{"id":"https://openalex.org/W2962786824","doi":"https://doi.org/10.21437/interspeech.2018-1224","title":"Singing Voice Phoneme Segmentation by Hierarchically Inferring Syllable and Phoneme Onset Positions","display_name":"Singing Voice Phoneme Segmentation by Hierarchically Inferring Syllable and Phoneme Onset Positions","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2962786824","doi":"https://doi.org/10.21437/interspeech.2018-1224","mag":"2962786824"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1224","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repositori.upf.edu/bitstreams/57308059-ac2a-435d-8ab9-0fe97f6c6bcf/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rong Gong","orcid":null},"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":"Rong Gong","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","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":"Xavier Serra","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","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":0.1804,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4576119,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"716","last_page":"720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7838923931121826},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7830554246902466},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7824867963790894},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6746358275413513},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.647667646408081},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6178083419799805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5569735765457153},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4694882035255432},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4689359664916992},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.42488592863082886},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1761464774608612}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7838923931121826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7830554246902466},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7824867963790894},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6746358275413513},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.647667646408081},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6178083419799805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5569735765457153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4694882035255432},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4689359664916992},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.42488592863082886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1761464774608612},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1224","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori.upf.edu:10230/37115","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/37115","pdf_url":"https://repositori.upf.edu/bitstreams/57308059-ac2a-435d-8ab9-0fe97f6c6bcf/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:repositori.upf.edu:10230/37115","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/37115","pdf_url":"https://repositori.upf.edu/bitstreams/57308059-ac2a-435d-8ab9-0fe97f6c6bcf/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962786824.pdf","grobid_xml":"https://content.openalex.org/works/W2962786824.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W92207287","https://openalex.org/W182406043","https://openalex.org/W1164175658","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1558543783","https://openalex.org/W1585181552","https://openalex.org/W1875231349","https://openalex.org/W2042390666","https://openalex.org/W2075329984","https://openalex.org/W2088867696","https://openalex.org/W2115076730","https://openalex.org/W2134387846","https://openalex.org/W2144827818","https://openalex.org/W2168052445","https://openalex.org/W2174992124","https://openalex.org/W2201063935","https://openalex.org/W2482558056","https://openalex.org/W2518427066","https://openalex.org/W2573694925","https://openalex.org/W2577736846","https://openalex.org/W2580796476","https://openalex.org/W2604509013","https://openalex.org/W2624871570","https://openalex.org/W2747874407","https://openalex.org/W2770424094","https://openalex.org/W2771429098","https://openalex.org/W4253573210"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2158625849","https://openalex.org/W1968372539","https://openalex.org/W4317625904"],"abstract_inverted_index":{"Comunicaci\u00f3":[0],"presentada":[1],"a:":[2],"Interspeech":[3],"2018,":[4],"celebrada":[5],"del":[6],"2":[7],"al":[8],"6":[9],"de":[10,12],"setembre":[11],"2018":[13],"a":[14],"Hyderabad,":[15],"India.":[16]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
