{"id":"https://openalex.org/W4408353511","doi":"https://doi.org/10.1109/icassp49660.2025.10889233","title":"Generating Vocals from Lyrics and Musical Accompaniment","display_name":"Generating Vocals from Lyrics and Musical Accompaniment","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353511","doi":"https://doi.org/10.1109/icassp49660.2025.10889233"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5116594435","display_name":"Georg Streich","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Georg Streich","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092092756","display_name":"Luca A. Lanzend\u00f6rfer","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luca A. Lanzend\u00f6rfer","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023201175","display_name":"Florian Gr\u00f6tschla","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Florian Gr\u00f6tschla","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078339613","display_name":"Roger Wattenhofer","orcid":"https://orcid.org/0000-0002-6339-3134"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Roger Wattenhofer","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04104282,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9678999781608582,"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":0.9678999781608582,"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":0.961899995803833,"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/lyrics","display_name":"Lyrics","score":0.916983962059021},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.7650822401046753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4998297691345215},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.4227745831012726},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3703935146331787},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.23350608348846436},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.17534509301185608}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.916983962059021},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.7650822401046753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4998297691345215},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.4227745831012726},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3703935146331787},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.23350608348846436},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.17534509301185608}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2752796333","https://openalex.org/W2995181338","https://openalex.org/W3158762648","https://openalex.org/W3167533889","https://openalex.org/W3198871389","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W4381786045","https://openalex.org/W4385571362","https://openalex.org/W4390075359","https://openalex.org/W4402112011","https://openalex.org/W6853096648","https://openalex.org/W6855313532","https://openalex.org/W6873870642"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W4391375266"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,114],"introduce":[4],"AutoSing,":[5],"a":[6,66],"novel":[7,67],"framework":[8],"designed":[9],"to":[10,43,59,75,84,89,106,118],"generate":[11,107],"diverse":[12],"and":[13,20,51,109],"high-quality":[14],"singing":[15,76,111,126],"voices":[16],"from":[17],"provided":[18,61],"lyrics":[19],"musical":[21,33,93],"accompaniment.":[22,94],"AutoSing":[23,42],"extends":[24],"an":[25,36],"existing":[26],"semantic":[27],"token-based":[28],"text-to-speech":[29],"approach":[30],"by":[31],"incorporating":[32],"accompaniment":[34,56],"as":[35,79,81],"additional":[37],"conditioning":[38],"input.":[39],"This":[40],"enables":[41],"synchronize":[44],"its":[45,104],"vocal":[46],"output":[47],"with":[48,99],"the":[49,55,60,86,123],"rhythm":[50],"melodic":[52],"nuances":[53],"of":[54,125],"while":[57],"adhering":[58],"lyrics.":[62],"Our":[63],"contributions":[64],"include":[65],"training":[68],"scheme":[69],"for":[70],"autoregressive":[71],"audio":[72],"models":[73],"applied":[74],"voice":[77,127],"synthesis,":[78],"well":[80],"ablation":[82],"studies":[83],"identify":[85],"best":[87],"way":[88],"condition":[90],"generation":[91],"on":[92],"We":[95],"measure":[96],"AutoSing\u2019s":[97],"performance":[98],"subjective":[100],"listening":[101],"tests,":[102],"demonstrating":[103],"capability":[105],"coherent":[108],"creative":[110],"voices.":[112],"Furthermore,":[113],"open-source":[115],"our":[116],"codebase":[117],"foster":[119],"further":[120],"research":[121],"in":[122],"field":[124],"synthesis.":[128]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
