{"id":"https://openalex.org/W4297841648","doi":"https://doi.org/10.21437/interspeech.2022-10756","title":"DeepFry: Identifying Vocal Fry Using Deep Neural Networks","display_name":"DeepFry: Identifying Vocal Fry Using Deep Neural Networks","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841648","doi":"https://doi.org/10.21437/interspeech.2022-10756"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10756","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10756","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/A5075899909","display_name":"Bronya Roni Chernyak","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":"Bronya Roni Chernyak","raw_affiliation_strings":["Faculty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty 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/A5066408476","display_name":"Talia Ben Simon","orcid":null},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Talia Ben Simon","raw_affiliation_strings":["Zurich Open Repository and Archive University of Zurich University Library Strickhofstrasse 39 CH-8057 Zurich www.zora.uzh.ch"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zurich Open Repository and Archive University of Zurich University Library Strickhofstrasse 39 CH-8057 Zurich www.zora.uzh.ch","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006031844","display_name":"Yael Segal","orcid":"https://orcid.org/0000-0003-2513-0752"},"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":"Yael Segal","raw_affiliation_strings":["Faculty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty 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/A5051344225","display_name":"Jeremy Steffman","orcid":"https://orcid.org/0000-0003-3675-910X"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Steffman","raw_affiliation_strings":["Deptartment of Linguistics, Northwestern University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deptartment of Linguistics, Northwestern University, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041778529","display_name":"Eleanor Chodroff","orcid":"https://orcid.org/0000-0003-4549-5919"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eleanor Chodroff","raw_affiliation_strings":["Deptartment of Language and Linguistic Science, University of York, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deptartment of Language and Linguistic Science, University of York, UK","institution_ids":["https://openalex.org/I52099693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001457934","display_name":"Jennifer Cole","orcid":"https://orcid.org/0000-0002-0465-4920"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jennifer Cole","raw_affiliation_strings":["Zurich Open Repository and Archive University of Zurich University Library Strickhofstrasse 39 CH-8057 Zurich www.zora.uzh.ch"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zurich Open Repository and Archive University of Zurich University Library Strickhofstrasse 39 CH-8057 Zurich www.zora.uzh.ch","institution_ids":["https://openalex.org/I202697423"]}]},{"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":["Faculty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3578","last_page":"3582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9990000128746033,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7872216701507568},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7819146513938904},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.5946239233016968},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5460827350616455},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.545149028301239},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5343503355979919},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5333319306373596},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5255233645439148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5152812004089355},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43687355518341064},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3939438760280609}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872216701507568},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7819146513938904},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.5946239233016968},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5460827350616455},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.545149028301239},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5343503355979919},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5333319306373596},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5255233645439148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5152812004089355},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43687355518341064},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3939438760280609},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10756","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10756","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323706","display_name":"Ministry of Science and Technology, Israel","ror":"https://ror.org/02heb2n75"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W22870543","https://openalex.org/W144053593","https://openalex.org/W2096760972","https://openalex.org/W2097062205","https://openalex.org/W2107831318","https://openalex.org/W2113516703","https://openalex.org/W2122334831","https://openalex.org/W2136101712","https://openalex.org/W2223030742","https://openalex.org/W2396205624","https://openalex.org/W2576336341","https://openalex.org/W2742149109","https://openalex.org/W2747874407","https://openalex.org/W2749645739","https://openalex.org/W2896457183","https://openalex.org/W2901891354","https://openalex.org/W2909246629","https://openalex.org/W2972646747","https://openalex.org/W2981664394","https://openalex.org/W3036601975","https://openalex.org/W3090062985","https://openalex.org/W3160799772","https://openalex.org/W3169320628","https://openalex.org/W3194982571"],"related_works":["https://openalex.org/W2036753972","https://openalex.org/W1996861825","https://openalex.org/W2497205885","https://openalex.org/W2079621619","https://openalex.org/W2046280377","https://openalex.org/W4388535697","https://openalex.org/W2036128733","https://openalex.org/W1976086899","https://openalex.org/W4285526294","https://openalex.org/W2313188200"],"abstract_inverted_index":{"Vocal":[0],"fry":[1],"or":[2],"creaky":[3,48,73,114],"voice":[4,8,49,74],"refers":[5],"to":[6,34,44,71,112,125,182],"a":[7,67,85,96,99,107,167],"quality":[9],"characterized":[10],"by":[11,143],"irregular":[12,46],"glottal":[13],"opening":[14],"and":[15,22,42,54,84,94,117,132,161,178],"low":[16],"pitch.It":[17],"occurs":[18],"in":[19,25,75],"diverse":[20],"languages":[21,59],"is":[23,30,62,79,104,130,156,164],"prevalent":[24],"American":[26,137],"English,":[27],"where":[28,60,119],"it":[29],"used":[31,124],"not":[32],"only":[33],"mark":[35],"phrase":[36],"finality,":[37],"but":[38],"also":[39],"sociolinguistic":[40],"factors":[41],"affect.Due":[43],"its":[45],"periodicity,":[47],"challenges":[50],"automatic":[51],"speech":[52,135],"processing":[53],"recognition":[55],"systems,":[56],"particularly":[57],"for":[58,141,158],"creak":[61,127,142],"frequently":[63],"used.This":[64],"paper":[65],"proposes":[66],"deep":[68],"learning":[69],"model":[70,78,129],"detect":[72,113],"fluent":[76],"speech.The":[77],"composed":[80],"of":[81,136,149],"an":[82],"encoder":[83,89],"classifier":[86,103],"trained":[87,111,131,144],"together.The":[88],"takes":[90],"the":[91,120,147,159,162],"raw":[92],"waveform":[93],"learns":[95],"representation":[97],"using":[98,152],"convolutional":[100],"neural":[101],"network.The":[102],"implemented":[105],"as":[106],"multi-headed":[108],"fully-connected":[109],"network":[110],"voice,":[115],"voicing,":[116],"pitch,":[118],"last":[121],"two":[122,153],"are":[123],"refine":[126],"prediction.The":[128],"tested":[133],"on":[134,166,185],"English":[138],"speakers,":[139],"annotated":[140],"phoneticians.We":[145],"evaluated":[146],"performance":[148],"our":[150,172],"system":[151,174],"encoders:":[154],"one":[155],"tailored":[157],"task,":[160],"other":[163],"based":[165],"state-of-the-art":[168],"unsupervised":[169],"representation.Results":[170],"suggest":[171],"best-performing":[173],"has":[175],"improved":[176],"recall":[177],"F1":[179],"scores":[180],"compared":[181],"previous":[183],"methods":[184],"unseen":[186],"data.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}