{"id":"https://openalex.org/W4375869273","doi":"https://doi.org/10.1109/icassp49357.2023.10094738","title":"Extreme Audio Time Stretching Using Neural Synthesis","display_name":"Extreme Audio Time Stretching Using Neural Synthesis","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869273","doi":"https://doi.org/10.1109/icassp49357.2023.10094738"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/4b2eaa1a-b031-4007-9bb3-a9ee1dd5bdf0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055959373","display_name":"Leonardo Fierro","orcid":"https://orcid.org/0000-0002-4972-4494"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Leonardo Fierro","raw_affiliation_strings":["Aalto University,Acoustics Lab,Dept. Information &#x0026; Communications Engineering,Espoo,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Acoustics Lab,Dept. Information &#x0026; Communications Engineering,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109412201","display_name":"Alec Wright","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Alec Wright","raw_affiliation_strings":["Aalto University,Acoustics Lab,Dept. Information &#x0026; Communications Engineering,Espoo,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Acoustics Lab,Dept. Information &#x0026; Communications Engineering,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021963945","display_name":"Vesa V\u00e4lim\u00e4ki","orcid":"https://orcid.org/0000-0002-7869-292X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Vesa V\u00e4lim\u00e4ki","raw_affiliation_strings":["Aalto University,Acoustics Lab,Dept. Information &#x0026; Communications Engineering,Espoo,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Acoustics Lab,Dept. Information &#x0026; Communications Engineering,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044501245","display_name":"Matti H\u00e4m\u00e4l\u00e4inen","orcid":"https://orcid.org/0000-0001-6841-112X"},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Matti H\u00e4m\u00e4l\u00e4inen","raw_affiliation_strings":["Nokia Technologies,Tampere,Finland","Nokia Technologies, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nokia Technologies,Tampere,Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"Nokia Technologies, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7832229137420654},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.7020692825317383},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.63246750831604},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5930171608924866},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.562017560005188},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5448293089866638},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4587540626525879},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.41693413257598877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31084659695625305},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1351226270198822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832229137420654},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.7020692825317383},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.63246750831604},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5930171608924866},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.562017560005188},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5448293089866638},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4587540626525879},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.41693413257598877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31084659695625305},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1351226270198822},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/123898","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/4b2eaa1a-b031-4007-9bb3-a9ee1dd5bdf0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/7e169066-ffa5-40f1-adbe-ff9b42a6b932","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/7e169066-ffa5-40f1-adbe-ff9b42a6b932","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wright, A, Valimaki, V, Fierro, L & H\u00e4m\u00e4l\u00e4inen, M 2023, Extreme audio time stretching using neural synthesis. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Institute of Electrical and Electronics Engineers, pp. 1-5. https://doi.org/10.1109/ICASSP49357.2023.10094738","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/7e169066-ffa5-40f1-adbe-ff9b42a6b932","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/7e169066-ffa5-40f1-adbe-ff9b42a6b932","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wright, A, Valimaki, V, Fierro, L & H\u00e4m\u00e4l\u00e4inen, M 2023, Extreme audio time stretching using neural synthesis. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Institute of Electrical and Electronics Engineers, pp. 1-5. https://doi.org/10.1109/ICASSP49357.2023.10094738","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/123898","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/4b2eaa1a-b031-4007-9bb3-a9ee1dd5bdf0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307798","display_name":"Nokia","ror":"https://ror.org/04pkc8m17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1504066297","https://openalex.org/W1505480452","https://openalex.org/W1521240943","https://openalex.org/W1561135842","https://openalex.org/W1979932443","https://openalex.org/W1990248658","https://openalex.org/W2029039148","https://openalex.org/W2052666245","https://openalex.org/W2076608692","https://openalex.org/W2088432713","https://openalex.org/W2110420312","https://openalex.org/W2114653980","https://openalex.org/W2116428736","https://openalex.org/W2168510624","https://openalex.org/W2278339107","https://openalex.org/W2295413924","https://openalex.org/W2519091744","https://openalex.org/W2641889749","https://openalex.org/W2769810959","https://openalex.org/W2771971536","https://openalex.org/W2791686384","https://openalex.org/W2905804369","https://openalex.org/W2912767540","https://openalex.org/W2914158211","https://openalex.org/W2963889406","https://openalex.org/W3198774053","https://openalex.org/W4226421894","https://openalex.org/W4280517025","https://openalex.org/W4294619240","https://openalex.org/W4297802552","https://openalex.org/W4372341905","https://openalex.org/W4384273636","https://openalex.org/W6631238246","https://openalex.org/W6633727632","https://openalex.org/W6696873690","https://openalex.org/W6740195615","https://openalex.org/W6757028937","https://openalex.org/W6781919197","https://openalex.org/W6917585676","https://openalex.org/W7047640044"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W2366328218"],"abstract_inverted_index":{"A":[0],"deep":[1],"neural":[2],"network":[3],"solution":[4,80],"for":[5,104],"time-scale":[6],"modification":[7],"(TSM)":[8],"focused":[9],"on":[10,55],"large":[11,105],"stretching":[12,106],"factors":[13],"is":[14,43,132],"proposed,":[15],"targeting":[16],"environmental":[17],"sounds.":[18],"Traditional":[19],"TSM":[20,41,51,117],"artifacts":[21],"such":[22],"as":[23],"transient":[24,69],"smearing,":[25],"loss":[26],"of":[27,49,67,75,95,109,140,147],"presence,":[28],"and":[29,34,65,70,99,135],"phasiness":[30],"are":[31,119],"heavily":[32],"accentuated":[33],"cause":[35],"poor":[36,63],"audio":[37],"quality":[38,103],"when":[39],"the":[40,62,68,96,122,144],"factor":[42],"four":[44,115],"or":[45,73],"larger.":[46],"The":[47,129],"weakness":[48],"established":[50],"methods,":[52],"often":[53,127],"based":[54],"a":[56,76,82,92,110,137],"phase":[57],"vocoder":[58],"structure,":[59],"lies":[60],"in":[61],"description":[64,94],"scaling":[66],"noise":[71,97],"components,":[72],"nuances,":[74],"sound.":[77],"Our":[78],"novel":[79],"combines":[81],"sines-transients-noise":[83],"decomposition":[84],"with":[85],"an":[86,100],"independent":[87],"WaveNet":[88],"synthesizer":[89],"to":[90,125,143],"provide":[91],"better":[93],"component":[98],"improve":[101],"sound":[102],"factors.":[107],"Results":[108],"subjective":[111],"listening":[112],"test":[113],"against":[114],"other":[116],"algorithms":[118],"reported,":[120],"showing":[121],"proposed":[123,130],"method":[124,131],"be":[126],"superior.":[128],"stereo":[133],"compatible":[134],"has":[136],"wide":[138],"range":[139],"applications":[141],"related":[142],"slow":[145],"motion":[146],"media":[148],"content.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
