{"id":"https://openalex.org/W4402111704","doi":"https://doi.org/10.21437/interspeech.2024-2134","title":"Towards Self-Attention Understanding for Automatic Articulatory Processes Analysis in Cleft Lip and Palate Speech","display_name":"Towards Self-Attention Understanding for Automatic Articulatory Processes Analysis in Cleft Lip and Palate Speech","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111704","doi":"https://doi.org/10.21437/interspeech.2024-2134"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-2134","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","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/A5047469130","display_name":"Ilja Baumann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilja Baumann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016617263","display_name":"Dominik Wagner","orcid":"https://orcid.org/0000-0002-3631-4138"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dominik Wagner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061935473","display_name":"Maria Schuster","orcid":"https://orcid.org/0000-0001-9122-7478"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria Schuster","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053498662","display_name":"Korbinian Riedhammer","orcid":"https://orcid.org/0000-0003-3582-2154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korbinian Riedhammer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023454896","display_name":"Elmar Noeth","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elmar Noeth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033302750","display_name":"Tobias Bocklet","orcid":"https://orcid.org/0009-0008-7780-8821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tobias Bocklet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5651,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71711628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2430","last_page":"2434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9419999718666077,"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":0.9419999718666077,"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":0.7096607089042664},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6052662134170532},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4141681492328644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3204222321510315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096607089042664},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6052662134170532},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4141681492328644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3204222321510315}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-2134","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:kobv.de-opus4-th-nuernberg:2314","is_oa":false,"landing_page_url":"https://opus4.kobv.de/opus4-ohm/frontdoor/index/index/docId/2314","pdf_url":null,"source":{"id":"https://openalex.org/S4306401730","display_name":"OHMdok (Technische Hochschule N\u00fcrnberg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210100612","host_organization_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","host_organization_lineage":["https://openalex.org/I4210100612"],"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":"conferenceobject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"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/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Cleft":[0],"lip":[1],"and":[2,19,119],"palate":[3],"(CLP)":[4],"speech":[5,28,47,90],"presents":[6],"unique":[7],"challenges":[8],"for":[9,101,112,117],"automatic":[10,103],"phoneme":[11,24,55,104],"analysis":[12,25,105],"due":[13],"to":[14,41,81],"its":[15],"distinct":[16],"acoustic":[17],"characteristics":[18],"articulatory":[20,69],"anomalies.":[21],"We":[22,57],"perform":[23],"in":[26,64,71,106],"CLP":[27,72,89,107],"using":[29],"a":[30,36],"pre-trained":[31],"wav2vec":[32],"2.0":[33],"model":[34],"with":[35],"multi-head":[37],"self-attention":[38,80],"classification":[39,66],"module":[40],"capture":[42],"long-range":[43],"dependencies":[44],"within":[45],"the":[46,59,65,77,85,95,98,110],"signal,":[48],"thereby":[49],"enabling":[50],"better":[51],"contextual":[52],"understanding":[53,87],"of":[54,61,67,79,88,97],"sequences.":[56],"demonstrate":[58],"effectiveness":[60],"our":[62],"approach":[63],"various":[68],"processes":[70],"speech.":[73],"Furthermore,":[74],"we":[75],"investigate":[76],"interpretability":[78,116],"gain":[82],"insights":[83],"into":[84],"model\u2019s":[86],"characteristics.":[91],"Our":[92],"findings":[93],"highlight":[94],"potential":[96],"selfattention":[99],"mechanisms":[100],"improving":[102],"speech,":[108],"paving":[109],"way":[111],"enhanced":[113],"diagnostics,":[114],"adding":[115],"therapists":[118],"affected":[120],"patients.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
