{"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":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10368","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5077069016","display_name":"Junyi Ao","orcid":"https://orcid.org/0000-0001-8979-0835"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Junyi Ao","raw_affiliation_strings":[],"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":[],"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":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-0785-8882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":[],"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":[],"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":[],"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":[],"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":[],"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":[],"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":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5077069016"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3568,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.82620448,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"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":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10368","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"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":[3,20],"novel":[4],"pre-training":[5,27],"technique":[6],"with":[7,90],"unpaired":[8],"speech":[9,16,88],"data,":[10],"Speech2C,":[11],"for":[12,29],"encoder-decoder":[13,31],"based":[14],"automatic":[15],"recognition":[17],"(ASR).":[18],"Within":[19],"multi-task":[21],"learning":[22,93],"framework,":[23],"we":[24],"introduce":[25],"two":[26],"tasks":[28],"the":[30,49,63,66,82,101,106,112,120,129],"network":[32],"using":[33],"acoustic":[34],"units,":[35],"i.e.,":[36],"pseudo":[37,50,71],"codes,":[38],"derived":[39],"from":[40],"an":[41],"offline":[42],"clustering":[43],"model.":[44],"One":[45],"is":[46],"to":[47,69,85,94],"predict":[48],"codes":[51,72,91],"via":[52],"masked":[53],"language":[54],"modeling":[55],"in":[56],"encoder":[57],"output,":[58],"like":[59],"HuBERT":[60,134],"model,":[61],"while":[62],"other":[64],"lets":[65],"decoder":[67,83,123],"learn":[68],"reconstruct":[70,86],"autoregressively":[73],"instead":[74],"of":[75,138],"generating":[76],"textual":[77],"scripts.":[78],"In":[79],"this":[80],"way,":[81],"learns":[84],"original":[87],"information":[89],"before":[92],"generate":[95],"correct":[96],"text.":[97],"Comprehensive":[98],"experiments":[99],"on":[100,135],"LibriSpeech":[102],"corpus":[103],"show":[104],"that":[105],"proposed":[107],"Speech2C":[108],"can":[109],"relatively":[110],"reduce":[111],"word":[113],"error":[114],"rate":[115],"(WER)":[116],"by":[117],"19.2%":[118],"over":[119],"method":[121],"without":[122],"pre-training,":[124],"and":[125,133,140,146],"also":[126],"outperforms":[127],"significantly":[128],"state-of-the-art":[130],"wav2vec":[131],"2.0":[132],"fine-tuning":[136],"subsets":[137],"10h":[139],"100h.":[141],"We":[142],"release":[143],"our":[144],"code":[145],"model":[147],"at":[148],"https://github.com/microsoft/SpeechT5/tree/main/Speech2C.":[149]},"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":"2026-04-04T06:10:10.580331","created_date":"2025-10-10T00:00:00"}