{"id":"https://openalex.org/W2770107007","doi":"https://doi.org/10.1109/taslp.2017.2751747","title":"Crosslingual and Multilingual Speech Recognition Based on the Speech Manifold","display_name":"Crosslingual and Multilingual Speech Recognition Based on the Speech Manifold","publication_year":2017,"publication_date":"2017-11-23","ids":{"openalex":"https://openalex.org/W2770107007","doi":"https://doi.org/10.1109/taslp.2017.2751747","mag":"2770107007"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2751747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2751747","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5019931395","display_name":"Reza Sahraeian","orcid":"https://orcid.org/0000-0002-6240-1438"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Reza Sahraeian","raw_affiliation_strings":["Center of Processing Speech and Image, Department of Electrical Engineering, Katholieke Universiteit Leuven, 3000 Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Processing Speech and Image, Department of Electrical Engineering, Katholieke Universiteit Leuven, 3000 Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041039488","display_name":"Dirk Van Compernolle","orcid":"https://orcid.org/0000-0003-0075-848X"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dirk Van Compernolle","raw_affiliation_strings":["Center of Processing Speech and Image, Department of Electrical Engineering, Katholieke Universiteit Leuven, 3000 Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Processing Speech and Image, Department of Electrical Engineering, Katholieke Universiteit Leuven, 3000 Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2392,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.85666582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"25","issue":"12","first_page":"2301","last_page":"2312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/computer-science","display_name":"Computer science","score":0.8000094890594482},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5878675580024719},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5467057824134827},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49212855100631714},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4796224534511566},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4681413769721985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46048176288604736},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43683600425720215},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.42307159304618835},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.18977141380310059},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09389039874076843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000094890594482},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5878675580024719},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5467057824134827},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49212855100631714},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4796224534511566},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4681413769721985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46048176288604736},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43683600425720215},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.42307159304618835},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.18977141380310059},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09389039874076843},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2017.2751747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2751747","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/614965","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/bitstream/123456789/614965/1/4260_final.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE-acm Transactions on Audio Speech and Language Processing, vol. 25 (12), Art.No. 12, (2301-2312)","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W60202269","https://openalex.org/W73572011","https://openalex.org/W120587654","https://openalex.org/W181056519","https://openalex.org/W262894896","https://openalex.org/W565868953","https://openalex.org/W1524333225","https://openalex.org/W1604771987","https://openalex.org/W1645145786","https://openalex.org/W1762484328","https://openalex.org/W1846073453","https://openalex.org/W1944979302","https://openalex.org/W1970890968","https://openalex.org/W1980850109","https://openalex.org/W1994606281","https://openalex.org/W2002276939","https://openalex.org/W2010800472","https://openalex.org/W2025198378","https://openalex.org/W2026149420","https://openalex.org/W2033436836","https://openalex.org/W2034829178","https://openalex.org/W2039763773","https://openalex.org/W2044048901","https://openalex.org/W2057781541","https://openalex.org/W2065136108","https://openalex.org/W2079508481","https://openalex.org/W2084534958","https://openalex.org/W2090764203","https://openalex.org/W2091746061","https://openalex.org/W2097308346","https://openalex.org/W2098330974","https://openalex.org/W2101094502","https://openalex.org/W2106554350","https://openalex.org/W2109816097","https://openalex.org/W2118020555","https://openalex.org/W2123798005","https://openalex.org/W2125879978","https://openalex.org/W2127982613","https://openalex.org/W2130414229","https://openalex.org/W2132534451","https://openalex.org/W2147276082","https://openalex.org/W2147768505","https://openalex.org/W2151311453","https://openalex.org/W2151402979","https://openalex.org/W2160815625","https://openalex.org/W2165436104","https://openalex.org/W2172097686","https://openalex.org/W2213952365","https://openalex.org/W2292087804","https://openalex.org/W2294245963","https://openalex.org/W2294428026","https://openalex.org/W2295676751","https://openalex.org/W2399363370","https://openalex.org/W2406820985","https://openalex.org/W2582857964","https://openalex.org/W2963461438","https://openalex.org/W4206319965","https://openalex.org/W4230367971","https://openalex.org/W6602447114","https://openalex.org/W6602987424","https://openalex.org/W6604952573","https://openalex.org/W6609884412","https://openalex.org/W6631362777","https://openalex.org/W6635896687","https://openalex.org/W6637956674","https://openalex.org/W6688428952","https://openalex.org/W6696449567","https://openalex.org/W6696829052","https://openalex.org/W6697289540","https://openalex.org/W6697607580","https://openalex.org/W6712968304","https://openalex.org/W6713619563","https://openalex.org/W7045329624"],"related_works":["https://openalex.org/W2342410338","https://openalex.org/W2571805528","https://openalex.org/W2793105386","https://openalex.org/W2354804986","https://openalex.org/W1966366482","https://openalex.org/W2390182490","https://openalex.org/W1617657290","https://openalex.org/W4246292674","https://openalex.org/W2141183350","https://openalex.org/W2138052734"],"abstract_inverted_index":{"Speech":[0],"signals":[1],"are":[2,107,153],"produced":[3],"by":[4],"the":[5,11,57,84,97,138,169,202,216],"smooth":[6],"and":[7,28,33,38,125,198],"continuous":[8],"movements":[9],"of":[10,17,100,122,160,171,178,187,196],"human":[12],"articulators.":[13],"An":[14],"articulatory":[15],"representation":[16,99,166,180],"speech":[18,30,40,188,207],"is":[19,181],"considered":[20],"to":[21,50,62,77,89,109,128,155],"be":[22,63,110],"a":[23,64,73,79,117,157,185,194],"more":[24,26],"compact,":[25],"universal,":[27],"language-independent":[29],"feature":[31,81,87,92],"space":[32,88,140],"can,":[34],"therefore,":[35],"improve":[36],"crosslingual":[37,197],"multilingual":[39,132,199,203],"recognition":[41,189,208],"systems,":[42],"especially":[43],"when":[44,141,163],"porting":[45],"components":[46],"from":[47,83,131,215],"one":[48],"language":[49,161],"another":[51],"in":[52,96,120,168,184,193,211],"low-resource":[53,212],"scenarios.":[54],"However,":[55],"learning":[56,75],"acoustic-to-articulatory":[58],"conversion":[59],"has":[60],"proven":[61],"very":[65],"challenging":[66],"task.":[67],"In":[68],"this":[69,165,179],"paper,":[70],"we":[71,142],"utilize":[72],"manifold":[74],"technique":[76],"derive":[78],"nonlinear":[80],"transformation":[82],"conventional":[85],"filterbank":[86,172],"an":[90],"articulatory-like":[91],"space.":[93],"The":[94,176],"coordinates":[95,130],"resultant":[98],"which":[101,134],"some":[102],"have":[103,143],"demonstrable":[104],"phonological":[105],"meaning":[106],"shown":[108],"highly":[111],"portable":[112],"across":[113,219],"languages.":[114,220],"We":[115],"propose":[116],"proper":[118],"framework":[119],"terms":[121],"data":[123],"selection":[124],"graph":[126],"construction":[127],"train":[129],"data,":[133],"allows":[135],"for":[136],"training":[137],"coordinate":[139],"abundant":[144],"out-of-language":[145],"data.":[146],"Deep":[147],"neural":[148],"network":[149],"(DNN)":[150],"bottleneck":[151],"features":[152,173],"demonstrated":[154,183],"exhibit":[156],"greater":[158],"degree":[159],"independence":[162],"using":[164,191,201],"than":[167],"case":[170],"as":[174],"inputs.":[175],"usability":[177],"further":[182],"number":[186],"experiments":[190],"DNNs":[192],"variety":[195],"scenarios":[200],"GlobalPhone":[204],"dataset.":[205],"Especially,":[206],"systems":[209],"developed":[210],"settings":[213],"profit":[214],"improved":[217],"portability":[218]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
