{"id":"https://openalex.org/W4402111983","doi":"https://doi.org/10.21437/interspeech.2024-822","title":"A data-driven model of acoustic speech intelligibility for optimization-based models of speech production","display_name":"A data-driven model of acoustic speech intelligibility for optimization-based models of speech production","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111983","doi":"https://doi.org/10.21437/interspeech.2024-822"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-822","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-822","pdf_url":"https://www.isca-archive.org/interspeech_2024/elie24_interspeech.pdf","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":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/elie24_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048947917","display_name":"Benjamin Elie","orcid":"https://orcid.org/0000-0001-5889-763X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Elie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081754009","display_name":"Juraj \u0160imko","orcid":"https://orcid.org/0000-0002-8693-9646"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juraj Simko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004886061","display_name":"Alice Turk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alice Turk","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":0.2773,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61522013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3610","last_page":"3614"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8668000102043152,"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":0.8668000102043152,"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":0.8051000237464905,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8198959827423096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7376142740249634},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.621421754360199},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5718667507171631},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.568462610244751},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44114768505096436},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.382264643907547}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8198959827423096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376142740249634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.621421754360199},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5718667507171631},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.568462610244751},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44114768505096436},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.382264643907547},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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":1,"locations":[{"id":"doi:10.21437/interspeech.2024-822","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-822","pdf_url":"https://www.isca-archive.org/interspeech_2024/elie24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-822","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-822","pdf_url":"https://www.isca-archive.org/interspeech_2024/elie24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111983.pdf","grobid_xml":"https://content.openalex.org/works/W4402111983.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2081919107","https://openalex.org/W3115948027","https://openalex.org/W2405110677","https://openalex.org/W2334129531","https://openalex.org/W2811496854","https://openalex.org/W1977838979","https://openalex.org/W2515097069","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4300049944"],"abstract_inverted_index":{"This":[0],"paper":[1,74],"presents":[2],"a":[3,26,31,49,102],"data-driven":[4,68],"model":[5,17,22,70],"of":[6,18,33,43,57,61,87,92,94,112],"intelligibility":[7,69,80,113],"which":[8,52],"is":[9,23,53,75],"intended":[10],"to":[11,77,109],"be":[12,97],"used":[13,76],"in":[14,72],"an":[15],"optimization-based":[16],"speech":[19,95],"production.The":[20],"BiLSTM-based":[21],"trained":[24],"as":[25,37,89],"phoneme":[27],"classifier":[28],"and":[29,39,64,99,114],"takes":[30],"sequence":[32],"real":[34],"articulatory":[35,66,116],"trajectories":[36],"input":[38],"returns":[40],"the":[41,54,58,79,90,106],"probability":[42],"phonemes":[44],"over":[45],"time.The":[46],"optimization":[47],"minimizes":[48],"cost":[50],"function":[51],"weighted":[55],"sum":[56],"conflicting":[59],"demands":[60],"being":[62],"intelligible":[63],"least":[65,115],"effort.The":[67],"presented":[71],"this":[73],"compute":[78],"score.Simulations":[81],"support":[82],"Lindblom's":[83],"hypo-and":[84],"hyper-articulation":[85,93],"theory":[86],"speech,":[88],"degree":[91],"can":[96],"modified":[98],"tuned":[100],"along":[101],"continuum":[103],"by":[104],"balancing":[105],"importance":[107],"given":[108],"both":[110],"requirements":[111],"effort.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}
