{"id":"https://openalex.org/W7148570168","doi":"https://doi.org/10.1109/asru65441.2025.11434698","title":"Speech Synthesis From Continuous Features Using Per-Token Latent Diffusion","display_name":"Speech Synthesis From Continuous Features Using Per-Token Latent Diffusion","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148570168","doi":"https://doi.org/10.1109/asru65441.2025.11434698"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5057757909","display_name":"Arnon Turetzky","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Arnon Turetzky","raw_affiliation_strings":["The Hebrew University of Jerusalem"],"affiliations":[{"raw_affiliation_string":"The Hebrew University of Jerusalem","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055632925","display_name":"Avihu Dekel","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Avihu Dekel","raw_affiliation_strings":["The Hebrew University of Jerusalem"],"affiliations":[{"raw_affiliation_string":"The Hebrew University of Jerusalem","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114534545","display_name":"Nimrod Shabtay","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Nimrod Shabtay","raw_affiliation_strings":["Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035109881","display_name":"Slava Shechtman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Slava Shechtman","raw_affiliation_strings":["IBM Research"],"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049318367","display_name":"David Haws","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Haws","raw_affiliation_strings":["IBM Research"],"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021900623","display_name":"Hagai Aronowitz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hagai Aronowitz","raw_affiliation_strings":["IBM Research"],"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132823496","display_name":"Ron Hoory","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron Hoory","raw_affiliation_strings":["IBM Research"],"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yossi Adi","raw_affiliation_strings":["The Hebrew University of Jerusalem"],"affiliations":[{"raw_affiliation_string":"The Hebrew University of Jerusalem","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5057757909"],"corresponding_institution_ids":["https://openalex.org/I197251160"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87578125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8687999844551086,"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":0.8687999844551086,"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":0.030799999833106995,"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":0.01269999984651804,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4207000136375427},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3296999931335449},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3294999897480011},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.31060001254081726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5224000215530396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5026999711990356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40610000491142273},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3294999897480011},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30090001225471497},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2930999994277954},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.24779999256134033}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W2160473997","https://openalex.org/W2515028311","https://openalex.org/W2733903155","https://openalex.org/W2913271971","https://openalex.org/W3095410713","https://openalex.org/W3180355996","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4225956675","https://openalex.org/W4226033575","https://openalex.org/W4252684946","https://openalex.org/W4312911498","https://openalex.org/W4392904154","https://openalex.org/W4402112533","https://openalex.org/W4402112548","https://openalex.org/W4402672020","https://openalex.org/W4402959532","https://openalex.org/W4412886819","https://openalex.org/W7133219565"],"related_works":[],"abstract_inverted_index":{"We":[0,31],"present":[1],"SALAD,":[2],"a":[3,16,36,51],"zero-shot":[4,46],"text-to-speech":[5],"(TTS)":[6],"autoregressive":[7],"model":[8],"operating":[9],"over":[10],"continuous":[11,24,57],"speech":[12,71],"representations.":[13],"SALAD":[14,40,64],"utilizes":[15],"per-token":[17],"diffusion":[18],"process":[19],"to":[20],"refine":[21],"and":[22,49,73],"predict":[23],"representations":[25],"for":[26],"the":[27,70],"next":[28],"time":[29],"step.":[30],"compare":[32],"our":[33],"approach":[34],"against":[35],"discrete":[37,55],"variant":[38],"of":[39,54,76],"as":[41,43],"well":[42],"publicly":[44],"available":[45],"TTS":[47],"systems,":[48],"conduct":[50],"comprehensive":[52],"analysis":[53],"versus":[56],"modeling":[58],"techniques.":[59],"Our":[60],"results":[61],"show":[62],"that":[63],"achieves":[65],"superior":[66],"intelligibility":[67],"while":[68],"matching":[69],"quality":[72],"speaker":[74],"similarity":[75],"ground-truth":[77],"audio.":[78]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}
