{"id":"https://openalex.org/W4226278833","doi":"https://doi.org/10.21437/interspeech.2022-10368","title":"Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data","display_name":"Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4226278833","doi":"https://doi.org/10.21437/interspeech.2022-10368"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10368","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10368","pdf_url":"https://www.isca-archive.org/interspeech_2022/ao22_interspeech.pdf","source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.isca-archive.org/interspeech_2022/ao22_interspeech.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077069016","display_name":"Junyi Ao","orcid":"https://orcid.org/0000-0001-8979-0835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junyi Ao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101577318","display_name":"Ziqiang Zhang","orcid":"https://orcid.org/0000-0003-0110-1543"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziqiang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106557565","display_name":"Long Zhou","orcid":"https://orcid.org/0009-0006-1919-4943"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-2599-6752"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Furu Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2658","last_page":"2662"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9940000176429749,"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":0.9873999953269958,"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":0.7276602983474731},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7150481343269348},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.649676501750946},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6056268215179443},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4965282082557678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2813321352005005},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13932478427886963},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12646484375},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09492164850234985},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.051733165979385376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7276602983474731},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7150481343269348},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.649676501750946},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6056268215179443},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4965282082557678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2813321352005005},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13932478427886963},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12646484375},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09492164850234985},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.051733165979385376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10368","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10368","pdf_url":"https://www.isca-archive.org/interspeech_2022/ao22_interspeech.pdf","source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2022-10368","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10368","pdf_url":"https://www.isca-archive.org/interspeech_2022/ao22_interspeech.pdf","source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5088964179","display_name":null,"funder_award_id":"T00120220002","funder_id":"https://openalex.org/F4320331102","funder_display_name":"Shenzhen Research Institute of Big Data"},{"id":"https://openalex.org/G861645084","display_name":null,"funder_award_id":"B10120210117-KP02","funder_id":"https://openalex.org/F4320322942","funder_display_name":"Chinese University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"},{"id":"https://openalex.org/F4320333998","display_name":"Shenzhen Research Institute, City University of Hong Kong","ror":"https://ror.org/00xc0ma20"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226278833.pdf","grobid_xml":"https://content.openalex.org/works/W4226278833.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W3196421258","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2151749779","https://openalex.org/W2382290278","https://openalex.org/W3203142394"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"a":[3,19],"novel":[4],"pre-training":[5,26],"technique":[6],"with":[7,87],"unpaired":[8],"speech":[9,16,85],"data,":[10],"Speech2C,":[11],"for":[12,28],"encoder-decoder":[13],"based":[14],"automatic":[15],"recognition":[17],"(ASR).Within":[18],"multi-task":[20],"learning":[21,90],"framework,":[22],"we":[23],"introduce":[24],"two":[25],"tasks":[27],"the":[29,47,61,64,79,97,102,108,116,125],"encoderdecoder":[30],"network":[31],"using":[32],"acoustic":[33],"units,":[34],"i.e.,":[35],"pseudo":[36,48,69],"codes,":[37],"derived":[38],"from":[39],"an":[40],"offline":[41],"clustering":[42],"model.One":[43],"is":[44],"to":[45,67,82,91],"predict":[46],"codes":[49,70,88],"via":[50],"masked":[51],"language":[52],"modeling":[53],"in":[54],"encoder":[55],"output,":[56],"like":[57],"HuBERT":[58],"model,":[59],"while":[60],"other":[62],"lets":[63],"decoder":[65,80,119],"learn":[66],"reconstruct":[68,83],"autoregressively":[71],"instead":[72],"of":[73,134],"generating":[74],"textual":[75],"scripts.In":[76],"this":[77],"way,":[78],"learns":[81],"original":[84],"information":[86],"before":[89],"generate":[92],"correct":[93],"text.Comprehensive":[94],"experiments":[95],"on":[96,131],"LibriSpeech":[98],"corpus":[99],"show":[100],"that":[101],"proposed":[103],"Speech2C":[104],"can":[105],"relatively":[106],"reduce":[107],"word":[109],"error":[110],"rate":[111],"(WER)":[112],"by":[113],"19.2%":[114],"over":[115],"method":[117],"without":[118],"pre-training,":[120],"and":[121,129,136,141],"also":[122],"outperforms":[123],"significantly":[124],"state-of-the-art":[126],"wav2vec":[127],"2.0":[128],"Hu-BERT":[130],"fine-tuning":[132],"subsets":[133],"10h":[135],"100h.We":[137],"release":[138],"our":[139],"code":[140],"model":[142],"at":[143],"https://github.com/microsoft/SpeechT5/tree/main/Speech2C.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}