{"id":"https://openalex.org/W4415433183","doi":"https://doi.org/10.21437/interspeech.2025-1599","title":"No Audiogram: Leveraging Existing Scores for Personalized Speech Intelligibility Prediction","display_name":"No Audiogram: Leveraging Existing Scores for Personalized Speech Intelligibility Prediction","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433183","doi":"https://doi.org/10.21437/interspeech.2025-1599"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1599","doi":"https://doi.org/10.21437/interspeech.2025-1599","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1599","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.02039","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018174793","display_name":"Haoshuai Zhou","orcid":"https://orcid.org/0009-0005-9851-3713","observed_orcids":["https://orcid.org/0009-0005-9851-3713"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoshuai Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119835694","display_name":"Changgeng Mo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changgeng Mo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119835693","display_name":"Boxuan Cao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boxuan Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101399443","display_name":"Linkai Li","orcid":"https://orcid.org/0000-0001-6531-3305","observed_orcids":["https://orcid.org/0000-0001-6531-3305"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linkai Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012766019","display_name":"Shan Xiang Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan Xiang Wang","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":0.6407,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62760284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"5468","last_page":"5472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7896000146865845,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7896000146865845,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.19689999520778656,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.004399999976158142,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-foundation-models","display_name":"speech foundation models","score":0.7319999933242798},{"id":"https://openalex.org/keywords/audiogram","display_name":"audiogram","score":0.42100000381469727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5982999801635742},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5245000123977661},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5234000086784363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4074000120162964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.23100000619888306},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2273000031709671},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.22269999980926514},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.21070000529289246},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2029999941587448}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-1599","doi":"https://doi.org/10.21437/interspeech.2025-1599","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1599","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.02039","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.02039","pdf_url":"https://arxiv.org/pdf/2506.02039","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.2506.02039","doi":"https://doi.org/10.48550/arxiv.2506.02039","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.02039","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.02039","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.02039","pdf_url":"https://arxiv.org/pdf/2506.02039","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433183.pdf","grobid_xml":"https://content.openalex.org/works/W4415433183.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2622263826","https://openalex.org/W4394642372"],"related_works":["https://openalex.org/W7165675509","https://openalex.org/W4295808794","https://openalex.org/W4367459805","https://openalex.org/W4285162109","https://openalex.org/W2601317809","https://openalex.org/W4387363548","https://openalex.org/W7155071850","https://openalex.org/W4387350634","https://openalex.org/W2260512115","https://openalex.org/W4381546369"],"abstract_inverted_index":{"Personalized":[0],"speech":[1,70,81,128],"intelligibility":[2,46,129],"prediction":[3],"is":[4],"challenging.":[5],"Previous":[6],"approaches":[7],"have":[8],"mainly":[9],"relied":[10],"on":[11,52,97],"audiograms,":[12],"which":[13],"are":[14],"inherently":[15],"limited":[16],"in":[17],"accuracy":[18],"as":[19],"they":[20],"only":[21],"capture":[22],"a":[23,38,64,75,79,107,123],"listener's":[24,80],"hearing":[25],"threshold":[26],"for":[27,93,126],"pure":[28],"tones.":[29],"Rather":[30],"than":[31],"incorporating":[32],"additional":[33],"listener":[34],"features,":[35],"we":[36],"propose":[37],"novel":[39],"approach":[40],"that":[41,68],"leverages":[42,69],"an":[43],"individual's":[44],"existing":[45],"data":[47],"to":[48,73],"predict":[49],"their":[50],"performance":[51],"new":[53,124],"audio.":[54,95],"We":[55],"introduce":[56],"the":[57,98],"Support":[58],"Sample-Based":[59],"Intelligibility":[60],"Prediction":[61,100],"Network":[62],"(SSIPNet),":[63],"deep":[65],"learning":[66],"model":[67],"foundation":[71],"models":[72],"build":[74],"high-dimensional":[76],"representation":[77],"of":[78,110],"recognition":[82],"ability":[83],"from":[84],"multiple":[85],"support":[86,111],"(audio,":[87,112],"score)":[88,113],"pairs,":[89,114],"enabling":[90],"accurate":[91],"predictions":[92],"unseen":[94],"Results":[96],"Clarity":[99],"Challenge":[101],"dataset":[102],"show":[103],"that,":[104],"even":[105],"with":[106],"small":[108],"number":[109],"our":[115],"method":[116],"outperforms":[117],"audiogram-based":[118],"predictions.":[119],"Our":[120],"work":[121],"presents":[122],"paradigm":[125],"personalized":[127],"prediction.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-24T00:00:00"}