{"id":"https://openalex.org/W4415036248","doi":"https://doi.org/10.21437/interspeech.2025-1434","title":"REWIND: Speech Time Reversal for Enhancing Speaker Representations in Diffusion-based Voice Conversion","display_name":"REWIND: Speech Time Reversal for Enhancing Speaker Representations in Diffusion-based Voice Conversion","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415036248","doi":"https://doi.org/10.21437/interspeech.2025-1434"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1434","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.20756","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115728896","display_name":"Ishan D. Biyani","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ishan D. Biyani","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091143209","display_name":"Nirmesh J. Shah","orcid":"https://orcid.org/0000-0002-7294-6757"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nirmesh J. Shah","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113361537","display_name":"Ashishkumar Gudmalwar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashishkumar P. Gudmalwar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012386561","display_name":"Pankaj Wasnik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pankaj Wasnik","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081154360","display_name":"Rajiv R. Shah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajiv R. Shah","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5115728896"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15483529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1368","last_page":"1372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9886000156402588,"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":0.9560999870300293,"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/context","display_name":"Context (archaeology)","score":0.5202999711036682},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.47780001163482666},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4537999927997589},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42669999599456787},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4129999876022339},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.39559999108314514},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.39089998602867126},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.35409998893737793}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8026000261306763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692300021648407},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.47780001163482666},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.35409998893737793},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3273000121116638},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.31189998984336853},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C541956065","wikidata":"https://www.wikidata.org/wiki/Q2250680","display_name":"Speech error","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2639000117778778}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1434","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.20756","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.20756","pdf_url":"https://arxiv.org/pdf/2505.20756","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.20756","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.20756","pdf_url":"https://arxiv.org/pdf/2505.20756","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415036248.pdf","grobid_xml":"https://content.openalex.org/works/W4415036248.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speech":[0],"time":[1,60],"reversal":[2],"refers":[3],"to":[4,17,67,82],"the":[5,9,26,99,105,116],"process":[6],"of":[7,29,98,107],"reversing":[8],"entire":[10],"speech":[11,62,127],"signal":[12],"in":[13,76,104],"time,":[14],"causing":[15],"it":[16],"play":[18],"backward.":[19],"Such":[20],"signals":[21],"are":[22,33],"completely":[23],"unintelligible":[24],"since":[25],"fundamental":[27],"structures":[28],"phonemes":[30],"and":[31,73],"syllables":[32],"destroyed.":[34],"However,":[35],"they":[36],"still":[37],"retain":[38],"tonal":[39],"patterns":[40],"that":[41,115],"enable":[42],"perceptual":[43],"speaker":[44,56,69,72,121],"identification":[45],"despite":[46],"losing":[47],"linguistic":[48,94],"content.":[49,95],"In":[50],"this":[51],"paper,":[52],"we":[53],"propose":[54],"leveraging":[55],"representations":[57],"learned":[58],"from":[59,93],"reversed":[61],"as":[63],"an":[64],"augmentation":[65],"strategy":[66],"enhance":[68],"representation.":[70],"Notably,":[71],"language":[74],"disentanglement":[75],"voice":[77],"conversion":[78],"(VC)":[79],"is":[80,102],"essential":[81],"accurately":[83],"preserve":[84],"a":[85],"speaker's":[86],"unique":[87],"vocal":[88],"traits":[89],"while":[90,124],"minimizing":[91],"interference":[92],"The":[96],"effectiveness":[97],"proposed":[100,117],"approach":[101,118],"evaluated":[103],"context":[106],"state-of-the-art":[108],"diffusion-based":[109],"VC":[110],"models.":[111],"Experimental":[112],"results":[113],"indicate":[114],"significantly":[119],"improves":[120],"similarity-related":[122],"scores":[123],"maintaining":[125],"high":[126],"quality.":[128]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}