{"id":"https://openalex.org/W4296069280","doi":"https://doi.org/10.21437/interspeech.2022-10874","title":"Articulatory Synthesis for Data Augmentation in Phoneme Recognition","display_name":"Articulatory Synthesis for Data Augmentation in Phoneme Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069280","doi":"https://doi.org/10.21437/interspeech.2022-10874"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10874","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10874","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://discovery.ucl.ac.uk/10158547/1/krug22_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004916681","display_name":"Paul Konstantin Krug","orcid":"https://orcid.org/0000-0001-8518-8142"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Konstantin Krug","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046141664","display_name":"Peter Birkholz","orcid":"https://orcid.org/0000-0003-0167-8123"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Birkholz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001239900","display_name":"Branislav Gerazov","orcid":"https://orcid.org/0000-0003-2498-6831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Branislav Gerazov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057837548","display_name":"Daniel van Niekerk","orcid":"https://orcid.org/0000-0002-7324-2751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Rudolph van Niekerk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022797639","display_name":"Anqi Xu","orcid":"https://orcid.org/0000-0002-4331-6676"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anqi Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100419183","display_name":"Yi Xu","orcid":"https://orcid.org/0000-0002-5768-8235"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5191,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6367877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1228","last_page":"1232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9664000272750854,"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":0.9664000272750854,"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/computer-science","display_name":"Computer science","score":0.7364198565483093},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7167727947235107},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4247794449329376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3968714475631714}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7364198565483093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7167727947235107},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4247794449329376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3968714475631714}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-10874","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10874","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10158547","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10158547/","pdf_url":"https://discovery.ucl.ac.uk/10158547/1/krug22_interspeech.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH.  (pp. pp. 1228-1232).  International Speech Communication Association (ISCA): Incheon, Korea. (2022)     ","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10158547","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10158547/","pdf_url":"https://discovery.ucl.ac.uk/10158547/1/krug22_interspeech.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH.  (pp. pp. 1228-1232).  International Speech Communication Association (ISCA): Incheon, Korea. (2022)     ","raw_type":"Proceedings paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4296069280.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W3204019825"],"abstract_inverted_index":{"While":[0],"numerous":[1],"studies":[2,114],"on":[3,18,28,95],"automatic":[4,130],"speech":[5,39,127,131],"recognition":[6,77],"have":[7],"been":[8],"published":[9],"in":[10,75,78,91],"recent":[11],"years":[12],"describing":[13],"data":[14,34,52,67],"augmentation":[15],"strategies":[16],"based":[17],"time":[19],"or":[20],"frequency":[21],"domain":[22],"signal":[23],"processing,":[24],"few":[25],"works":[26],"exist":[27],"the":[29,44,55,64,83,86,96,102,117,123],"artificial":[30],"extensions":[31],"of":[32,98,101,119],"training":[33],"sets":[35],"using":[36],"purely":[37],"synthetic":[38,51,66,103,126],"data.":[40],"In":[41],"this":[42,108],"work,":[43],"German":[45],"KIEL":[46],"corpus":[47],"was":[48],"augmented":[49],"with":[50,54],"generated":[53],"state-of-the-art":[56],"articulatory":[57,120],"synthesizer":[58],"VOCALTRACTLAB.":[59],"It":[60],"is":[61],"shown":[62],"that":[63],"additional":[65],"can":[68,88,110],"lead":[69],"to":[70,115],"a":[71,106],"significantly":[72],"better":[73],"performance":[74,87],"single-phoneme":[76],"certain":[79],"cases,":[80,93],"while":[81],"at":[82],"same":[84],"time,":[85],"also":[89],"decrease":[90],"other":[92],"depending":[94],"degree":[97],"acoustic":[99],"naturalness":[100],"phonemes.":[104],"As":[105],"result,":[107],"work":[109],"potentially":[111],"guide":[112],"future":[113],"improve":[116],"quality":[118],"synthesis":[121],"via":[122],"link":[124],"between":[125],"production":[128],"and":[129],"recognition.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}