{"id":"https://openalex.org/W4392979802","doi":"https://doi.org/10.1109/taslp.2024.3379877","title":"SpeechLM: Enhanced Speech Pre-Training With Unpaired Textual Data","display_name":"SpeechLM: Enhanced Speech Pre-Training With Unpaired Textual Data","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392979802","doi":"https://doi.org/10.1109/taslp.2024.3379877"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3379877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3379877","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101577318","display_name":"Ziqiang Zhang","orcid":"https://orcid.org/0000-0003-0110-1543"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqiang Zhang","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0110-1543","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079533447","display_name":"Sanyuan Chen","orcid":"https://orcid.org/0000-0002-3082-6052"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanyuan Chen","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-3082-6052","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106557565","display_name":"Long Zhou","orcid":"https://orcid.org/0009-0006-1919-4943"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Zhou","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Aisa, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-1919-4943","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Aisa, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709477","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-5715-3011"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Aisa, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5715-3011","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Aisa, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010323000","display_name":"Shuo Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Ren","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Aisa, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Aisa, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-2599-6752"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Aisa, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Aisa, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109482068","display_name":"Zhuoyuan Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoyuan Yao","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Aisa, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Aisa, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078493980","display_name":"Xun Gong","orcid":"https://orcid.org/0000-0002-1494-0955"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Gong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Aisa, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Aisa, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0859-2827","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1089-9748","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Furu Wei","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Aisa, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Aisa, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.3794,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.97549691,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"2177","last_page":"2187"},"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":0.9994999766349792,"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":0.9987999796867371,"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/training","display_name":"Training (meteorology)","score":0.6643980741500854},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49944210052490234},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49817681312561035},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3996736705303192},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3487497568130493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3246825337409973},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07296162843704224}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6643980741500854},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49944210052490234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49817681312561035},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3996736705303192},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3487497568130493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3246825337409973},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07296162843704224},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3379877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3379877","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W2033875152","https://openalex.org/W2046932483","https://openalex.org/W2101105183","https://openalex.org/W2127141656","https://openalex.org/W2187089797","https://openalex.org/W2509528580","https://openalex.org/W2896457183","https://openalex.org/W2963925437","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2982223350","https://openalex.org/W2995181338","https://openalex.org/W3011411500","https://openalex.org/W3015213852","https://openalex.org/W3015265920","https://openalex.org/W3016181583","https://openalex.org/W3041561163","https://openalex.org/W3097286738","https://openalex.org/W3161302809","https://openalex.org/W3162313915","https://openalex.org/W3163142165","https://openalex.org/W3196509775","https://openalex.org/W3197580070","https://openalex.org/W3198299542","https://openalex.org/W3198858531","https://openalex.org/W3207222250","https://openalex.org/W3209371554","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4221155340","https://openalex.org/W4224934179","https://openalex.org/W4226033575","https://openalex.org/W4226120743","https://openalex.org/W4283324001","https://openalex.org/W4297841852","https://openalex.org/W4319862474","https://openalex.org/W4385245566","https://openalex.org/W4392909760","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6762122294","https://openalex.org/W6763832098","https://openalex.org/W6769196770","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6795952400","https://openalex.org/W6796554684","https://openalex.org/W6802465204","https://openalex.org/W6803092890","https://openalex.org/W6810007534","https://openalex.org/W6810252168","https://openalex.org/W6810259195","https://openalex.org/W6846290820","https://openalex.org/W6847568899"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W3204019825"],"abstract_inverted_index":{"How":[0],"to":[1,13,35,55,108],"boost":[2],"speech":[3,17,38,58,73,91,111,136,138],"pre-training":[4,41,104],"with":[5,24,42,121],"textual":[6],"data":[7,94],"is":[8,106],"an":[9],"unsolved":[10],"problem":[11],"due":[12],"the":[14,57,84,89,110,113,116],"fact":[15],"that":[16],"and":[18,39,59,64,92,112,140,153],"text":[19,40,60,93,114],"are":[20,155],"very":[21],"different":[22],"modalities":[23],"distinct":[25],"characteristics.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30,49,87],"propose":[31],"a":[32,43,75,122],"cross-modalSpeechandLanguageModel":[33],"(SpeechLM)":[34],"explicitly":[36],"align":[37],"pre-defined":[44],"unified":[45,123],"discrete":[46,53,118],"representation.":[47],"Specifically,":[48],"introduce":[50],"two":[51],"alternative":[52],"tokenizers":[54],"bridge":[56],"modalities,":[61],"including":[62,135],"phoneme-unit":[63],"hidden-unit":[65],"tokenizers,":[66,86],"which":[67],"can":[68],"be":[69],"trained":[70,85],"using":[71],"unpaired":[72],"or":[74,100],"small":[76],"amount":[77],"of":[78,97],"paired":[79],"speech-text":[80],"data.":[81],"Based":[82],"on":[83,129,149],"convert":[88],"unlabeled":[90],"into":[95,115],"tokens":[96],"phoneme":[98],"units":[99],"hidden":[101],"units.":[102],"The":[103],"objective":[105],"designed":[107],"unify":[109],"same":[117],"semantic":[119],"space":[120],"Transformer":[124],"network.":[125],"We":[126],"evaluate":[127],"SpeechLM":[128],"various":[130],"spoken":[131],"language":[132],"processing":[133],"tasks":[134],"recognition,":[137],"translation,":[139],"universal":[141],"representation":[142],"evaluation":[143],"framework":[144],"SUPERB,":[145],"demonstrating":[146],"significant":[147],"improvements":[148],"content-related":[150],"tasks.":[151],"Code":[152],"models":[154],"available":[156],"athttps://aka.ms/SpeechLM.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}