{"id":"https://openalex.org/W4408356244","doi":"https://doi.org/10.1109/icassp49660.2025.10887979","title":"A Hybrid Probabilistic-Deterministic Model Recursively Enhancing Speech","display_name":"A Hybrid Probabilistic-Deterministic Model Recursively Enhancing Speech","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356244","doi":"https://doi.org/10.1109/icassp49660.2025.10887979"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887979","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":"conference-paper","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/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034382743","display_name":"Naoyuki Kamo","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoyuki Kamo","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.7831000089645386,"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":0.7831000089645386,"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/computer-science","display_name":"Computer science","score":0.7401257753372192},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6661114692687988},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3941768407821655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3369373679161072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401257753372192},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6661114692687988},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3941768407821655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3369373679161072}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887979","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":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W1991111872","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2242685705","https://openalex.org/W2289394825","https://openalex.org/W2568308529","https://openalex.org/W2673599284","https://openalex.org/W2810434345","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W3171278394","https://openalex.org/W4221144097","https://openalex.org/W4281820413","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4385822449","https://openalex.org/W4392903345","https://openalex.org/W4392904220","https://openalex.org/W4401597527","https://openalex.org/W4401609190","https://openalex.org/W4402112093","https://openalex.org/W4402112296","https://openalex.org/W4403126715","https://openalex.org/W6634817459","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6890361730"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"Probabilistic-Deterministic":[3],"Recursive":[4],"Enhancement":[5,11,82],"(PDRE),":[6],"an":[7,81],"innovative":[8],"iterative":[9,33],"Speech":[10],"(SE)":[12],"approach":[13],"that":[14,132],"integrates":[15],"probabilistic":[16,31],"and":[17,138],"deterministic":[18,41,121],"methodologies.":[19],"Recent":[20],"advancements":[21],"in":[22,35,125],"diffusion":[23,143],"models":[24,48],"have":[25],"demonstrated":[26],"the":[27,73,97,102,150],"exceptional":[28],"effectiveness":[29],"of":[30,96],"model-based":[32,144],"estimation":[34,153],"SE,":[36],"especially":[37],"when":[38],"combined":[39],"with":[40,111,120],"Neural":[42],"Network":[43,83],"(NN)-based":[44],"methods.":[45],"However,":[46],"these":[47],"often":[49],"require":[50],"extensive":[51],"iterations,":[52],"leading":[53],"to":[54,106,142],"significant":[55],"computational":[56,139],"costs.":[57],"To":[58],"tackle":[59],"this":[60],"issue,":[61],"we":[62],"propose":[63],"PDRE":[64,70,105,116,133],"as":[65],"a":[66,89],"more":[67],"efficient":[68],"alternative.":[69],"progressively":[71],"refines":[72],"clean":[74],"speech":[75],"density":[76],"estimates":[77],"by":[78],"recursively":[79],"applying":[80],"(EN),":[84],"which":[85],"is":[86],"trained":[87],"using":[88],"maximum":[90],"likelihood":[91],"objective.":[92],"A":[93],"single":[94],"application":[95],"EN":[98],"can":[99],"substantially":[100],"improve":[101],"estimation,":[103,123],"enabling":[104],"achieve":[107],"high":[108,152],"SE":[109],"accuracy":[110],"significantly":[112,134],"fewer":[113],"iterations.":[114],"Additionally,":[115],"synergizes":[117],"recursive":[118],"enhancement":[119],"signal":[122],"resulting":[124],"even":[126],"greater":[127],"accuracy.":[128,154],"Our":[129],"experiments":[130],"demonstrate":[131],"reduces":[135],"iteration":[136],"counts":[137],"costs":[140],"compared":[141],"SEs":[145],"while":[146],"maintaining":[147],"or":[148],"improving":[149],"remarkably":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}