{"id":"https://openalex.org/W4392910314","doi":"https://doi.org/10.1109/icassp48485.2024.10447632","title":"Towards Interpretability of Automatic Phoneme Analysis in Cleft Lip and Palate Speech","display_name":"Towards Interpretability of Automatic Phoneme Analysis in Cleft Lip and Palate Speech","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910314","doi":"https://doi.org/10.1109/icassp48485.2024.10447632"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5076479722","display_name":"Ilja Baumann","orcid":"https://orcid.org/0000-0002-1991-3710"},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ilja Baumann","raw_affiliation_strings":["Technische Hochschule Nürnberg Georg Simon Ohm,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany","institution_ids":["https://openalex.org/I4210100612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016617263","display_name":"Dominik Wagner","orcid":"https://orcid.org/0000-0002-3631-4138"},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Wagner","raw_affiliation_strings":["Technische Hochschule Nürnberg Georg Simon Ohm,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany","institution_ids":["https://openalex.org/I4210100612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061935473","display_name":"Maria Schuster","orcid":"https://orcid.org/0000-0001-9122-7478"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maria Schuster","raw_affiliation_strings":["Ludwig-Maximilians University,Department of Otorhinolaryngology, Head and Neck Surgery,Germany","Department of Otorhinolaryngology, Head and Neck Surgery, Ludwig-Maximilians University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians University,Department of Otorhinolaryngology, Head and Neck Surgery,Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Department of Otorhinolaryngology, Head and Neck Surgery, Ludwig-Maximilians University, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054443473","display_name":"Elmar N\u00f6th","orcid":"https://orcid.org/0000-0002-3396-555X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elmar N\u00f6th","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg,Pattern Recognition Lab,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg,Pattern Recognition Lab,Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033302750","display_name":"Tobias Bocklet","orcid":"https://orcid.org/0009-0008-7780-8821"},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Bocklet","raw_affiliation_strings":["Technische Hochschule Nürnberg Georg Simon Ohm,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany","institution_ids":["https://openalex.org/I4210100612"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2825,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57545759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12602","last_page":"12606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.899399995803833,"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":0.899399995803833,"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/interpretability","display_name":"Interpretability","score":0.9407562017440796},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.67294842004776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6541476845741272},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5025014877319336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40158581733703613}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9407562017440796},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.67294842004776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6541476845741272},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5025014877319336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40158581733703613}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:kobv.de-opus4-th-nuernberg:1755","is_oa":false,"landing_page_url":"https://opus4.kobv.de/opus4-ohm/frontdoor/index/index/docId/1755","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1820401534","https://openalex.org/W1993897419","https://openalex.org/W2048251069","https://openalex.org/W2090755665","https://openalex.org/W2095705004","https://openalex.org/W2122364000","https://openalex.org/W2171208768","https://openalex.org/W2899663614","https://openalex.org/W2970726176","https://openalex.org/W2972324944","https://openalex.org/W3036601975","https://openalex.org/W3085380432","https://openalex.org/W4297841747","https://openalex.org/W4375869379","https://openalex.org/W4385823067","https://openalex.org/W6631362777","https://openalex.org/W6674330103","https://openalex.org/W6734194636","https://openalex.org/W6736518430","https://openalex.org/W6753485147","https://openalex.org/W6755977528","https://openalex.org/W6764072591","https://openalex.org/W6780218876","https://openalex.org/W6783213970"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Cleft":[0],"Lip":[1],"and":[2,11,47,67,179],"Palate":[3],"ranks":[4],"among":[5],"the":[6,57,80,94,98,105,116,131,135,151,154,163,170],"most":[7],"common":[8],"congenital":[9],"abnormalities":[10],"significantly":[12],"influences":[13],"speech":[14,95],"articulation,":[15],"resulting":[16],"in":[17,129],"varying":[18],"phonemic":[19,62],"impacts.":[20],"In":[21],"a":[22,25,49,65,87,126,183],"clinical":[23,189],"context,":[24],"detailed":[26],"diagnosis":[27],"is":[28,72,169],"carried":[29],"out":[30],"by":[31,145],"time-consuming":[32],"perceptual":[33,37],"evaluations.":[34],"We":[35],"use":[36],"ratings":[38,114],"of":[39,60,82,90,93,134,153,165],"different":[40],"articulatory":[41,176],"modifications":[42,177],"on":[43,52,76,101],"phoneme-level":[44,180],"as":[45,64],"ground-truth":[46],"propose":[48],"system":[50,71,110],"based":[51],"wav2vec":[53],"2.0,":[54],"trained":[55,73],"to":[56,107,150],"downstream":[58],"task":[59],"classifying":[61],"criteria":[63],"multi-class":[66],"multi-label":[68],"problem.":[69],"The":[70,138],"for":[74,187],"detection":[75],"utterance":[77],"level,":[78],"without":[79],"usage":[81],"phoneme":[83,117],"labels.":[84],"To":[85,162],"gain":[86],"clearer":[88],"understanding":[89,186],"which":[91,108,122],"areas":[92],"signal":[96],"have":[97],"greatest":[99],"impact":[100],"classification,":[102],"we":[103,120],"assess":[104],"extent":[106],"our":[109,166],"aligns":[111],"with":[112],"expert":[113],"at":[115],"level.":[118],"Additionally,":[119],"examine":[121],"specific":[123],"phonemes":[124,143],"play":[125],"decisive":[127],"role":[128],"determining":[130],"final":[132],"classification":[133,152,178],"labeled":[136],"criteria.":[137],"results":[139],"show":[140],"that":[141],"salient":[142],"marked":[144],"experts":[146],"contribute":[147],"remarkably":[148],"greater":[149],"correct":[155],"class":[156],"using":[157],"feature":[158],"relevance":[159],"explanation":[160],"methods.":[161],"best":[164],"knowledge,":[167],"this":[168],"first":[171],"study":[172],"incorporating":[173],"various":[174],"utterance-level":[175],"interpretation,":[181],"offering":[182],"more":[184],"comprehensive":[185],"potential":[188],"applications.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}