{"id":"https://openalex.org/W3024872019","doi":"https://doi.org/10.21437/interspeech.2020-2121","title":"Automatic Estimation of Intelligibility Measure for Consonants in Speech","display_name":"Automatic Estimation of Intelligibility Measure for Consonants in Speech","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3024872019","doi":"https://doi.org/10.21437/interspeech.2020-2121","mag":"3024872019"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2121","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.06065","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062172410","display_name":"Ali Abavisani","orcid":"https://orcid.org/0000-0003-4235-9022"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Abavisani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","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":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1161","last_page":"1165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7378654479980469},{"id":"https://openalex.org/keywords/consonant","display_name":"Consonant","score":0.7369354367256165},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.718181312084198},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.6776840090751648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5543359518051147},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4623922109603882},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.41422972083091736},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3914186656475067}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7378654479980469},{"id":"https://openalex.org/C2778203577","wikidata":"https://www.wikidata.org/wiki/Q38035","display_name":"Consonant","level":3,"score":0.7369354367256165},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.718181312084198},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.6776840090751648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5543359518051147},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4623922109603882},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.41422972083091736},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3914186656475067},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-2121","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.06065","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.06065","pdf_url":"https://arxiv.org/pdf/2005.06065","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.06065","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.06065","pdf_url":"https://arxiv.org/pdf/2005.06065","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":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1861933605","https://openalex.org/W1970533835","https://openalex.org/W1980399492","https://openalex.org/W1994038057","https://openalex.org/W2005479302","https://openalex.org/W2021772487","https://openalex.org/W2026857116","https://openalex.org/W2028119394","https://openalex.org/W2095705004","https://openalex.org/W2117671523","https://openalex.org/W2156387975","https://openalex.org/W2402144811","https://openalex.org/W2404892923","https://openalex.org/W2776921726","https://openalex.org/W2954552820","https://openalex.org/W3209383001","https://openalex.org/W3216401400"],"related_works":["https://openalex.org/W1964706935","https://openalex.org/W2020946215","https://openalex.org/W2801025542","https://openalex.org/W1966580183","https://openalex.org/W2002773879","https://openalex.org/W2083136263","https://openalex.org/W4213283234","https://openalex.org/W4252296115","https://openalex.org/W2373394249","https://openalex.org/W2906310393"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3],"provide":[4],"a":[5,9,107,117,166],"model":[6],"to":[7,37,42,71,82,106,136,142,170],"estimate":[8,38,144],"real-valued":[10],"measure":[11,61,147,163],"of":[12,15,101,130,168],"the":[13,39,48,73,84,102,122,126,133,145,160,175],"intelligibility":[14,60],"individual":[16],"speech":[17,113],"segments.":[18],"We":[19],"trained":[20],"regression":[21],"models":[22,139],"based":[23,110],"on":[24,90,111,157,174],"Convolutional":[25],"Neural":[26],"Networks":[27],"(CNN)":[28],"for":[29,54,62],"stop":[30],"consonants":[31],"\\textipa{/p,t,k,b,d,g/}":[32],"associated":[33],"with":[34,97,148],"vowel":[35],"\\textipa{/A/},":[36],"corresponding":[40],"Signal":[41],"Noise":[43],"Ratio":[44],"(SNR)":[45],"at":[46,76,86,124],"which":[47,77,125],"Consonant-Vowel":[49],"(CV)":[50],"sound":[51,64],"becomes":[52,128],"intelligible":[53],"Normal":[55],"Hearing":[56],"(NH)":[57],"ears.":[58],"The":[59],"each":[63],"is":[65,69,104],"called":[66],"SNR$_{90}$,":[67],"and":[68],"defined":[70],"be":[72],"SNR":[74,123],"level":[75],"human":[78],"participants":[79],"are":[80],"able":[81,141],"recognize":[83],"consonant":[85],"least":[87],"90\\%":[88],"correctly,":[89],"average,":[91,158],"as":[92],"determined":[93],"in":[94],"prior":[95],"experiments":[96],"NH":[98],"subjects.":[99],"Performance":[100],"CNN":[103],"compared":[105],"baseline":[108,161],"prediction":[109],"automatic":[112],"recognition":[114],"(ASR),":[115],"specifically,":[116],"constant":[118],"offset":[119],"subtracted":[120],"from":[121],"ASR":[127],"capable":[129],"correctly":[131],"labeling":[132],"consonant.":[134,176],"Compared":[135],"baseline,":[137],"our":[138],"were":[140],"accurately":[143],"SNR$_{90}$~intelligibility":[146],"less":[149],"than":[150],"2":[151],"[dB$^2$]":[152],"Mean":[153],"Squared":[154],"Error":[155],"(MSE)":[156],"while":[159],"ASR-defined":[162],"computes":[164],"SNR$_{90}$~with":[165],"variance":[167],"5.2":[169],"26.6":[171],"[dB$^2$],":[172],"depending":[173]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
