{"id":"https://openalex.org/W2955846730","doi":"https://doi.org/10.21437/interspeech.2019-2612","title":"Ultrasound Tongue Imaging for Diarization and Alignment of Child Speech Therapy Sessions","display_name":"Ultrasound Tongue Imaging for Diarization and Alignment of Child Speech Therapy Sessions","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2955846730","doi":"https://doi.org/10.21437/interspeech.2019-2612","mag":"2955846730"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2612","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.00818","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuel Sam Ribeiro","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049305990","display_name":"Aciel Eshky","orcid":"https://orcid.org/0000-0002-7746-3412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aciel Eshky","raw_affiliation_strings":["Institute of Language, Cognition and Computation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Language, Cognition and Computation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korin Richmond","raw_affiliation_strings":["School of Philosophy, Psychology, and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy, Psychology, and Language Sciences","institution_ids":[]}]},{"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":["University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9991999864578247,"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":0.9987000226974487,"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":0.6995878219604492},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6538634896278381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6481012105941772},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5612016320228577},{"id":"https://openalex.org/keywords/ultrasound","display_name":"Ultrasound","score":0.5015275478363037},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4973490536212921},{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.488901287317276},{"id":"https://openalex.org/keywords/ultrasound-imaging","display_name":"Ultrasound imaging","score":0.4513798952102661},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.4418385922908783},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.325320839881897},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.18764561414718628},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.13896268606185913},{"id":"https://openalex.org/keywords/radiology","display_name":"Radiology","score":0.07547584176063538}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995878219604492},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6538634896278381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6481012105941772},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5612016320228577},{"id":"https://openalex.org/C143753070","wikidata":"https://www.wikidata.org/wiki/Q162564","display_name":"Ultrasound","level":2,"score":0.5015275478363037},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4973490536212921},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.488901287317276},{"id":"https://openalex.org/C2986892559","wikidata":"https://www.wikidata.org/wiki/Q234904","display_name":"Ultrasound imaging","level":3,"score":0.4513798952102661},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.4418385922908783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.325320839881897},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.18764561414718628},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.13896268606185913},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.07547584176063538},{"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/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/interspeech.2019-2612","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.00818","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.00818","pdf_url":"https://arxiv.org/pdf/1907.00818","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":"mag:2955846730","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.00818.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:pure.ed.ac.uk:openaire/eab1a2bd-6ac9-4876-afb8-ba9c9aed7d9d","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/eab1a2bd-6ac9-4876-afb8-ba9c9aed7d9d","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, Eshky, A, Richmond, K & Renals, S 2019, Ultrasound tongue imaging for diarization and alignment of child speech therapy sessions. in INTERSPEECH 2019: Proceedings of the 20th Annual Conference of the International Speech Communication Association (ISCA). International Speech Communication Association, Graz, Austria, pp. 16-20, Interspeech 2019, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-2612","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/eab1a2bd-6ac9-4876-afb8-ba9c9aed7d9d","is_oa":true,"landing_page_url":"https://www.isca-speech.org/archive/Interspeech_2019/abstracts/2612.html","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, Eshky, A, Richmond, K & Renals, S 2019, Ultrasound tongue imaging for diarization and alignment of child speech therapy sessions. in INTERSPEECH 2019: Proceedings of the 20th Annual Conference of the International Speech Communication Association (ISCA). International Speech Communication Association, Graz, Austria, pp. 16-20, Interspeech 2019, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-2612","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.1907.00818","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.00818","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.00818","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.00818","pdf_url":"https://arxiv.org/pdf/1907.00818","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W150713575","https://openalex.org/W1524333225","https://openalex.org/W1540779870","https://openalex.org/W1965819578","https://openalex.org/W1995440941","https://openalex.org/W2022423195","https://openalex.org/W2025556366","https://openalex.org/W2033757988","https://openalex.org/W2069584151","https://openalex.org/W2081074144","https://openalex.org/W2085628288","https://openalex.org/W2087570929","https://openalex.org/W2101307193","https://openalex.org/W2292479959","https://openalex.org/W2292656914","https://openalex.org/W2295119550","https://openalex.org/W2401277329","https://openalex.org/W2402172738","https://openalex.org/W2405263627","https://openalex.org/W2471412687","https://openalex.org/W2511419867","https://openalex.org/W2512506745","https://openalex.org/W2587126577","https://openalex.org/W2750259098","https://openalex.org/W2889418448","https://openalex.org/W2901322269","https://openalex.org/W2939800755"],"related_works":["https://openalex.org/W91932436","https://openalex.org/W3181806133","https://openalex.org/W2146499996","https://openalex.org/W2316138215","https://openalex.org/W3164409797","https://openalex.org/W2744379673","https://openalex.org/W3140645045","https://openalex.org/W2294901616","https://openalex.org/W1583773829","https://openalex.org/W2967498147","https://openalex.org/W2623570296","https://openalex.org/W341711312","https://openalex.org/W2035632683","https://openalex.org/W2102986479","https://openalex.org/W2945998549","https://openalex.org/W2987026005","https://openalex.org/W2900292050","https://openalex.org/W3163287738","https://openalex.org/W2889624961","https://openalex.org/W3160672713"],"abstract_inverted_index":{"We":[0,76],"investigate":[1],"the":[2,26,29,68,81,110],"automatic":[3],"processing":[4],"of":[5,25,31,36,64,67,84],"child":[6,90],"speech":[7,87,91],"therapy":[8,92],"sessions":[9],"using":[10,80,108],"ultrasound":[11,23,65,85,103],"visual":[12],"biofeedback,":[13],"with":[14,22,61,102],"a":[15,72],"specific":[16],"focus":[17],"on":[18],"complementing":[19],"acoustic":[20,59],"features":[21],"images":[24,66],"tongue":[27,52],"for":[28,89],"tasks":[30],"speaker":[32,40],"diarization":[33],"and":[34,86],"time-alignment":[35],"target":[37],"words.":[38],"For":[39,54,94],"diarization,":[41],"we":[42,49,56,97],"propose":[43],"an":[44,58],"ultrasound-based":[45],"time-domain":[46],"signal":[47],"which":[48],"call":[50],"estimated":[51],"activity.":[53],"word-alignment,":[55],"augment":[57],"model":[60],"low-dimensional":[62],"representations":[63],"tongue,":[69],"learned":[70],"by":[71],"convolutional":[73],"neural":[74],"network.":[75],"conduct":[77],"our":[78],"experiments":[79],"Ultrasuite":[82],"repository":[83],"recordings":[88],"sessions.":[93],"both":[95],"tasks,":[96],"observe":[98],"that":[99],"systems":[100,107],"augmented":[101],"data":[104],"outperform":[105],"corresponding":[106],"only":[109],"audio":[111],"signal.":[112]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}