{"id":"https://openalex.org/W4408294588","doi":"https://doi.org/10.1186/s13636-025-00400-x","title":"Singing to speech conversion with generative flow","display_name":"Singing to speech conversion with generative flow","publication_year":2025,"publication_date":"2025-03-10","ids":{"openalex":"https://openalex.org/W4408294588","doi":"https://doi.org/10.1186/s13636-025-00400-x","pmid":"https://pubmed.ncbi.nlm.nih.gov/40078713"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00400-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00400-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00400-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00400-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110256726","display_name":"Jiawen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jiawen Huang","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110256726"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01769517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2025","issue":"1","first_page":"12","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8722146153450012},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8655200004577637},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7432700991630554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7206212282180786},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5448229312896729},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.5352270007133484},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.5214818716049194},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.4730769097805023},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.4601071774959564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44874000549316406},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4149768650531769},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41097187995910645},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.27101612091064453},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11456406116485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8722146153450012},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8655200004577637},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7432700991630554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7206212282180786},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5448229312896729},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5352270007133484},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.5214818716049194},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.4730769097805023},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.4601071774959564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44874000549316406},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4149768650531769},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41097187995910645},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.27101612091064453},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11456406116485596},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13636-025-00400-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00400-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00400-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmid:40078713","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40078713","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP journal on audio, speech, and music processing","raw_type":null},{"id":"pmh:oai:europepmc.org:10705838","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11893632","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11893632/pdf/13636_2025_Article_400.pdf","source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:031d827b01ef45809ff133741233af54","is_oa":true,"landing_page_url":"https://doaj.org/article/031d827b01ef45809ff133741233af54","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-14 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00400-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00400-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00400-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8793594538","display_name":null,"funder_award_id":"EP/S022694/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4408294588.pdf"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1583912456","https://openalex.org/W2067709094","https://openalex.org/W2077626438","https://openalex.org/W2105057076","https://openalex.org/W2108382268","https://openalex.org/W2127141656","https://openalex.org/W2471520273","https://openalex.org/W2766219058","https://openalex.org/W2786495826","https://openalex.org/W2889429804","https://openalex.org/W2902070858","https://openalex.org/W2936774411","https://openalex.org/W2938583109","https://openalex.org/W2963786016","https://openalex.org/W2964243274","https://openalex.org/W2972394484","https://openalex.org/W2972552229","https://openalex.org/W2972659941","https://openalex.org/W2973071600","https://openalex.org/W2974194285","https://openalex.org/W3015759143","https://openalex.org/W3015843452","https://openalex.org/W3016243847","https://openalex.org/W3025528898","https://openalex.org/W3026874504","https://openalex.org/W3081565196","https://openalex.org/W3090751054","https://openalex.org/W3095948607","https://openalex.org/W3096864844","https://openalex.org/W3097538987","https://openalex.org/W3101882441","https://openalex.org/W3170751106","https://openalex.org/W3181854487","https://openalex.org/W3199364993","https://openalex.org/W3207340675","https://openalex.org/W4206279954","https://openalex.org/W4223646224","https://openalex.org/W4226320669","https://openalex.org/W4237182219","https://openalex.org/W4285345683","https://openalex.org/W4296070378","https://openalex.org/W4297841639","https://openalex.org/W4309395027","https://openalex.org/W6603578652","https://openalex.org/W6605269899","https://openalex.org/W6607786901","https://openalex.org/W6631190155","https://openalex.org/W6632668414","https://openalex.org/W6700616980"],"related_works":["https://openalex.org/W2500371832","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250","https://openalex.org/W1813881148"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"singing":[3,25],"to":[4,23,70,79,110],"speech":[5,27],"conversion":[6,11],"(S2S),":[7],"a":[8,76,104],"cross-domain":[9],"voice":[10],"task,":[12],"and":[13,38,74,102],"presents":[14],"the":[15,30,42,45,59,64,71,82,86,93,111],"first":[16],"deep":[17],"learning-based":[18],"S2S":[19,21,72],"system.":[20],"aims":[22],"transform":[24],"into":[26],"while":[28],"retaining":[29],"phonetic":[31,108],"information,":[32],"reducing":[33],"variations":[34],"in":[35,100,107],"pitch,":[36],"rhythm,":[37],"timbre.":[39],"Inspired":[40],"by":[41],"Glow-TTS":[43],"architecture,":[44],"proposed":[46,94],"model":[47,95],"is":[48],"built":[49],"using":[50],"generative":[51],"flow,":[52],"with":[53,81],"an":[54,121],"adjusted":[55],"alignment":[56,67],"module":[57],"between":[58,85],"latent":[60],"features.":[61],"We":[62,114],"adapt":[63],"original":[65,112],"monotonic":[66],"search":[68],"(MAS)":[69],"scenario":[73],"utilize":[75],"duration":[77,83],"predictor":[78],"deal":[80],"differences":[84],"two":[87],"modalities.":[88],"Subjective":[89],"evaluations":[90],"show":[91],"that":[92,117],"outperforms":[96,103],"signal":[97],"processing":[98],"baselines":[99],"naturalness":[101],"transcribe-and-synthesize":[105],"baseline":[106],"similarity":[109],"singing.":[113],"further":[115],"demonstrate":[116],"singing-to-speech":[118],"could":[119],"be":[120],"effective":[122],"augmentation":[123],"method":[124],"for":[125],"low-resource":[126],"lyrics":[127],"transcription.":[128]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}