{"id":"https://openalex.org/W2077828209","doi":"https://doi.org/10.1109/mlsp.2015.7324331","title":"Vowel duration measurement using deep neural networks","display_name":"Vowel duration measurement using deep neural networks","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2077828209","doi":"https://doi.org/10.1109/mlsp.2015.7324331","mag":"2077828209","pmid":"https://pubmed.ncbi.nlm.nih.gov/29034132"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2015.7324331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"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":true,"raw_author_name":"Yossi Adi","raw_affiliation_strings":["Dept. of Computer Science, Bar-Ilan University, Ramat-Gan, Israel","Department of Computer Science, Bar Ilan University, Ramat Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Department of Computer Science, Bar Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008847407","display_name":"Joseph Keshet","orcid":"https://orcid.org/0000-0003-2332-5783"},"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":"Joseph Keshet","raw_affiliation_strings":["Dept. of Computer Science, Bar-Ilan University, Ramat-Gan, Israel","Department of Computer Science, Bar Ilan University, Ramat Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]},{"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/A5026401498","display_name":"Matthew Goldrick","orcid":"https://orcid.org/0000-0002-2035-416X"},"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":"Matthew Goldrick","raw_affiliation_strings":["Dept. of Linguistics, Northwestern University, Evanston, IL, USA","Department of Linguistics, Northwestern University, Evanston, IL, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Linguistics, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Department of Linguistics, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005191803"],"corresponding_institution_ids":["https://openalex.org/I13955877"],"apc_list":null,"apc_paid":null,"fwci":1.8371,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85612017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2015","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.8117802143096924},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.7349295616149902},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7191219329833984},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6495935916900635},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.6431578993797302},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6374514102935791},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5429894328117371},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49471351504325867},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48424312472343445},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4805312752723694},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.43448567390441895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3294903039932251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8117802143096924},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.7349295616149902},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7191219329833984},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6495935916900635},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.6431578993797302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6374514102935791},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5429894328117371},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49471351504325867},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48424312472343445},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4805312752723694},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43448567390441895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3294903039932251},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/mlsp.2015.7324331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmid:29034132","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29034132","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing","raw_type":null},{"id":"pmh:oai:europepmc.org:4556074","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5636193","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W61096326","https://openalex.org/W1122155490","https://openalex.org/W1592805114","https://openalex.org/W1667072054","https://openalex.org/W1813659000","https://openalex.org/W1875231349","https://openalex.org/W2029996593","https://openalex.org/W2049419997","https://openalex.org/W2067481950","https://openalex.org/W2071175130","https://openalex.org/W2076596602","https://openalex.org/W2125001590","https://openalex.org/W2136922672","https://openalex.org/W2139582890","https://openalex.org/W2141845152","https://openalex.org/W2160815625","https://openalex.org/W2187281534","https://openalex.org/W2406467606","https://openalex.org/W4243041937","https://openalex.org/W6637187546","https://openalex.org/W6649664491"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2348837382","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W1995619422","https://openalex.org/W4390926392","https://openalex.org/W2940658159","https://openalex.org/W2741358513"],"abstract_inverted_index":{"Vowel":[0],"durations":[1],"are":[2,121],"most":[3],"often":[4],"utilized":[5],"in":[6,11,123],"studies":[7],"addressing":[8],"specific":[9],"issues":[10],"phonetics.":[12],"Thus":[13],"far":[14],"this":[15],"has":[16],"been":[17],"hampered":[18],"by":[19,57],"a":[20,48,65,79],"reliance":[21],"on":[22,64,74],"subjective,":[23],"labor-intensive":[24],"manual":[25],"annotation.":[26],"Our":[27,60],"goal":[28],"is":[29,47,62,110],"to":[30,44,101,137],"build":[31],"an":[32,102],"algorithm":[33,46,61],"for":[34],"automatic":[35],"accurate":[36],"measurement":[37],"of":[38,128],"vowel":[39,53],"duration,":[40],"where":[41],"the":[42,45,71,131],"input":[43],"speech":[49],"segment":[50],"contains":[51],"one":[52],"preceded":[54],"and":[55,92,97,114,117],"followed":[56],"consonants":[58],"(CVC).":[59],"based":[63],"deep":[66,93],"neural":[67,89],"network":[68,90,95],"trained":[69],"at":[70],"frame":[72],"level":[73],"manually":[75,138],"annotated":[76,139],"data":[77],"from":[78],"phonetic":[80],"study.":[81],"Specifically,":[82],"we":[83],"try":[84],"two":[85],"deep-network":[86],"architectures:":[87],"convolutional":[88],"(CNN),":[91],"belief":[94],"(DBN),":[96],"compare":[98],"their":[99,124],"accuracy":[100],"HMM-based":[103,118],"forced":[104,119],"aligner.":[105],"Results":[106],"suggest":[107],"that":[108],"CNN":[109,116],"better":[111],"than":[112],"DBN,":[113],"both":[115],"aligner":[120],"comparable":[122],"results,":[125],"but":[126],"neither":[127],"them":[129],"yielded":[130],"same":[132],"predictions":[133],"as":[134],"models":[135],"fit":[136],"data.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}