{"id":"https://openalex.org/W6929500595","doi":"https://doi.org/10.5281/zenodo.10265285","title":"Mono-to-Stereo Through Parametric Stereo Generation","display_name":"Mono-to-Stereo Through Parametric Stereo Generation","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6929500595","doi":"https://doi.org/10.5281/zenodo.10265285"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265285","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265285","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10265285","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Joan Serr\u00e0","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Joan Serr\u00e0","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Davide Scaini","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davide Scaini","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Santiago Pascual","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Santiago Pascual","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Daniel Arteaga","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Arteaga","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jordi Pons","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jordi Pons","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jeroen Breebaart","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeroen Breebaart","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Giulio Cengarle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giulio Cengarle","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3266118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.37869998812675476,"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"}},"topics":[{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.37869998812675476,"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/T10860","display_name":"Speech and Audio Processing","score":0.3246000111103058,"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/T11309","display_name":"Music and Audio Processing","score":0.06109999865293503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stereophonic-sound","display_name":"Stereophonic sound","score":0.602400004863739},{"id":"https://openalex.org/keywords/panning","display_name":"Panning (audio)","score":0.5945000052452087},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5501000285148621},{"id":"https://openalex.org/keywords/decorrelation","display_name":"Decorrelation","score":0.5479999780654907},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4999000132083893},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4975999891757965},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.43130001425743103},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42340001463890076},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.40400001406669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6988999843597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6287000179290771},{"id":"https://openalex.org/C140631703","wikidata":"https://www.wikidata.org/wiki/Q34678","display_name":"Stereophonic sound","level":3,"score":0.602400004863739},{"id":"https://openalex.org/C108944566","wikidata":"https://www.wikidata.org/wiki/Q1524510","display_name":"Panning (audio)","level":4,"score":0.5945000052452087},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5501000285148621},{"id":"https://openalex.org/C177860922","wikidata":"https://www.wikidata.org/wiki/Q788608","display_name":"Decorrelation","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4975999891757965},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4747999906539917},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4235000014305115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.40400001406669617},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.399399995803833},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25929999351501465},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265285","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265285","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.10265285","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265285","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"a":[1,5,10,21,26,106,114],"stereophonic":[2],"presentation":[3],"from":[4,80],"monophonic":[6],"audio":[7],"signal":[8],"is":[9,18,150],"challenging":[11],"open":[12],"task,":[13],"especially":[14],"if":[15],"the":[16,67,81,101,145],"goal":[17],"to":[19,37,40,65,73],"obtain":[20],"realistic":[22],"spatial":[23],"imaging":[24],"with":[25,60,69],"specific":[27],"panning":[28],"of":[29,44,144,147],"sound":[30],"elements.":[31],"In":[32,58],"this":[33],"work,":[34],"we":[35,62,88],"propose":[36,64],"convert":[38],"mono":[39,83],"stereo":[41,47,78],"by":[42],"means":[43],"predicting":[45],"parametric":[46],"(PS)":[48],"parameters":[49],"using":[50],"both":[51,90,129],"nearest":[52],"neighbor":[53],"and":[54,76,92,111,131,136],"deep":[55],"network":[56],"approaches.":[57,96],"combination":[59],"PS,":[61],"also":[63,151],"model":[66],"task":[68],"generative":[70,119,132],"approaches,":[71],"allowing":[72],"synthesize":[74],"multiple":[75],"equally-plausible":[77],"renditions":[79],"same":[82],"signal.":[84],"To":[85],"achieve":[86],"this,":[87],"consider":[89],"autoregressive":[91],"masked":[93],"token":[94],"modelling":[95,133],"We":[97],"provide":[98],"evidence":[99],"that":[100],"proposed":[102],"PS-based":[103],"models":[104,120],"outperform":[105],"competitive":[107],"classical":[108],"decorrelation":[109],"baseline":[110],"that,":[112],"within":[113],"PS":[115,130],"prediction":[116],"framework,":[117],"modern":[118],"outshine":[121],"equivalent":[122],"non-generative":[123],"counterparts.":[124],"Overall,":[125],"our":[126],"work":[127],"positions":[128],"as":[134],"strong":[135],"appealing":[137],"methodologies":[138],"for":[139],"mono-to-stereo":[140],"upmixing.":[141],"A":[142],"discussion":[143],"limitations":[146],"these":[148],"approaches":[149],"provided.":[152]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}