{"id":"https://openalex.org/W2940347029","doi":"https://doi.org/10.1109/icassp.2019.8683513","title":"Segment-level Training of ANNs Based on Acoustic Confidence Measures for Hybrid HMM/ANN Speech Recognition","display_name":"Segment-level Training of ANNs Based on Acoustic Confidence Measures for Hybrid HMM/ANN Speech Recognition","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2940347029","doi":"https://doi.org/10.1109/icassp.2019.8683513","mag":"2940347029"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/264112","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":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"S. Pavankumar Dubagunta","raw_affiliation_strings":["\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai.-Doss","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4373,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65088293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"3","issue":null,"first_page":"6435","last_page":"6439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9962000250816345,"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/T10860","display_name":"Speech and Audio Processing","score":0.995199978351593,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7999292016029358},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7812029123306274},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7672970294952393},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7108194231987},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5122553706169128},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5024826526641846},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.48381131887435913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44579246640205383},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4421243667602539},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4377990961074829},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43446505069732666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06979647278785706}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7999292016029358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7812029123306274},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7672970294952393},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7108194231987},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5122553706169128},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5024826526641846},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.48381131887435913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44579246640205383},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4421243667602539},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4377990961074829},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43446505069732666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06979647278785706},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8683513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:264112","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/264112","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/264112","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:264112","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/264112","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/264112","raw_type":"Text"},"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W1506693879","https://openalex.org/W1513116003","https://openalex.org/W1526516369","https://openalex.org/W1553004968","https://openalex.org/W1553381619","https://openalex.org/W1635512741","https://openalex.org/W1802155944","https://openalex.org/W1974556460","https://openalex.org/W2013932300","https://openalex.org/W2034597819","https://openalex.org/W2045211645","https://openalex.org/W2083393647","https://openalex.org/W2115685217","https://openalex.org/W2125336414","https://openalex.org/W2131033001","https://openalex.org/W2131342762","https://openalex.org/W2137222873","https://openalex.org/W2140766383","https://openalex.org/W2147768505","https://openalex.org/W2152617511","https://openalex.org/W2160815625","https://openalex.org/W2176713451","https://openalex.org/W2287914047","https://openalex.org/W2395342389","https://openalex.org/W2514741789","https://openalex.org/W2889187401","https://openalex.org/W2962875366","https://openalex.org/W2963175699","https://openalex.org/W4247489549","https://openalex.org/W6632879737","https://openalex.org/W6638423073","https://openalex.org/W6678409544","https://openalex.org/W6678809451","https://openalex.org/W6680789778","https://openalex.org/W6696116229"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2053269318","https://openalex.org/W2110523656","https://openalex.org/W2153098279"],"abstract_inverted_index":{"We":[0,45],"show":[1,69],"that":[2,32,48,70],"confidence":[3],"measures":[4,47],"estimated":[5],"from":[6],"local":[7],"posterior":[8],"probabilities":[9],"can":[10],"serve":[11],"as":[12],"objective":[13],"functions":[14],"for":[15],"training":[16,30],"ANNs":[17],"in":[18,43,60,78],"hybrid":[19],"HMM":[20],"based":[21],"speech":[22],"recognition":[23],"systems.":[24],"This":[25],"leads":[26],"to":[27],"a":[28],"segment-level":[29],"paradigm":[31],"overcomes":[33],"the":[34,40,51,61,102,109],"limitation":[35],"of":[36,80,104],"frame-level":[37],"updates":[38],"ignoring":[39],"sequence":[41,88],"structure":[42],"speech.":[44],"propose":[46],"train":[49],"at":[50],"state":[52],"and":[53,96,99],"phone":[54],"segment":[55,105],"levels,":[56],"while":[57],"still":[58],"decoding":[59],"conventional":[62],"framework.":[63],"Experimental":[64],"results":[65],"on":[66,108],"multiple":[67],"corpora":[68],"such":[71],"trainings":[72],"not":[73],"only":[74],"yield":[75],"better":[76],"systems":[77],"terms":[79],"performance,":[81],"but":[82],"also":[83],"give":[84],"additional":[85],"improvements":[86],"with":[87],"discriminative":[89],"training.":[90,111],"These":[91],"techniques":[92],"generalise":[93],"across":[94],"front-ends":[95],"model":[97],"architectures,":[98],"efficiently":[100],"handle":[101],"effect":[103],"duration":[106],"variations":[107],"ANN":[110]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}