{"id":"https://openalex.org/W4416250841","doi":"https://doi.org/10.1109/waspaa66052.2025.11231011","title":"Schr\u00f6dinger Bridge Consistency Trajectory Models for Speech Enhancement","display_name":"Schr\u00f6dinger Bridge Consistency Trajectory Models for Speech Enhancement","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250841","doi":"https://doi.org/10.1109/waspaa66052.2025.11231011"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11231011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11231011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5119982629","display_name":"Shuichiro Nishigori","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shuichiro Nishigori","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102972958","display_name":"Koichi Saito","orcid":"https://orcid.org/0000-0002-8563-9262"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Koichi Saito","raw_affiliation_strings":["Sony AI,New York,USA"],"affiliations":[{"raw_affiliation_string":"Sony AI,New York,USA","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031225419","display_name":"Naoki Murata","orcid":"https://orcid.org/0000-0001-7418-5173"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]},{"id":"https://openalex.org/I4210143797","display_name":"Sony (Japan)","ror":"https://ror.org/04wzv3n59","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210143797"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoki Murata","raw_affiliation_strings":["Sony AI,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony AI,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I4210143797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036188375","display_name":"Masato Hirano","orcid":"https://orcid.org/0000-0001-7219-5212"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masato Hirano","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021350698","display_name":"Shusuke Takahashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shusuke Takahashi","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5119982629"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45263213,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9401000142097473,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9401000142097473,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.017999999225139618,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.007199999876320362,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7250999808311462},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7143999934196472},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5206000208854675},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5113999843597412},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45660001039505005},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.43639999628067017},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43070000410079956}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7250999808311462},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7143999934196472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7053999900817871},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5113999843597412},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45660001039505005},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31310001015663147},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30570000410079956},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11231011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11231011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2516001803","https://openalex.org/W2603567530","https://openalex.org/W3097945073","https://openalex.org/W3145029257","https://openalex.org/W3158779859","https://openalex.org/W3161480375","https://openalex.org/W4297841790","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4385807442","https://openalex.org/W4385823353","https://openalex.org/W4395447416","https://openalex.org/W4402112506","https://openalex.org/W4405974256","https://openalex.org/W4406461266","https://openalex.org/W4408354850"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,259],"(SE)":[2],"using":[3],"diffusion":[4],"models":[5,72,87,108,182],"is":[6,250],"a":[7,59,122,151,197,265],"promising":[8],"technology":[9],"for":[10,58,191,225,268],"improving":[11],"speech":[12,16,258],"quality":[13,99,126,155,232,270],"in":[14,26,88,173,217,235,246],"noisy":[15],"data.":[17],"Recently,":[18],"the":[19,31,34,37,41,45,49,56,89,101,141,167,189,205,222,228],"Schr\u00f6dinger":[20,178],"bridge":[21,179],"(SB)":[22],"has":[23],"been":[24,74,111],"utilized":[25],"diffusion-based":[27],"SE":[28],"to":[29,55,66,76,96,113,135,166,188,244],"resolve":[30],"mismatch":[32,143],"between":[33,125,154,231],"endpoint":[35],"of":[36,44,62,91,103,169],"forward":[38],"process":[39],"and":[40,127,144,156,233,256,264,276],"starting":[42],"point":[43],"reverse":[46],"process.":[47],"However,":[48,158],"SB":[50,139,190,224],"inference":[51,119,147,239,249,263],"remains":[52],"slow":[53],"owing":[54],"need":[57],"large":[60],"number":[61,102],"function":[63],"evaluations":[64],"(NFE)":[65],"achieve":[67],"high-quality":[68],"results.":[69],"Although":[70],"consistency":[71,81,180],"have":[73,110],"proposed":[75],"accelerate":[77],"inference,":[78],"by":[79,240,260],"employing":[80],"training":[82,208],"via":[83],"distillation":[84],"from":[85],"pretrained":[86,274],"field":[90],"image":[92],"generation,":[93],"they":[94],"struggle":[95],"improve":[97],"generation":[98],"as":[100],"steps":[104],"increases.":[105],"Consistency":[106],"trajectory":[107,181],"(CTMs)":[109],"introduced":[112],"overcome":[114],"this":[115,174],"limitation,":[116],"achieving":[117],"faster":[118],"while":[120,149],"preserving":[121],"favorable":[123,152,229],"trade-off":[124,153,230],"speed.":[128,157],"In":[129,193],"particular,":[130],"SoundCTM":[131],"applies":[132],"CTM":[133,145,186,207],"techniques":[134,187],"sound":[136],"generation.":[137],"The":[138],"addresses":[140],"aforementioned":[142],"improves":[146],"speed":[148,234],"maintaining":[150],"no":[159],"existing":[160],"method":[161],"simultaneously":[162],"resolves":[163],"both":[164],"issues":[165],"best":[168],"our":[170],"knowledge.":[171],"Hence,":[172],"study,":[175],"we":[176,195],"propose":[177],"(SBCTM),":[183],"which":[184,247],"apply":[185],"SE.":[192,226],"addition,":[194],"introduce":[196],"novel":[198],"auxiliary":[199],"loss,":[200,203],"incorporating":[201],"perceptual":[202],"into":[204],"original":[206],"framework.":[209],"Consequently,":[210],"SBCTM":[211,236,252],"achieves":[212],"an":[213],"approximately":[214],"16\u00d7":[215],"improvement":[216],"real-time":[218],"factor":[219],"compared":[220],"with":[221],"conventional":[223],"Furthermore,":[227],"enables":[237,253],"time-efficient":[238],"limiting":[241],"multi-step":[242],"refinement":[243],"cases":[245],"one-step":[248],"insufficient.":[251],"more":[254],"practical":[255],"efficient":[257],"providing":[261],"fast":[262],"flexible":[266],"mechanism":[267],"further":[269],"improvement.":[271],"Our":[272],"codes,":[273],"models,":[275],"audio":[277],"samples":[278],"are":[279],"available":[280],"at":[281],"https://github.com/sony/sbctm/.":[282]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}