"Liming Wang","orcid":"https://orcid.org/0000-0002-5562-8386"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liming Wang","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073287748","display_name":"Chang D. Yoo","orcid":"https://orcid.org/0000-0002-0756-7179"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I283854653","display_name":"Machine Intelligence Research Institute","ror":"https://ror.org/01h4ass90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I283854653"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","KR","US"],"is_corresponding":false,"raw_author_name":"Chang D. Yoo","raw_affiliation_strings":["KAIST,Artificial Intelligence and Machine Learning Lab","Artificial Intelligence and Machine Learning Lab, KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Artificial Intelligence and Machine Learning Lab","institution_ids":["https://openalex.org/I4210164862","https://openalex.org/I283854653"]},{"raw_affiliation_string":"Artificial Intelligence and Machine Learning Lab, KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6109,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71092302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10936","last_page":"10940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9480000138282776,"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":0.9480000138282776,"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/computer-science","display_name":"Computer science","score":0.723221480846405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6283494830131531},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5828555822372437},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5234396457672119},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4889329969882965},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09889298677444458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723221480846405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6283494830131531},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5828555822372437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5234396457672119},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4889329969882965},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09889298677444458},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446327","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/5","display_name":"Gender equality","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2055408826","https://openalex.org/W2962799131","https://openalex.org/W2962799225","https://openalex.org/W2972706021","https://openalex.org/W2995181338","https://openalex.org/W3036601975","https://openalex.org/W3096656254","https://openalex.org/W3198782837","https://openalex.org/W3204917342","https://openalex.org/W4287173589","https://openalex.org/W4293363567","https://openalex.org/W4296070453","https://openalex.org/W4297841354","https://openalex.org/W4319862440","https://openalex.org/W4319862670","https://openalex.org/W4385570746","https://openalex.org/W4385893869","https://openalex.org/W6757699909","https://openalex.org/W6780218876","https://openalex.org/W6795952400","https://openalex.org/W6852720755"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Training":[0],"unsupervised":[1],"speech":[2,13],"recognition":[3],"systems":[4],"presents":[5],"challenges":[6],"due":[7],"to":[8,40],"GAN-associated":[9],"instability,":[10],"misalignment":[11],"between":[12],"and":[14,16,68],"text,":[15],"significant":[17],"memory":[18],"demands.":[19],"To":[20],"tackle":[21],"these":[22],"challenges,":[23],"we":[24],"introduce":[25],"a":[26,51],"novel":[27],"ASR":[28,67],"system,":[29],"ESPUM.":[30],"This":[31],"system":[32],"harnesses":[33],"the":[34,58],"power":[35],"of":[36,54],"lower-order":[37],"N-skipgrams":[38],"(up":[39],"N":[41],"=":[42],"3)":[43],"combined":[44],"with":[45],"positional":[46],"unigram":[47],"statistics":[48],"gathered":[49],"from":[50],"small":[52],"batch":[53],"samples.":[55],"Evaluated":[56],"on":[57],"TIMIT":[59],"benchmark,":[60],"our":[61,73],"model":[62],"showcases":[63],"competitive":[64],"performance":[65],"in":[66],"phoneme":[69],"segmentation":[70],"tasks.":[71],"Access":[72],"publicly":[74],"available":[75],"code":[76],"at":[77],"https://github.com/lwang114/GraphUnsupASR.":[78]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}