{"id":"https://openalex.org/W2296543600","doi":"https://doi.org/10.21437/interspeech.2012-105","title":"Automatic intelligibility assessment of pathologic speech in head and neck cancer based on auditory-inspired spectro-temporal modulations","display_name":"Automatic intelligibility assessment of pathologic speech in head and neck cancer based on auditory-inspired spectro-temporal modulations","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2296543600","doi":"https://doi.org/10.21437/interspeech.2012-105","mag":"2296543600"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-105","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Xinhui Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinhui Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000143881","display_name":"Daniel Garcia-Romero","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Garcia-Romero","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033351155","display_name":"Nima Mesgarani","orcid":"https://orcid.org/0000-0002-2987-759X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nima Mesgarani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109307699","display_name":"Maureen Stone","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maureen Stone","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078241735","display_name":"Carol Espy-Wilson","orcid":"https://orcid.org/0000-0002-1012-183X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carol Espy-Wilson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057113698","display_name":"Shihab Shamma","orcid":"https://orcid.org/0000-0002-1283-6804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shihab Shamma","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":0.5203,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.64565477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"542","last_page":"545"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9986000061035156,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9939000010490417,"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":0.7394692897796631},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7012343406677246},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5499982237815857},{"id":"https://openalex.org/keywords/head-and-neck","display_name":"Head and neck","score":0.4356245994567871},{"id":"https://openalex.org/keywords/amplitude-modulation","display_name":"Amplitude modulation","score":0.4248647093772888},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.31834959983825684},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.1355779469013214},{"id":"https://openalex.org/keywords/radio-frequency","display_name":"Radio frequency","score":0.09013259410858154}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7394692897796631},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7012343406677246},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5499982237815857},{"id":"https://openalex.org/C3018411727","wikidata":"https://www.wikidata.org/wiki/Q3867488","display_name":"Head and neck","level":2,"score":0.4356245994567871},{"id":"https://openalex.org/C201905106","wikidata":"https://www.wikidata.org/wiki/Q183755","display_name":"Amplitude modulation","level":4,"score":0.4248647093772888},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.31834959983825684},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.1355779469013214},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.09013259410858154},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C141071460","wikidata":"https://www.wikidata.org/wiki/Q40821","display_name":"Surgery","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2012-105","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W28060258","https://openalex.org/W1501506202","https://openalex.org/W1987048275","https://openalex.org/W1994139191","https://openalex.org/W1999686891","https://openalex.org/W2002976016","https://openalex.org/W2005076458","https://openalex.org/W2018175860","https://openalex.org/W2030763496","https://openalex.org/W2058497667","https://openalex.org/W2082833614","https://openalex.org/W2088711720","https://openalex.org/W2121147910","https://openalex.org/W2130426352","https://openalex.org/W2142709321","https://openalex.org/W2153635508","https://openalex.org/W2168595965","https://openalex.org/W2398847633"],"related_works":["https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W2068642629","https://openalex.org/W4363647395","https://openalex.org/W2046525430","https://openalex.org/W2004723848","https://openalex.org/W2093894424","https://openalex.org/W2971711574","https://openalex.org/W1969950000","https://openalex.org/W2002161999"],"abstract_inverted_index":{"Oral,":[0],"head":[1],"and":[2,14,28,54,113,133,138,153,161],"neck":[3],"cancer":[4,20],"represents":[5],"3%":[6],"of":[7,41,68,81,91,99,141],"all":[8],"cancers":[9],"in":[10,107],"the":[11,16,24,69,79,108,118,148,154,159,162,168],"United":[12],"States":[13],"is":[15],"6th":[17],"most":[18],"common":[19],"worldwide.":[21],"Depending":[22],"on":[23,61,136,147,157],"tumor":[25],"size,":[26],"location":[27],"staging,":[29],"patients":[30],"are":[31,52,165],"treated":[32],"by":[33],"radical":[34],"surgery,":[35],"radiology,":[36],"chemotherapy":[37],"or":[38,105],"a":[39,45,66,130],"combination":[40],"those":[42,92],"treatments.":[43],"As":[44,65],"result,":[46],"their":[47,62],"anatomical":[48],"structures":[49],"for":[50,86],"speech":[51,63,88,100,120],"impaired":[53],"this":[55,76],"leads":[56],"to":[57,122,167],"some":[58],"negative":[59],"impact":[60],"intelligibility.":[64],"part":[67],"INTERSPEECH":[70],"2012":[71],"speaker":[72,149],"trait":[73,150],"Pathology":[74],"sub-challenge,":[75],"study":[77],"explored":[78],"use":[80],"auditory-inspired":[82],"spectro-temporal":[83,97,142],"modulation":[84,125,143],"features":[85,144],"automatic":[87],"intelligibility":[89],"assessment":[90],"pathologic":[93],"speech.":[94],"The":[95],"averaged":[96],"modulations":[98],"considered":[101],"as":[102],"either":[103],"intelligible":[104],"non-intelligible":[106,119],"challenge":[109,151],"database":[110],"were":[111,145],"analyzed":[112],"it":[114],"was":[115],"found":[116],"that":[117],"tends":[121],"have":[123],"its":[124],"amplitude":[126],"peaks":[127],"shift":[128],"towards":[129],"smaller":[131],"rate":[132],"scale.":[134],"Based":[135],"SVM":[137],"GMM,":[139],"variants":[140],"tested":[146],"problem":[152],"resulting":[155],"performances":[156],"both":[158],"development":[160],"test":[163],"datasets":[164],"comparable":[166],"baseline":[169],"performance.":[170]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}