{"id":"https://openalex.org/W4372349499","doi":"https://doi.org/10.1109/icassp49357.2023.10096707","title":"A Phoneme-Informed Neural Network Model For Note-Level Singing Transcription","display_name":"A Phoneme-Informed Neural Network Model For Note-Level Singing Transcription","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349499","doi":"https://doi.org/10.1109/icassp49357.2023.10096707"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096707","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":"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/A5014282591","display_name":"Sangeon Yong","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sangeon Yong","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Daejeon,Republic of Korea","Graduate School of Culture Technology, KAIST, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038264558","display_name":"Li Su","orcid":"https://orcid.org/0000-0003-4275-8832"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li Su","raw_affiliation_strings":["Academia Sinica,Institute of Information Science,Taipei,Taiwan","Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica,Institute of Information Science,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Daejeon,Republic of Korea","Graduate School of Culture Technology, KAIST, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014282591"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.7147,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8496003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"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":1.0,"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":1.0,"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":0.9976000189781189,"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":0.9975000023841858,"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/singing","display_name":"Singing","score":0.9196917414665222},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8269246816635132},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7836295366287231},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7403327822685242},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7390660047531128},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7214491367340088},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5135400295257568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.397078275680542},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3843839466571808},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1702289581298828},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09091737866401672}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9196917414665222},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8269246816635132},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7836295366287231},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7403327822685242},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390660047531128},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7214491367340088},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5135400295257568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.397078275680542},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3843839466571808},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1702289581298828},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09091737866401672},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096707","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1533416326","https://openalex.org/W2118774185","https://openalex.org/W2127141656","https://openalex.org/W2294039222","https://openalex.org/W2407685581","https://openalex.org/W2586947700","https://openalex.org/W2903006902","https://openalex.org/W2908510526","https://openalex.org/W2939957001","https://openalex.org/W2950335938","https://openalex.org/W2950547518","https://openalex.org/W2989926340","https://openalex.org/W3091031764","https://openalex.org/W3127686677","https://openalex.org/W3165908916","https://openalex.org/W3196294373","https://openalex.org/W3209419355","https://openalex.org/W4224917360","https://openalex.org/W4286858320","https://openalex.org/W4293775315","https://openalex.org/W6697015887","https://openalex.org/W6714030504","https://openalex.org/W6733426572","https://openalex.org/W6733936739","https://openalex.org/W6745851314","https://openalex.org/W6755182157","https://openalex.org/W6757817989","https://openalex.org/W6784081880","https://openalex.org/W6789826613","https://openalex.org/W6840344411","https://openalex.org/W7066299598"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2011227383","https://openalex.org/W4375868962","https://openalex.org/W3016250102","https://openalex.org/W4288088492","https://openalex.org/W2982290989","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Note-level":[0],"automatic":[1],"music":[2,10],"transcription":[3,34,166],"is":[4,38,51,121],"one":[5],"of":[6,30,35,48,73,77,87,109,114,164,172],"the":[7,28,46,84,115,124,142,146,162,170],"most":[8],"representative":[9],"information":[11],"retrieval":[12],"(MIR)":[13],"tasks":[14],"and":[15,64,102,129,151,167],"has":[16],"been":[17],"studied":[18],"for":[19,155],"various":[20],"instruments":[21,37],"to":[22,27,53,58],"understand":[23],"music.":[24],"However,":[25],"due":[26,57],"lack":[29],"high-quality":[31],"labeled":[32],"data,":[33],"many":[36],"still":[39],"a":[40,71,106],"challenging":[41],"task.":[42],"In":[43,66],"particular,":[44],"in":[45,61,93,175],"case":[47],"singing,":[49,88],"it":[50],"difficult":[52],"find":[54],"accurate":[55],"notes":[56],"its":[59],"expressiveness":[60],"pitch,":[62],"timbre,":[63],"dynamics.":[65],"this":[67],"paper,":[68],"we":[69,140],"propose":[70],"method":[72],"finding":[74],"note":[75],"onsets":[76],"singing":[78,128,165,176],"voice":[79],"more":[80],"accurately":[81],"by":[82,123],"leveraging":[83],"linguistic":[85,135,173],"characteristics":[86],"which":[89],"are":[90],"not":[91],"seen":[92],"other":[94],"instruments.":[95],"The":[96],"proposed":[97],"model":[98],"uses":[99],"mel-scaled":[100],"spectrogram":[101],"phonetic":[103],"posteriorgram":[104],"(PPG),":[105],"frame-wise":[107],"likelihood":[108],"phoneme,":[110],"as":[111],"an":[112],"input":[113],"onset":[116,138,153],"detection":[117],"network":[118,126],"while":[119],"PPG":[120],"generated":[122],"pre-trained":[125],"with":[127,148],"speech":[130],"data.":[131],"To":[132],"verify":[133],"how":[134],"features":[136,174],"affect":[137],"detection,":[139],"compare":[141],"evaluation":[143],"results":[144],"through":[145],"dataset":[147],"different":[149],"languages":[150],"divide":[152],"types":[154],"detailed":[156],"analysis.":[157,177],"Our":[158],"approach":[159],"substantially":[160],"improves":[161],"performance":[163],"therefore":[168],"emphasizes":[169],"importance":[171]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
