{"id":"https://openalex.org/W3207272747","doi":"https://doi.org/10.1109/icassp43922.2022.9746112","title":"Phone-to-Audio Alignment without Text: A Semi-Supervised Approach","display_name":"Phone-to-Audio Alignment without Text: A Semi-Supervised Approach","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207272747","doi":"https://doi.org/10.1109/icassp43922.2022.9746112","mag":"3207272747"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746112","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5022489629","display_name":"Jian Zhu","orcid":"https://orcid.org/0000-0002-7849-1060"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I1344076864","display_name":"Center for Applied Linguistics","ror":"https://ror.org/020pekv35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1344076864"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jian Zhu","raw_affiliation_strings":["University of Michigan,Department of Linguistics,Ann Arbor,USA","Department of Linguistics, University of Michigan, Ann Arbor, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Linguistics,Ann Arbor,USA","institution_ids":["https://openalex.org/I27837315","https://openalex.org/I1344076864"]},{"raw_affiliation_string":"Department of Linguistics, University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438374","display_name":"Cong Zhang","orcid":"https://orcid.org/0000-0002-0841-5476"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cong Zhang","raw_affiliation_strings":["Radboud University,Center for Language Studies,Nijmegen,Netherlands","Center for Language Studies, Radboud University, Nijmegen, Netherlands"],"affiliations":[{"raw_affiliation_string":"Radboud University,Center for Language Studies,Nijmegen,Netherlands","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Center for Language Studies, Radboud University, Nijmegen, Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046126345","display_name":"David Jurgens","orcid":"https://orcid.org/0000-0002-2135-9878"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Jurgens","raw_affiliation_strings":["University of Michigan,School of Information,Ann Arbor,USA","School of Information, University of Michigan, Ann Arbor, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,School of Information,Ann Arbor,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"School of Information, University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022489629"],"corresponding_institution_ids":["https://openalex.org/I1344076864","https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":3.6533,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94270419,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8167","last_page":"8171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8629747629165649},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.8253393769264221},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6134776473045349},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5843846797943115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5520161986351013},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5489634871482849},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5308666825294495},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5023887157440186},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47665196657180786},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4223538637161255}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8629747629165649},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.8253393769264221},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6134776473045349},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5843846797943115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5520161986351013},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5489634871482849},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5308666825294495},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5023887157440186},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47665196657180786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4223538637161255},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746112","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/305562","is_oa":false,"landing_page_url":"https://repository.ubn.ru.nl/handle/2066/305562","pdf_url":null,"source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2022, pp. 8167-8171","raw_type":"Article in monograph or in proceedings"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W267812377","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1556470778","https://openalex.org/W1566289585","https://openalex.org/W1635512741","https://openalex.org/W2127141656","https://openalex.org/W2296073425","https://openalex.org/W2747874407","https://openalex.org/W2748816379","https://openalex.org/W2767052532","https://openalex.org/W2808743435","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2963341956","https://openalex.org/W2972584841","https://openalex.org/W3016185664","https://openalex.org/W3026041220","https://openalex.org/W3030437843","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3043783436","https://openalex.org/W3096656254","https://openalex.org/W3099782249","https://openalex.org/W3112613336","https://openalex.org/W3130016944","https://openalex.org/W3169072315","https://openalex.org/W3194000401","https://openalex.org/W3196001064","https://openalex.org/W3196294373","https://openalex.org/W3197876970","https://openalex.org/W3198134274","https://openalex.org/W3198782837","https://openalex.org/W6603616073","https://openalex.org/W6609836551","https://openalex.org/W6631362777","https://openalex.org/W6633249632","https://openalex.org/W6745317255","https://openalex.org/W6755207826","https://openalex.org/W6771467084","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6787178341","https://openalex.org/W6800389019","https://openalex.org/W6800393981"],"related_works":["https://openalex.org/W3037187668","https://openalex.org/W2370205415","https://openalex.org/W4387493491","https://openalex.org/W2904225411","https://openalex.org/W4388331409","https://openalex.org/W2169921015","https://openalex.org/W2380685755","https://openalex.org/W3021540629","https://openalex.org/W2252100032","https://openalex.org/W4388446985"],"abstract_inverted_index":{"The":[0,24,55],"task":[1],"of":[2,106],"phone-to-audio":[3,22,32,109],"alignment":[4,33,74,98],"has":[5],"many":[6],"applications":[7],"in":[8],"speech":[9],"research.":[10],"Here":[11],"we":[12],"introduce":[13],"two":[14],"Wav2Vec2-based":[15],"models":[16,114],"for":[17],"both":[18,71,82],"text-dependent":[19],"and":[20,37,42,75,112],"text-independent":[21,53,76],"alignment.":[23,54,110],"proposed":[25,83],"Wav2Vec2-FS,":[26],"a":[27,38,47,60,103],"semi-supervised":[28],"model,":[29,57],"directly":[30],"learns":[31],"through":[34],"contrastive":[35],"learning":[36],"forward":[39],"sum":[40],"loss,":[41],"can":[43,70],"be":[44],"coupled":[45],"with":[46],"pretrained":[48,113],"phone":[49],"recognizer":[50],"to":[51,95],"achieve":[52],"other":[56],"Wav2Vec2-FC,":[58],"is":[59],"frame":[61],"classification":[62],"model":[63],"trained":[64],"on":[65],"forced":[66,73,97],"aligned":[67],"labels":[68],"that":[69,81],"perform":[72],"segmentation.":[77],"Evaluation":[78],"results":[79,94],"suggest":[80],"methods,":[84],"even":[85],"when":[86],"transcriptions":[87],"are":[88,115],"not":[89],"available,":[90],"generate":[91],"highly":[92],"close":[93],"existing":[96],"tools.":[99],"Our":[100],"work":[101],"presents":[102],"neural":[104],"pipeline":[105],"fully":[107],"automated":[108],"Code":[111],"available":[116],"at":[117],"https://github.com/lingjzhu/charsiu.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2021-10-25T00:00:00"}