{"id":"https://openalex.org/W4375869473","doi":"https://doi.org/10.1109/icassp49357.2023.10095848","title":"Can Knowledge of End-to-End Text-to-Speech Models Improve Neural Midi-to-Audio Synthesis Systems?","display_name":"Can Knowledge of End-to-End Text-to-Speech Models Improve Neural Midi-to-Audio Synthesis Systems?","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869473","doi":"https://doi.org/10.1109/icassp49357.2023.10095848"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095848","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101907238","display_name":"Xuan Shi","orcid":"https://orcid.org/0000-0002-1387-5418"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuan Shi","raw_affiliation_strings":["University of Southern California,USA","University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California,USA","University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9667,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74812559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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":0.9998999834060669,"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":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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/midi","display_name":"MIDI","score":0.884588897228241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7961417436599731},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7092915773391724},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6783275604248047},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5824877619743347},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5442743897438049}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.884588897228241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961417436599731},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7092915773391724},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6783275604248047},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5824877619743347},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5442743897438049},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095848","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2120847449","https://openalex.org/W2191779130","https://openalex.org/W2774077477","https://openalex.org/W2899724567","https://openalex.org/W2903739847","https://openalex.org/W2919624000","https://openalex.org/W2950547518","https://openalex.org/W2962721334","https://openalex.org/W2962866891","https://openalex.org/W2963609956","https://openalex.org/W2963945466","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2985308740","https://openalex.org/W2990440871","https://openalex.org/W3000389243","https://openalex.org/W3015826515","https://openalex.org/W3016160783","https://openalex.org/W3092028330","https://openalex.org/W3127854286","https://openalex.org/W3169905056","https://openalex.org/W3195902116","https://openalex.org/W4221145412","https://openalex.org/W4225716783","https://openalex.org/W4282913091","https://openalex.org/W6631190155","https://openalex.org/W6746762590","https://openalex.org/W6755182157","https://openalex.org/W6760601182","https://openalex.org/W6767111847","https://openalex.org/W6771763809","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6810708459","https://openalex.org/W6839133533"],"related_works":["https://openalex.org/W3133630535","https://openalex.org/W2398084541","https://openalex.org/W4242364395","https://openalex.org/W2386555541","https://openalex.org/W3042962886","https://openalex.org/W2920621887","https://openalex.org/W2187442448","https://openalex.org/W2126252750","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"With":[0],"the":[1,12,27,40,101],"similarity":[2],"between":[3],"music":[4,90],"and":[5,11,47,57,78,97,109],"speech":[6],"synthesis":[7,86],"from":[8,32],"symbolic":[9],"input":[10],"rapid":[13],"development":[14],"of":[15,42,52,87],"text-to-speech":[16],"(TTS)":[17],"techniques,":[18],"it":[19,49],"is":[20],"worthwhile":[21],"to":[22,25,61],"explore":[23],"ways":[24],"improve":[26,48],"MIDI-to-audio":[28,45],"performance":[29],"by":[30],"borrowing":[31],"TTS":[33],"techniques.":[34],"In":[35],"this":[36],"study,":[37],"we":[38,67],"analyze":[39],"shortcomings":[41],"a":[43,93],"TTS-based":[44],"system":[46],"in":[50],"terms":[51],"feature":[53],"computation,":[54],"model":[55,71],"selection,":[56],"training":[58],"strategy,":[59],"aiming":[60],"synthesize":[62],"highly":[63,88],"natural-sounding":[64],"audio.":[65],"Moreover,":[66],"conducted":[68],"an":[69],"extensive":[70],"evaluation":[72],"through":[73],"listening":[74],"tests,":[75],"pitch":[76],"measurement,":[77],"spectrogram":[79],"analysis.":[80],"This":[81],"work":[82],"demonstrates":[83],"not":[84],"only":[85],"natural":[89],"but":[91],"offers":[92],"thorough":[94],"analytical":[95],"approach":[96],"useful":[98],"outcomes":[99],"for":[100],"community.":[102],"Our":[103],"code,":[104],"pre-trained":[105],"models,":[106],"supplementary":[107],"materials,":[108],"audio":[110],"samples":[111],"are":[112],"open":[113],"sourced":[114],"at":[115],"https://github.com/nii-yamagishilab/midi-to-audio.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
