{"id":"https://openalex.org/W4297841471","doi":"https://doi.org/10.21437/interspeech.2022-749","title":"Formant Estimation and Tracking using Probabilistic Heat-Maps","display_name":"Formant Estimation and Tracking using Probabilistic Heat-Maps","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841471","doi":"https://doi.org/10.21437/interspeech.2022-749"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-749","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-749","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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 2022","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":"https://openalex.org/A5076089159","display_name":"Yosi Shrem","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yosi Shrem","raw_affiliation_strings":["Facullty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facullty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000406733","display_name":"Felix Kreuk","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Felix Kreuk","raw_affiliation_strings":["Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008847407","display_name":"Joseph Keshet","orcid":"https://orcid.org/0000-0003-2332-5783"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Joseph Keshet","raw_affiliation_strings":["Facullty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facullty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3563","last_page":"3567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9926999807357788,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9926999807357788,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9876999855041504,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6781206727027893},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.62830650806427},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5750938057899475},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.5568827390670776},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5366015434265137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4486616849899292},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3810713291168213},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.23016318678855896},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11499646306037903}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6781206727027893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.62830650806427},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5750938057899475},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.5568827390670776},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5366015434265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4486616849899292},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3810713291168213},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.23016318678855896},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11499646306037903},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-749","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-749","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.4699999988079071,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1936750108","https://openalex.org/W1994888226","https://openalex.org/W2046335163","https://openalex.org/W2057800825","https://openalex.org/W2106610722","https://openalex.org/W2161964681","https://openalex.org/W2165544306","https://openalex.org/W2509814936","https://openalex.org/W2807696699","https://openalex.org/W2912019251","https://openalex.org/W2948210185","https://openalex.org/W2963037989","https://openalex.org/W2964304707","https://openalex.org/W3015611303","https://openalex.org/W3073142260","https://openalex.org/W3095938191","https://openalex.org/W3209383001","https://openalex.org/W4233131682","https://openalex.org/W4285781481","https://openalex.org/W4290709727"],"related_works":["https://openalex.org/W2046217390","https://openalex.org/W4365503437","https://openalex.org/W2362995206","https://openalex.org/W2004825552","https://openalex.org/W1986672430","https://openalex.org/W1990629684","https://openalex.org/W1971436356","https://openalex.org/W1975851543","https://openalex.org/W2070163607","https://openalex.org/W2158788032"],"abstract_inverted_index":{"Formants":[0],"are":[1],"the":[2,11,21,130,160],"spectral":[3],"maxima":[4],"that":[5,31,52,84,104,139,145,154],"result":[6],"from":[7,47],"acoustic":[8],"resonances":[9],"of":[10,74,90,100,135],"human":[12],"vocal":[13],"tract,":[14],"and":[15,93,110,165,172],"their":[16,68],"accurate":[17],"estimation":[18],"is":[19,77,98,138,141],"among":[20],"most":[22],"fundamental":[23],"speech":[24,46,94],"processing":[25],"problems.Recent":[26],"work":[27],"has":[28],"been":[29,57],"shown":[30],"those":[32],"frequencies":[33],"can":[34],"accurately":[35],"be":[36],"estimated":[37],"using":[38],"deep":[39],"learning":[40],"techniques.However,":[41],"when":[42],"presented":[43],"with":[44],"a":[45,48,63,80,88,101,108,112,125,147],"different":[49,91,126],"domain":[50],"than":[51],"in":[53,65],"which":[54],"they":[55],"have":[56],"trained":[58],"on,":[59],"these":[60],"methods":[61],"exhibit":[62],"decline":[64],"performance,":[66],"limiting":[67],"usage":[69],"as":[70,106],"generic":[71],"tools.The":[72],"contribution":[73],"this":[75,119],"paper":[76],"to":[78,167],"propose":[79],"new":[81],"network":[82],"architecture":[83],"performs":[85],"well":[86],"on":[87,143],"variety":[89],"speaker":[92],"domains.Our":[95],"proposed":[96,156],"model":[97,137,157],"composed":[99],"shared":[102],"encoder":[103],"gets":[105],"input":[107],"spectrogram":[109],"outputs":[111],"domain-invariant":[113],"representation.Then,":[114],"multiple":[115],"decoders":[116],"further":[117],"process":[118],"representation,":[120],"each":[121],"responsible":[122],"for":[123],"predicting":[124],"formant":[127,132,151,169],"while":[128],"considering":[129],"lower":[131],"predictions.An":[133],"advantage":[134],"our":[136,155],"it":[140],"based":[142],"heatmaps":[144],"generate":[146],"probability":[148],"distribution":[149],"over":[150,162],"predictions.Results":[152],"suggest":[153],"better":[158,168],"represents":[159],"signal":[161],"various":[163],"domains":[164],"leads":[166],"frequency":[170],"tracking":[171],"estimation.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}