{"id":"https://openalex.org/W3162588046","doi":"https://doi.org/10.1109/icassp39728.2021.9414203","title":"Singing Language Identification Using a Deep Phonotactic Approach","display_name":"Singing Language Identification Using a Deep Phonotactic Approach","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162588046","doi":"https://doi.org/10.1109/icassp39728.2021.9414203","mag":"3162588046"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.15014","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054555889","display_name":"Lenny Renault","orcid":"https://orcid.org/0000-0001-5261-7756"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lenny Renault","raw_affiliation_strings":["Deezer Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deezer Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002946055","display_name":"Andrea Vaglio","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Andrea Vaglio","raw_affiliation_strings":["Deezer Research","LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deezer Research","institution_ids":[]},{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004879177","display_name":"Romain Hennequin","orcid":"https://orcid.org/0000-0001-8158-5562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romain Hennequin","raw_affiliation_strings":["Deezer Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deezer Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9065,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73757592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"271","last_page":"275"},"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":0.9994000196456909,"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":0.9972000122070312,"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/phonotactics","display_name":"Phonotactics","score":0.867547869682312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7896448969841003},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7812348008155823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6581735610961914},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6026052236557007},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5925440788269043},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5038596987724304},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48809778690338135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41117021441459656},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34046101570129395},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.17020362615585327},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.112651526927948},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08913111686706543}],"concepts":[{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.867547869682312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896448969841003},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7812348008155823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6581735610961914},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6026052236557007},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5925440788269043},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5038596987724304},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48809778690338135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41117021441459656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34046101570129395},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.17020362615585327},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.112651526927948},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08913111686706543},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.15014","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.15014","pdf_url":"https://arxiv.org/pdf/2105.15014","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.15014","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.15014","pdf_url":"https://arxiv.org/pdf/2105.15014","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":42,"referenced_works":["https://openalex.org/W99528949","https://openalex.org/W135838486","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1586200585","https://openalex.org/W1899504021","https://openalex.org/W2057745663","https://openalex.org/W2059363583","https://openalex.org/W2104457544","https://openalex.org/W2116373735","https://openalex.org/W2124758433","https://openalex.org/W2127141656","https://openalex.org/W2170416904","https://openalex.org/W2295094876","https://openalex.org/W2400969690","https://openalex.org/W2408021097","https://openalex.org/W2500162720","https://openalex.org/W2515533971","https://openalex.org/W2563351168","https://openalex.org/W2786835190","https://openalex.org/W2903006902","https://openalex.org/W2917340025","https://openalex.org/W2941349731","https://openalex.org/W2963032538","https://openalex.org/W2963112418","https://openalex.org/W2964121744","https://openalex.org/W2972856300","https://openalex.org/W3016156006","https://openalex.org/W3037149862","https://openalex.org/W4235128394","https://openalex.org/W6604053933","https://openalex.org/W6605595087","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6631636882","https://openalex.org/W6634879495","https://openalex.org/W6687442591","https://openalex.org/W6697145955","https://openalex.org/W6713219328","https://openalex.org/W6731031554","https://openalex.org/W6758930882","https://openalex.org/W6762288408"],"related_works":["https://openalex.org/W2615317726","https://openalex.org/W2021909761","https://openalex.org/W198649858","https://openalex.org/W2411659965","https://openalex.org/W2467354670","https://openalex.org/W2498910126","https://openalex.org/W2387677326","https://openalex.org/W2497306275","https://openalex.org/W1602082497","https://openalex.org/W4200063482"],"abstract_inverted_index":{"Extensive":[0],"works":[1],"have":[2],"tackled":[3],"Language":[4,23],"Identification":[5,24],"(LID)":[6],"in":[7,33],"the":[8,15,75],"speech":[9],"domain,":[10],"however":[11],"their":[12],"application":[13],"to":[14],"singing":[16,35],"voice":[17],"trails":[18],"and":[19,83,88],"performances":[20],"on":[21,47,74],"Singing":[22],"(SLID)":[25],"can":[26],"be":[27],"improved":[28],"leveraging":[29],"recent":[30],"progresses":[31],"made":[32],"other":[34],"related":[36],"tasks.":[37],"This":[38],"work":[39],"presents":[40],"a":[41,55,70,86],"modernized":[42],"phonotactic":[43],"system":[44],"for":[45],"SLID":[46,98],"polyphonic":[48],"music:":[49],"phoneme":[50],"recognition":[51],"is":[52,81],"performed":[53],"with":[54,63,69,85,92,99],"Connectionist":[56],"Temporal":[57],"Classification":[58],"(CTC)-based":[59],"acoustic":[60],"model":[61,72],"trained":[62,82],"multilingual":[64],"data,":[65],"before":[66],"language":[67],"classification":[68],"recurrent":[71],"based":[73],"phonemes":[76],"estimation.":[77],"The":[78],"full":[79],"pipeline":[80],"evaluated":[84],"large":[87],"publicly":[89],"available":[90],"dataset,":[91],"unprecedented":[93],"performances.":[94],"First":[95],"results":[96],"of":[97],"out-of-set":[100],"languages":[101],"are":[102],"also":[103],"presented.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}