{"id":"https://openalex.org/W4372270126","doi":"https://doi.org/10.1109/icassp49357.2023.10096988","title":"Wav2Seq: Pre-Training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","display_name":"Wav2Seq: Pre-Training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372270126","doi":"https://doi.org/10.1109/icassp49357.2023.10096988"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5074393700","display_name":"Felix Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Wu","raw_affiliation_strings":["ASAPP Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052377938","display_name":"Kwangyoun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwangyoun Kim","raw_affiliation_strings":["ASAPP Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106859201","display_name":"Kyu J. Han","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyu J. Han","raw_affiliation_strings":["ASAPP Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022489655","display_name":"Ryan McDonald","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan McDonald","raw_affiliation_strings":["ASAPP Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006380227","display_name":"Kilian Q. Weinberger","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]},{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kilian Q. Weinberger","raw_affiliation_strings":["ASAPP Inc","Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047026141","display_name":"Yoav Artzi","orcid":"https://orcid.org/0000-0002-4605-6144"},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]},{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yoav Artzi","raw_affiliation_strings":["ASAPP Inc","Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8948,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.96088345,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9990000128746033,"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":0.8728517293930054},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7530864477157593},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6731662750244141},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6453445553779602},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5968412160873413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.565157413482666},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.546390950679779},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5229433178901672},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49633365869522095},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4787242114543915},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.47210708260536194},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46540623903274536},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4647476077079773},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4430299401283264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8728517293930054},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7530864477157593},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6731662750244141},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6453445553779602},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5968412160873413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.565157413482666},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.546390950679779},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5229433178901672},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49633365869522095},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4787242114543915},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.47210708260536194},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46540623903274536},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4647476077079773},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4430299401283264},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2073459066","https://openalex.org/W2101234009","https://openalex.org/W2130942839","https://openalex.org/W2142838865","https://openalex.org/W2327501763","https://openalex.org/W2520160253","https://openalex.org/W2549416390","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2914417638","https://openalex.org/W2933138175","https://openalex.org/W2953190524","https://openalex.org/W2962780374","https://openalex.org/W2963347649","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2995181338","https://openalex.org/W3001434439","https://openalex.org/W3034999214","https://openalex.org/W3036601975","https://openalex.org/W3054645415","https://openalex.org/W3095173472","https://openalex.org/W3095918555","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3160799772","https://openalex.org/W3173767661","https://openalex.org/W3197580070","https://openalex.org/W3198299542","https://openalex.org/W3198429080","https://openalex.org/W3200129129","https://openalex.org/W3205644108","https://openalex.org/W3213029956","https://openalex.org/W4221145109","https://openalex.org/W4226103796","https://openalex.org/W4226278833","https://openalex.org/W4287887773","https://openalex.org/W4288089799","https://openalex.org/W4297808394","https://openalex.org/W4372270126","https://openalex.org/W4394671563","https://openalex.org/W6601894380","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6668990524","https://openalex.org/W6675354045","https://openalex.org/W6679436768","https://openalex.org/W6727336983","https://openalex.org/W6729239390","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6769627184","https://openalex.org/W6780218876","https://openalex.org/W6781927165","https://openalex.org/W6790356757","https://openalex.org/W6795346631","https://openalex.org/W6810007534","https://openalex.org/W6850036870"],"related_works":["https://openalex.org/W2404510748","https://openalex.org/W3089218859","https://openalex.org/W2794347674","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361","https://openalex.org/W2003020325"],"abstract_inverted_index":{"We":[0,17,57,71],"introduce":[1],"Wav2Seq,":[2],"the":[3,118],"first":[4],"self-supervised":[5,30],"approach":[6,106],"to":[7,110,124],"pre-train":[8],"both":[9],"parts":[10,116],"of":[11,117],"encoder-decoder":[12,108],"models":[13],"for":[14,76,90,101,114],"speech":[15,32,61],"data.":[16],"induce":[18],"a":[19,23,29],"pseudo":[20,31,40],"language":[21,88],"as":[22,53],"compact":[24],"discrete":[25],"representation,":[26],"and":[27,68,82,120],"formulate":[28],"recognition":[33,62],"task":[34],"\u2014":[35],"transcribing":[36],"audio":[37],"inputs":[38],"into":[39],"subword":[41],"sequences.":[42],"This":[43],"process":[44],"stands":[45],"on":[46,86],"its":[47],"own,":[48],"or":[49],"can":[50],"be":[51],"applied":[52],"low-cost":[54],"second-stage":[55],"pre-training.":[56],"experiment":[58],"with":[59],"automatic":[60],"(ASR),":[63],"spoken":[64,78],"named":[65,79],"entity":[66,80],"recognition,":[67,81],"speech-to-text":[69,91],"translation.":[70],"set":[72],"new":[73],"state-of-the-art":[74],"results":[75],"end-to-end":[77],"show":[83],"consistent":[84],"improvements":[85],"8":[87],"pairs":[89],"translation,":[92],"even":[93],"when":[94],"competing":[95],"methods":[96,109],"use":[97],"additional":[98],"text":[99],"data":[100],"training.":[102],"On":[103],"ASR,":[104],"our":[105],"enables":[107],"benefit":[111],"from":[112],"pre-training":[113],"all":[115],"network,":[119],"shows":[121],"comparable":[122],"performance":[123],"highly":[125],"optimized":[126],"recent":[127],"methods.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}