{"id":"https://openalex.org/W4226421894","doi":"https://doi.org/10.1109/lsp.2022.3164361","title":"Speech Time-Scale Modification With GANs","display_name":"Speech Time-Scale Modification With GANs","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226421894","doi":"https://doi.org/10.1109/lsp.2022.3164361"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2022.3164361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3164361","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5018697006","display_name":"Eyal Cohen","orcid":"https://orcid.org/0000-0001-7501-3517"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Eyal Cohen","raw_affiliation_strings":["Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000406733","display_name":"Felix Kreuk","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Felix Kreuk","raw_affiliation_strings":["Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008847407","display_name":"Joseph Keshet","orcid":"https://orcid.org/0000-0003-2332-5783"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Joseph Keshet","raw_affiliation_strings":["Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018697006"],"corresponding_institution_ids":["https://openalex.org/I13955877"],"apc_list":null,"apc_paid":null,"fwci":1.7848,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.84350244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"1067","last_page":"1071"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9975000023841858,"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":0.7998658418655396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7031371593475342},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6854580044746399},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5228846073150635},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.4844055771827698},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47197896242141724},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4707377851009369},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4470941424369812},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.44054117798805237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3512241244316101},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.07449892163276672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998658418655396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7031371593475342},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6854580044746399},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5228846073150635},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.4844055771827698},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47197896242141724},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4707377851009369},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4470941424369812},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.44054117798805237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3512241244316101},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.07449892163276672},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2022.3164361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3164361","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W8699629","https://openalex.org/W175951530","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1901129140","https://openalex.org/W1975163393","https://openalex.org/W1979932443","https://openalex.org/W2098920026","https://openalex.org/W2149260990","https://openalex.org/W2154075391","https://openalex.org/W2166348079","https://openalex.org/W2168510624","https://openalex.org/W2194775991","https://openalex.org/W2519091744","https://openalex.org/W2725868244","https://openalex.org/W2765677863","https://openalex.org/W2785075253","https://openalex.org/W2785678896","https://openalex.org/W2890271448","https://openalex.org/W2962793481","https://openalex.org/W2963300588","https://openalex.org/W2963691546","https://openalex.org/W2963767194","https://openalex.org/W2964243274","https://openalex.org/W2996286887","https://openalex.org/W2997210290","https://openalex.org/W3009014607","https://openalex.org/W3015338123","https://openalex.org/W3092028330","https://openalex.org/W4320013936","https://openalex.org/W6607085208","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6740333300","https://openalex.org/W6747849691","https://openalex.org/W6748582592","https://openalex.org/W6749489859","https://openalex.org/W6768435317","https://openalex.org/W6783867762","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2953246223","https://openalex.org/W4293320219","https://openalex.org/W3110074278","https://openalex.org/W4283584549","https://openalex.org/W2618858825","https://openalex.org/W2554314924","https://openalex.org/W2998859928","https://openalex.org/W4381885966","https://openalex.org/W4288256692","https://openalex.org/W2969399009"],"abstract_inverted_index":{"While":[0],"listening":[1],"to":[2,9,29,39,129,133,148],"spoken":[3],"content,":[4],"it":[5,34],"is":[6,77,93],"often":[7],"desired":[8,105],"vary":[10],"the":[11,16,50,104,125,130,160],"speech":[12,43,53,83,102,161],"rate":[13,106,132],"while":[14],"preserving":[15],"speaker\u2019s":[17],"timbre":[18],"and":[19,107,120,140],"pitch.":[20],"To":[21],"date,":[22],"advanced":[23],"signal":[24,127],"processing":[25],"techniques":[26],"are":[27,88],"used":[28],"address":[30],"this":[31],"task,":[32],"but":[33],"still":[35],"remains":[36],"a":[37,41,62,80,96,109,112,121],"challenge":[38],"maintain":[40,134],"high":[42],"quality":[44,162],"at":[45],"all":[46,166],"time-scales.":[47],"Inspired":[48],"by":[49],"success":[51],"of":[52,71,82,95,163],"generation":[54],"using":[55,79],"Generative":[56],"Adversarial":[57],"Networks":[58],"(GANs),":[59],"we":[60],"propose":[61],"novel":[63],"unsupervised":[64],"learning":[65],"algorithm":[66,92],"for":[67],"time-scale":[68],"modification":[69],"(TSM)":[70],"speech,":[72],"called":[73],"ScalerGAN.":[74],"The":[75,90,156],"model":[76],"trained":[78],"set":[81],"utterances,":[84],"where":[85],"no":[86],"time-scales":[87],"provided.":[89],"ScalerGAN":[91,150,164],"composed":[94],"generator":[97],"that":[98,114,123,159],"gets":[99],"as":[100],"input":[101],"with":[103,151],"outputs":[108],"time-adjusted":[110,126],"speech;":[111],"discriminator":[113],"works":[115],"on":[116],"various":[117],"spectrum":[118],"scales;":[119],"decoder":[122],"converts":[124],"back":[128],"original":[131],"consistency.":[135],"Using":[136],"an":[137],"A/B":[138,142],"test":[139],"conditional":[141],"test,":[143],"human":[144],"listeners":[145],"were":[146],"asked":[147],"compare":[149],"other":[152,167],"state-of-the-art":[153],"TSM":[154],"methods.":[155,168],"results":[157],"showed":[158],"outperforms":[165]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}