{"id":"https://openalex.org/W4393763452","doi":"https://doi.org/10.5281/zenodo.1185124","title":"Dataset for Interspeech 2018 submission: Singing voice phoneme segmentation by hierarchically inferring syllable and phoneme onset positions","display_name":"Dataset for Interspeech 2018 submission: Singing voice phoneme segmentation by hierarchically inferring syllable and phoneme onset positions","publication_year":2018,"publication_date":"2018-02-27","ids":{"openalex":"https://openalex.org/W4393763452","doi":"https://doi.org/10.5281/zenodo.1185124"},"language":"en","primary_location":{"id":"pmh:oai:figshare.com:article/11549544","is_oa":true,"landing_page_url":"https://figshare.com/articles/Dataset_for_Interspeech_2018_submission_Singing_voice_phoneme_segmentation_by_hierarchically_inferring_syllable_and_phoneme_onset_positions/11549544","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/Dataset_for_Interspeech_2018_submission_Singing_voice_phoneme_segmentation_by_hierarchically_inferring_syllable_and_phoneme_onset_positions/11549544","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101791904","display_name":"Rong Gong","orcid":"https://orcid.org/0000-0002-4659-9034"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Gong, Rong","raw_affiliation_strings":["Music Technology Group - Universitat Pompeu Fabra"],"raw_orcid":"https://orcid.org/0000-0002-4659-9034","affiliations":[{"raw_affiliation_string":"Music Technology Group - Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Serra, Xavier","raw_affiliation_strings":["Music Technology Group - Universitat Pompeu Fabra"],"raw_orcid":"https://orcid.org/0000-0003-1395-2345","affiliations":[{"raw_affiliation_string":"Music Technology Group - Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9926999807357788,"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":0.9926999807357788,"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/syllable","display_name":"Syllable","score":0.8643906116485596},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7216144800186157},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6529462337493896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6364226341247559},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5117976069450378},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.33397674560546875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26771223545074463},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0869465172290802}],"concepts":[{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.8643906116485596},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7216144800186157},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6529462337493896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6364226341247559},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5117976069450378},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.33397674560546875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26771223545074463},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0869465172290802}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:figshare.com:article/11549544","is_oa":true,"landing_page_url":"https://figshare.com/articles/Dataset_for_Interspeech_2018_submission_Singing_voice_phoneme_segmentation_by_hierarchically_inferring_syllable_and_phoneme_onset_positions/11549544","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},{"id":"pmh:oai:zenodo.org:1185124","is_oa":true,"landing_page_url":"https://zenodo.org/record/1185124","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},{"id":"doi:10.5281/zenodo.1185124","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.1185124","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/11549544","is_oa":true,"landing_page_url":"https://figshare.com/articles/Dataset_for_Interspeech_2018_submission_Singing_voice_phoneme_segmentation_by_hierarchically_inferring_syllable_and_phoneme_onset_positions/11549544","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7129673670","display_name":null,"funder_award_id":"267583","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2514064218","https://openalex.org/W2132658536","https://openalex.org/W2094188777","https://openalex.org/W2112609279","https://openalex.org/W1581825163","https://openalex.org/W2399404538","https://openalex.org/W1483316057","https://openalex.org/W2366310385","https://openalex.org/W2061937230"],"abstract_inverted_index":{"This":[0],"dataset":[1,34,46,77,81,117,129,138],"contains":[2,47],"the":[3,8,15,39,48,54,74,95,102,112,115,124,127,134,136,149],"materials":[4],"for":[5],"training,":[6],"testing":[7],"joint":[9],"and":[10,25,51,58,68],"HSMM":[11],"models":[12],"mentioned":[13],"in":[14,38,97],"paper":[16],"\"<em>Singing":[17],"voice":[18],"phoneme":[19,26],"segmentation":[20],"by":[21],"hierarchically":[22],"inferring":[23],"syllable":[24],"onset":[27],"positions\"</em>.":[28],"The":[29,45],"filename":[30],"list":[31],"of":[32,42,53,105,114,126],"this":[33,144],"can":[35],"be":[36],"found":[37],"function":[40],"<em>get_train_test_recordings_joint()</em>":[41],"<em>./general/trainTestSeparation.py</em>":[43],"file.":[44],"Praat":[49],"TextGrids":[50],".wavs":[52],"variables:":[55],"<em>train_primary_school,":[56],"val_primary_school</em>":[57],"<em>test_primary_school</em>.":[59],"For":[60,140],"accessing":[61],"other":[62],"datasets":[63],"such":[64],"as":[65],"<em>train_nacta_2017,":[66],"train_nacta</em>":[67],"<em>train_sepa</em>,":[69],"please":[70,146],"download":[71],"them":[72],"from":[73],"links:":[75],"jingju":[76,80,128,137],"part1:":[78],"https://zenodo.org/record/1185154":[79],"part2:":[82],"https://doi.org/10.5281/zenodo.842229":[83],"Once":[84],"you":[85,91],"have":[86],"downloaded":[87],"these":[88,106],"three":[89,107],"datasets,":[90],"need":[92],"to":[93,101,111,123,133,148],"set":[94],"paths":[96],"<em>./general/filePathShared.py</em>.":[98],"Set":[99,109,121,131],"<em>path_jingju_dataset</em>":[100],"parent":[103],"path":[104,113,125,135],"datasets.":[108],"<em>primarySchool_dataset_root_path</em>":[110],"interspeech2018":[116],"(the":[118],"current":[119],"dataset).":[120],"<em>nacta_dataset_root_path</em>":[122],"part1.":[130],"<em>nacta2017_dataset_root_path</em>":[132],"part2.":[139],"more":[141],"information":[142],"on":[143],"paper,":[145],"refer":[147],"Github":[150],"page:":[151],"https://github.com/ronggong/interspeech2018_submission01":[152]},"counts_by_year":[],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}