{"id":"https://openalex.org/W2890506449","doi":"https://doi.org/10.1109/icassp.2018.8462587","title":"Joint Gender-, Tone-, Vowel- Classification Via Novel Hierarchical Classification for Annotation of Monosyllabic Mandarin Word Tokens","display_name":"Joint Gender-, Tone-, Vowel- Classification Via Novel Hierarchical Classification for Annotation of Monosyllabic Mandarin Word Tokens","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2890506449","doi":"https://doi.org/10.1109/icassp.2018.8462587","mag":"2890506449"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5013136179","display_name":"Saurabh Garg","orcid":"https://orcid.org/0000-0001-8719-284X"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Saurabh Garg","raw_affiliation_strings":["Department of Linguistics, Simon Fraser University, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics, Simon Fraser University, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072684302","display_name":"Ghassan Hamarneh","orcid":"https://orcid.org/0000-0001-5040-7448"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ghassan Hamarneh","raw_affiliation_strings":["Medical Image Analysis Lab, Simon Fraser University (SFU), Canada"],"affiliations":[{"raw_affiliation_string":"Medical Image Analysis Lab, Simon Fraser University (SFU), Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068290371","display_name":"Allard Jongman","orcid":"https://orcid.org/0000-0002-7384-2036"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allard Jongman","raw_affiliation_strings":["Department of Linguistics, University of Kansas (KU), USA"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics, University of Kansas (KU), USA","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080409793","display_name":"Joan A. Sereno","orcid":"https://orcid.org/0000-0002-1227-7715"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joan Sereno","raw_affiliation_strings":["Department of Linguistics, University of Kansas (KU), USA"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics, University of Kansas (KU), USA","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100372089","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0146-7262"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["Department of Linguistics, Simon Fraser University, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics, Simon Fraser University, Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013136179"],"corresponding_institution_ids":["https://openalex.org/I18014758"],"apc_list":null,"apc_paid":null,"fwci":0.4887,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73069762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5744","last_page":"5748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8776553869247437},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.730888843536377},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6959238052368164},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6957847476005554},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.6894936561584473},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6237367987632751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.529657781124115},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5095770359039307},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.5074295401573181},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4428536891937256},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.42190301418304443},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13452854752540588}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8776553869247437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.730888843536377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6959238052368164},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6957847476005554},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.6894936561584473},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6237367987632751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.529657781124115},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5095770359039307},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5074295401573181},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4428536891937256},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.42190301418304443},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13452854752540588},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1512197617","https://openalex.org/W1518188273","https://openalex.org/W1550985492","https://openalex.org/W1875219865","https://openalex.org/W1880232642","https://openalex.org/W1977430937","https://openalex.org/W2017722841","https://openalex.org/W2032429609","https://openalex.org/W2117486215","https://openalex.org/W2145528340","https://openalex.org/W2160212752","https://openalex.org/W2170505850","https://openalex.org/W2188420569","https://openalex.org/W2341379805","https://openalex.org/W2405499418","https://openalex.org/W2406544397","https://openalex.org/W2411723680","https://openalex.org/W2471176452","https://openalex.org/W2492342376","https://openalex.org/W2515753980","https://openalex.org/W2870375580","https://openalex.org/W4237468081","https://openalex.org/W4285719527","https://openalex.org/W4399448693","https://openalex.org/W6633010775","https://openalex.org/W6655056742","https://openalex.org/W6658511027","https://openalex.org/W6681515065","https://openalex.org/W6683777557","https://openalex.org/W6687175668","https://openalex.org/W6713699388","https://openalex.org/W6713747097","https://openalex.org/W6715014057"],"related_works":["https://openalex.org/W2393887907","https://openalex.org/W2347443630","https://openalex.org/W2388826840","https://openalex.org/W2481138693","https://openalex.org/W2379831327","https://openalex.org/W2386691339","https://openalex.org/W156219719","https://openalex.org/W2163874654","https://openalex.org/W2365805939","https://openalex.org/W2287147624"],"abstract_inverted_index":{"The":[0],"automatic":[1],"annotation":[2,24,133],"of":[3,41,51,100,130,138],"Mandarin":[4,63],"monosyllabic":[5],"audio":[6],"word":[7,35],"tokens":[8],"remains":[9],"an":[10,136],"important":[11],"yet":[12],"challenging":[13],"issue":[14],"in":[15,56,97,127],"phonetics":[16],"research.":[17],"In":[18],"this":[19,23],"work,":[20],"we":[21],"address":[22],"task":[25],"via":[26,37],"a":[27,77],"novel":[28,78],"subcategories-classification":[29],"framework":[30],"that":[31,65,91],"not":[32],"only":[33,67,112],"performs":[34,48],"identification":[36],"the":[38,52,123,131,147],"joint":[39],"classifications":[40],"vowel":[42],"and":[43,102,115],"tone":[44],"subcategories,":[45],"but":[46],"also":[47,75,121],"gender":[49],"discrimination":[50],"speaker,":[53,118],"which":[54],"stands":[55],"contrast":[57],"to":[58,82,142],"previously":[59],"proposed":[60],"methods":[61],"for":[62],"speech":[64],"focused":[66],"on":[68],"tone-,":[69],"vowel-,":[70],"or":[71],"gender-":[72],"classification.":[73],"We":[74],"propose":[76],"hierarchical":[79],"classification":[80,85,125],"algorithm":[81],"boost":[83],"overall":[84],"performance.":[86],"Extensive":[87],"experimental":[88],"results":[89],"show":[90],"our":[92,119],"approach":[93,120],"yielded":[94,122],"superior":[95],"performance":[96],"both":[98],"cases":[99],"adequate":[101],"very":[103],"limited":[104],"training":[105],"data.":[106],"When":[107],"trained":[108],"using":[109],"data":[110],"from":[111],"one":[113,116],"female":[114],"male":[117],"best":[124],"accuracy":[126],"all":[128],"subcategories":[129],"token":[132],"problem,":[134],"achieving":[135],"Fl-score":[137],"0.742":[139],"as":[140,144],"opposed":[141],"0.705":[143],"achieved":[145],"by":[146],"second":[148],"competing":[149],"approach.":[150]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}