{"id":"https://openalex.org/W4408345880","doi":"https://doi.org/10.1109/icassp49660.2025.10887605","title":"A Non-autoregressive Model for Joint STT and TTS","display_name":"A Non-autoregressive Model for Joint STT and TTS","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345880","doi":"https://doi.org/10.1109/icassp49660.2025.10887605"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5113145191","display_name":"Vishal Sunder","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishal Sunder","raw_affiliation_strings":["The Ohio State University,Columbus,OH,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Columbus,OH,USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Research,Yorktown Heights,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Yorktown Heights,NY,USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research,Yorktown Heights,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Yorktown Heights,NY,USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Research,Yorktown Heights,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Yorktown Heights,NY,USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035109881","display_name":"Slava Shechtman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Slava Shechtman","raw_affiliation_strings":["IBM Research,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021900623","display_name":"Hagai Aronowitz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Hagai Aronowitz","raw_affiliation_strings":["IBM Research,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["The Ohio State University,Columbus,OH,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Columbus,OH,USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023268703","display_name":"Luis Lastras","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luis Lastras","raw_affiliation_strings":["IBM Research,Yorktown Heights,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Yorktown Heights,NY,USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5175,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9195223,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"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":0.9599999785423279,"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":0.9599999785423279,"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/T10860","display_name":"Speech and Audio Processing","score":0.01140000019222498,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.8535467982292175},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7020401358604431},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.682111918926239},{"id":"https://openalex.org/keywords/nonlinear-autoregressive-exogenous-model","display_name":"Nonlinear autoregressive exogenous model","score":0.5263903141021729},{"id":"https://openalex.org/keywords/star-model","display_name":"STAR model","score":0.5076996088027954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3849948048591614},{"id":"https://openalex.org/keywords/autoregressive-integrated-moving-average","display_name":"Autoregressive integrated moving average","score":0.35395950078964233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3418560028076172},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2154134213924408},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.21220064163208008},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1587654948234558},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.1508522927761078},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.146327942609787},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05737534165382385}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8535467982292175},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7020401358604431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.682111918926239},{"id":"https://openalex.org/C42536954","wikidata":"https://www.wikidata.org/wiki/Q7049462","display_name":"Nonlinear autoregressive exogenous model","level":3,"score":0.5263903141021729},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.5076996088027954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3849948048591614},{"id":"https://openalex.org/C24338571","wikidata":"https://www.wikidata.org/wiki/Q2566298","display_name":"Autoregressive integrated moving average","level":3,"score":0.35395950078964233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3418560028076172},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2154134213924408},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.21220064163208008},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1587654948234558},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.1508522927761078},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.146327942609787},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05737534165382385}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2183341477","https://openalex.org/W2407080277","https://openalex.org/W2936774411","https://openalex.org/W2937780860","https://openalex.org/W2963587345","https://openalex.org/W2972359262","https://openalex.org/W3024869864","https://openalex.org/W3097777922","https://openalex.org/W3097882114","https://openalex.org/W3169714379","https://openalex.org/W3197140813","https://openalex.org/W3205644108","https://openalex.org/W4225308107","https://openalex.org/W4225956675","https://openalex.org/W4319862474","https://openalex.org/W4372260576","https://openalex.org/W4385567350","https://openalex.org/W4385823191","https://openalex.org/W4387595589","https://openalex.org/W4391021684","https://openalex.org/W4392904348","https://openalex.org/W4401070302","https://openalex.org/W4402111799","https://openalex.org/W4402671610","https://openalex.org/W6600213771","https://openalex.org/W6762242920","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6847363464","https://openalex.org/W6866575372","https://openalex.org/W6869471027","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2439807930","https://openalex.org/W2606910468","https://openalex.org/W3116827148","https://openalex.org/W3120843198","https://openalex.org/W2036704594","https://openalex.org/W4287185323","https://openalex.org/W304218021","https://openalex.org/W3123153965","https://openalex.org/W2154965898","https://openalex.org/W2098152933"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"take":[4],"a":[5,19,25,133],"step":[6],"towards":[7],"jointly":[8],"modeling":[9],"automatic":[10],"speech":[11,15,33,52],"recognition":[12],"(STT)":[13],"and":[14,34,72,101,115,125],"synthesis":[16],"(TTS)":[17],"in":[18,122],"fully":[20],"non-autoregressive":[21],"way.":[22],"We":[23,61,104],"develop":[24],"novel":[26],"multimodal":[27,59],"framework":[28],"capable":[29],"of":[30,75,93,136],"handling":[31],"the":[32,70,80,84,91,119,129],"text":[35,54],"modalities":[36],"as":[37],"input":[38,92],"either":[39],"individually":[40],"or":[41,53],"together.":[42],"The":[43],"proposed":[44],"model":[45,77,109],"can":[46,86,110],"also":[47],"be":[48,87],"trained":[49],"with":[50,128],"unpaired":[51],"data":[55],"owing":[56],"to":[57,68,90],"its":[58],"nature.":[60],"further":[62],"propose":[63],"an":[64],"iterative":[65],"refinement":[66],"strategy":[67],"improve":[69],"STT":[71,100,114],"TTS":[73,102,116],"performance":[74],"our":[76,94,107],"such":[78],"that":[79,106],"partial":[81],"hypothesis":[82],"at":[83],"output":[85],"fed":[88],"back":[89],"model,":[95],"thus":[96],"iteratively":[97],"improving":[98],"both":[99,113],"predictions.":[103],"show":[105],"joint":[108],"effectively":[111],"perform":[112],"tasks,":[117],"outperforming":[118],"STT-specific":[120],"baseline":[121,131],"all":[123],"tasks":[124],"performing":[126],"competitively":[127],"TTS-specific":[130],"across":[132],"wide":[134],"range":[135],"evaluation":[137],"metrics.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}