{"id":"https://openalex.org/W3198017524","doi":"https://doi.org/10.5075/epfl-thesis-8793","title":"Novel Methods for Incorporating Prior Knowledge for Automatic Speech Assessment","display_name":"Novel Methods for Incorporating Prior Knowledge for Automatic Speech Assessment","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3198017524","doi":"https://doi.org/10.5075/epfl-thesis-8793","mag":"3198017524"},"language":"en","primary_location":{"id":"pmh:oai:infoscience.epfl.ch:288398","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/181137","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/handle/20.500.14299/181137","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008235303","display_name":"S. Pavankumar Dubagunta","orcid":"https://orcid.org/0000-0002-4307-8604"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dubagunta, Subrahmanya Pavankumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5008235303"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9520000219345093,"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":0.9520000219345093,"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/computer-science","display_name":"Computer science","score":0.5810911655426025},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4879402816295624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4055972695350647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5810911655426025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4879402816295624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4055972695350647}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:infoscience.epfl.ch:288398","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/181137","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},{"id":"doi:10.5075/epfl-thesis-8793","is_oa":true,"landing_page_url":"https://doi.org/10.5075/epfl-thesis-8793","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dissertation"},{"id":"mag:3198017524","is_oa":false,"landing_page_url":"https://infoscience.epfl.ch/record/288398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:288398","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/181137","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1492258091","https://openalex.org/W2963045393","https://openalex.org/W2625027024","https://openalex.org/W2738035098","https://openalex.org/W2856923010","https://openalex.org/W2084481840","https://openalex.org/W2532540590","https://openalex.org/W1585045112","https://openalex.org/W3156774516","https://openalex.org/W2148579858","https://openalex.org/W1505251852","https://openalex.org/W2013135134","https://openalex.org/W1989181678","https://openalex.org/W1597109047","https://openalex.org/W1964143424","https://openalex.org/W127975155","https://openalex.org/W2153754015","https://openalex.org/W2993841421","https://openalex.org/W2110188288","https://openalex.org/W1966130427"],"abstract_inverted_index":{"Speech":[0],"signal":[1,259],"conveys":[2],"several":[3,176],"kinds":[4,43],"of":[5,15,21,44,52,59,85,88,135,225,230,253],"information":[6,45,268,273],"such":[7,49,67],"as":[8,50,68],"a":[9,28,114,195,258],"message,":[10,55],"speaker":[11,17,76,281],"identity,":[12,282],"emotional":[13],"state":[14,20],"the":[16,22,53,60,89,133,170,223,235,251,280,287,295],"and":[18,57,74,117,185,243,269,289,302],"social":[19],"speaker.":[23,61],"Automatic":[24],"speech":[25,64,70,79,107,126,143,158,164,177,186,241,245,261],"assessment":[26,80,108,127,178,247],"is":[27,81,94,97],"broad":[29],"area":[30],"that":[31,95,103,152,264],"refers":[32],"to":[33,37,160,162,205,216,278],"using":[34],"automatic":[35,69,75,78,240,303],"methods":[36,139,151,172],"predict":[38],"human":[39],"judgements":[40],"regarding":[41],"different":[42],"conveyed":[46],"in":[47,91,250],"speech,":[48],"intelligibility":[51,201,246],"spoken":[54],"dialect":[56,181],"fluency":[58,187],"Unlike":[62],"other":[63],"technology":[65],"areas,":[66],"recognition,":[71,77],"text-to-speech":[72],"synthesis":[73],"an":[82],"emerging":[83],"direction":[84],"research.":[86],"One":[87],"challenges":[90],"this":[92,111],"field":[93],"there":[96],"no":[98],"single":[99],"method":[100],"or":[101],"framework":[102],"scales":[104],"across":[105],"diverse":[106,124],"tasks.":[109],"Thus,":[110],"thesis":[112],"takes":[113],"broader":[115],"outlook":[116],"focuses":[118],"on":[119,132,175,193,275],"prior":[120,155,276],"knowledge":[121,156,221,277],"incorporation":[122],"for":[123,140],"data-driven":[125],"problems.":[128],"First,":[129],"we":[130,147,191,211,256],"focus":[131,192],"development":[134],"end-to-end":[136],"acoustic":[137],"modelling":[138],"non-verbal":[141],"cue-based":[142],"assessment.":[144],"More":[145],"precisely,":[146],"develop":[148,257],"neural":[149,226],"network-based":[150],"can":[153],"integrate":[154],"about":[157],"production":[159],"learn":[161],"assess":[163],"from":[165],"raw":[166],"waveform.":[167],"We":[168,233,293],"validate":[169,234,294],"developed":[171],"through":[173,228,239,299],"investigations":[174],"tasks,":[179],"viz.":[180],"identification,":[182],"depression":[183],"detection":[184],"rating":[188],"prediction.":[189],"Second,":[190],"advancing":[194],"recently":[196],"proposed":[197,237,296],"phone":[198,207],"posterior":[199,208],"feature-based":[200],"estimation":[202,229],"technique.":[203],"Specifically,":[204],"enhance":[206],"probability":[209],"estimation,":[210],"propose":[212],"two":[213,236],"novel":[214],"approaches":[215,238],"incorporate":[217],"linguistic":[218],"segment":[219],"level":[220],"during":[222],"training":[224],"networks":[227],"confidence":[231],"measures.":[232],"recognition":[242],"dysarthric":[244],"studies.":[248],"Finally,":[249],"context":[252],"privacy":[254],"preservation,":[255],"processing-based":[260],"pseudonymization":[262,297],"approach":[263,298],"alters":[265],"voice":[266],"source":[267],"vocal":[270],"tract":[271],"system":[272],"based":[274],"obfuscate":[279],"while":[283],"retaining":[284],"intelligibility,":[285],"i.e.":[286],"phones":[288],"words":[290],"remain":[291],"recognizable.":[292],"listening":[300],"experiments":[301],"evaluations.":[304]},"counts_by_year":[],"updated_date":"2026-08-14T07:06:38.338062","created_date":"2025-10-10T00:00:00"}
