{"id":"https://openalex.org/W3015843452","doi":"https://doi.org/10.1109/icassp40776.2020.9054473","title":"Speech-To-Singing Conversion in an Encoder-Decoder Framework","display_name":"Speech-To-Singing Conversion in an Encoder-Decoder Framework","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015843452","doi":"https://doi.org/10.1109/icassp40776.2020.9054473","mag":"3015843452"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5049601339","display_name":"Jayneel Parekh","orcid":"https://orcid.org/0009-0008-4762-6998"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Jayneel Parekh","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France"],"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084496610","display_name":"Preeti Rao","orcid":"https://orcid.org/0000-0002-2842-8450"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preeti Rao","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Bombay, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Research Center for IT Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049601339"],"corresponding_institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":1.3638,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80776827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9994000196456909,"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":0.81531822681427},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7334665656089783},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7298228144645691},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.602451741695404},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5607401132583618},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5229763984680176},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5211043953895569},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5026378631591797},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47267279028892517},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.452426552772522},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41053587198257446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3817526698112488}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81531822681427},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7334665656089783},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7298228144645691},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.602451741695404},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5607401132583618},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5229763984680176},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5211043953895569},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5026378631591797},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47267279028892517},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.452426552772522},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41053587198257446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3817526698112488},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/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/icassp40776.2020.9054473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1901129140","https://openalex.org/W1924770834","https://openalex.org/W2067709094","https://openalex.org/W2108382268","https://openalex.org/W2118774185","https://openalex.org/W2120847449","https://openalex.org/W2150933458","https://openalex.org/W2191779130","https://openalex.org/W2407685581","https://openalex.org/W2502312327","https://openalex.org/W2525577390","https://openalex.org/W2766465839","https://openalex.org/W2786495826","https://openalex.org/W2795935131","https://openalex.org/W2803963372","https://openalex.org/W2849790107","https://openalex.org/W2899771611","https://openalex.org/W2905741299","https://openalex.org/W2905804369","https://openalex.org/W2910577860","https://openalex.org/W2962793481","https://openalex.org/W2962981281","https://openalex.org/W2963011080","https://openalex.org/W2963233633","https://openalex.org/W2963609956","https://openalex.org/W2964121744","https://openalex.org/W2964177567","https://openalex.org/W2964307104","https://openalex.org/W2964607787","https://openalex.org/W2972552229","https://openalex.org/W2995005087","https://openalex.org/W3010943931","https://openalex.org/W3114301328","https://openalex.org/W4246602265","https://openalex.org/W4298580827","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6640212811","https://openalex.org/W6714030504","https://openalex.org/W6724804524","https://openalex.org/W6736996214","https://openalex.org/W6748409065","https://openalex.org/W6752096078","https://openalex.org/W6752934364","https://openalex.org/W6756040250","https://openalex.org/W6758675244","https://openalex.org/W6771665576"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W4288088492","https://openalex.org/W2982290989","https://openalex.org/W1840351222","https://openalex.org/W2114688254"],"abstract_inverted_index":{"In":[0],"this":[1,40],"paper":[2],"our":[3,65,122],"goal":[4],"is":[5],"to":[6,28,34,83,98,110],"convert":[7],"a":[8,24,73,105,116],"set":[9],"of":[10,39,70,93,121],"spoken":[11],"lines":[12],"into":[13],"sung":[14],"ones.":[15],"Unlike":[16],"previous":[17],"signal":[18],"processing":[19],"based":[20,26,108],"methods,":[21],"we":[22,59,77],"take":[23],"learning":[25,107],"approach":[27],"the":[29,88,94,99],"problem.":[30],"This":[31],"allows":[32],"us":[33,82],"automatically":[35],"model":[36],"various":[37],"aspects":[38],"transformation,":[41],"thus":[42],"overcoming":[43],"dependence":[44],"on":[45],"specific":[46],"inputs":[47],"such":[48],"as":[49],"high":[50],"quality":[51],"singing":[52,85],"templates":[53],"or":[54],"phoneme-score":[55],"synchronization":[56],"information.":[57],"Specifically,":[58],"propose":[60,104],"an":[61],"encoder-decoder":[62],"framework":[63],"for":[64],"task.":[66],"Given":[67],"time-frequency":[68],"representations":[69],"speech":[71],"and":[72,91,118],"target":[74,100],"melody":[75],"contour,":[76],"learn":[78],"encodings":[79],"that":[80,86],"enable":[81],"synthesize":[84],"preserves":[87],"linguistic":[89],"content":[90],"timbre":[92],"speaker":[95],"while":[96],"adhering":[97],"melody.":[101],"We":[102,114],"also":[103],"multi-task":[106],"objective":[109],"improve":[111],"lyric":[112],"intelligibility.":[113],"present":[115],"quantitative":[117],"qualitative":[119],"analysis":[120],"framework.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
