{"id":"https://openalex.org/W2939800755","doi":"https://doi.org/10.1109/icassp.2019.8683564","title":"Speaker-independent Classification of Phonetic Segments from Raw Ultrasound in Child Speech","display_name":"Speaker-independent Classification of Phonetic Segments from Raw Ultrasound in Child Speech","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939800755","doi":"https://doi.org/10.1109/icassp.2019.8683564","mag":"2939800755"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.01413","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109494794","display_name":"Manuel Sam Ribeiro","orcid":"https://orcid.org/0000-0001-8096-2231"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Manuel Sam Ribeiro","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049305990","display_name":"Aciel Eshky","orcid":"https://orcid.org/0000-0002-7746-3412"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aciel Eshky","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Korin Richmond","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109494794"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":2.0253,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.89918296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1328","last_page":"1332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9958000183105469,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9822999835014343,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7853742837905884},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.7596757411956787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7516241073608398},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.5335002541542053},{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.5301814079284668},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43491244316101074},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4230138659477234},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.42262983322143555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42073023319244385},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4183659553527832},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.333188533782959},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07189959287643433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853742837905884},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.7596757411956787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7516241073608398},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.5335002541542053},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.5301814079284668},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43491244316101074},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4230138659477234},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.42262983322143555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42073023319244385},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4183659553527832},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.333188533782959},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07189959287643433},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8683564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.01413","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.01413","pdf_url":"https://arxiv.org/pdf/1907.01413","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/87071137-b539-4896-b73b-550151ee5cd0","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/87071137-b539-4896-b73b-550151ee5cd0","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ribeiro, M S, Eshky, A, Richmond, K & Renals, S 2019, Speaker-Independent Classification of Phonetic Segments from Raw Ultrasound in Child Speech. in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, Brighton, United Kingdom, pp. 1328-1332, 44th International Conference on Acoustics, Speech, and Signal Processing, Brighton , United Kingdom, 12/05/19. https://doi.org/10.1109/ICASSP.2019.8683564","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/87071137-b539-4896-b73b-550151ee5cd0","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/87071137-b539-4896-b73b-550151ee5cd0","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.01413","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.01413","pdf_url":"https://arxiv.org/pdf/1907.01413","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"score":0.7200000286102295,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7869365812","display_name":null,"funder_award_id":"EP/P02338X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W91932436","https://openalex.org/W144370208","https://openalex.org/W1211067074","https://openalex.org/W1995440941","https://openalex.org/W1995735739","https://openalex.org/W2008120082","https://openalex.org/W2022423195","https://openalex.org/W2129160496","https://openalex.org/W2145442746","https://openalex.org/W2152262131","https://openalex.org/W2501279594","https://openalex.org/W2511959717","https://openalex.org/W2593268422","https://openalex.org/W2603597171","https://openalex.org/W2623570296","https://openalex.org/W2723896375","https://openalex.org/W2744379673","https://openalex.org/W2746109435","https://openalex.org/W2768153200","https://openalex.org/W2889224030","https://openalex.org/W2889418448","https://openalex.org/W2889853672","https://openalex.org/W2901322269","https://openalex.org/W2963272864","https://openalex.org/W4320815369","https://openalex.org/W6603833124","https://openalex.org/W6605905736","https://openalex.org/W6692304228","https://openalex.org/W6725830792","https://openalex.org/W6740755497","https://openalex.org/W6755833808"],"related_works":["https://openalex.org/W2082000062","https://openalex.org/W2206035908","https://openalex.org/W2058733683","https://openalex.org/W2150243332","https://openalex.org/W2804836678","https://openalex.org/W953964455","https://openalex.org/W2010642486","https://openalex.org/W4234201046","https://openalex.org/W2120882262","https://openalex.org/W2503775272"],"abstract_inverted_index":{"Ultrasound":[0],"tongue":[1,53],"imaging":[2],"(UTI)":[3],"provides":[4],"a":[5],"convenient":[6],"way":[7],"to":[8,27,31,46,55,91,118],"visualize":[9],"the":[10,48,64,110,114],"vocal":[11],"tract":[12],"during":[13],"speech":[14,22,40],"production.":[15],"UTI":[16],"is":[17,45],"increasingly":[18],"being":[19],"used":[20],"for":[21],"therapy,":[23],"making":[24],"it":[25],"important":[26],"develop":[28],"automatic":[29,49],"methods":[30],"assist":[32],"various":[33],"time-consuming":[34],"manual":[35],"tasks":[36],"currently":[37],"performed":[38],"by":[39],"therapists.":[41],"A":[42],"key":[43],"challenge":[44],"generalize":[47,116],"processing":[50],"of":[51,66],"ultrasound":[52,73,112],"images":[54],"previously":[56],"unseen":[57,119],"speakers.":[58,120],"In":[59],"this":[60],"work,":[61],"we":[62],"investigate":[63],"classification":[65],"phonetic":[67],"segments":[68],"(tongue":[69],"shapes)":[70],"from":[71,93],"raw":[72],"recordings":[74],"under":[75],"several":[76],"training":[77,98],"scenarios:":[78],"speaker-dependent,":[79],"multi-speaker,":[80],"speaker-independent,":[81],"and":[82],"speaker-adapted.":[83],"We":[84],"observe":[85],"that":[86],"models":[87,115],"underperform":[88],"when":[89,101],"applied":[90],"data":[92],"speakers":[94],"not":[95],"seen":[96],"at":[97],"time.":[99],"However,":[100],"provided":[102],"with":[103],"minimal":[104],"additional":[105],"speaker":[106],"information,":[107],"such":[108],"as":[109],"mean":[111],"frame,":[113],"better":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}