{"id":"https://openalex.org/W2758697525","doi":"https://doi.org/10.18653/v1/d17-1112","title":"Speech segmentation with a neural encoder model of working memory","display_name":"Speech segmentation with a neural encoder model of working memory","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2758697525","doi":"https://doi.org/10.18653/v1/d17-1112","mag":"2758697525"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1112","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1112","pdf_url":"https://www.aclweb.org/anthology/D17-1112.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1112.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017409643","display_name":"Micha Elsner","orcid":"https://orcid.org/0000-0002-1432-2129"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Micha Elsner","raw_affiliation_strings":["Department of Linguistics The Ohio State University, Columbus, OH 43210"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics The Ohio State University, Columbus, OH 43210","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033058937","display_name":"Cory Shain","orcid":"https://orcid.org/0000-0002-2704-7197"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cory Shain","raw_affiliation_strings":["Department of Linguistics The Ohio State University, Columbus, OH 43210"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics The Ohio State University, Columbus, OH 43210","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4458,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87053716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1070","last_page":"1080"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.8253467082977295},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6916403770446777},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6550755500793457},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.651585042476654},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.5635449886322021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5102062225341797},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.4530874490737915},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4515688121318817},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4161277711391449},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4063074588775635},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40082287788391113},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3306090235710144},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09078842401504517},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07856887578964233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253467082977295},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6916403770446777},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6550755500793457},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.651585042476654},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.5635449886322021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5102062225341797},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4530874490737915},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4515688121318817},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4161277711391449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4063074588775635},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40082287788391113},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3306090235710144},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09078842401504517},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07856887578964233},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d17-1112","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1112","pdf_url":"https://www.aclweb.org/anthology/D17-1112.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1112","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1112","pdf_url":"https://www.aclweb.org/anthology/D17-1112.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5911140373","display_name":"RI: Small: Collaborative Research: Cognitive models of the acquisition of vowels in context","funder_award_id":"1422987","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2758697525.pdf","grobid_xml":"https://content.openalex.org/works/W2758697525.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W32086369","https://openalex.org/W52412328","https://openalex.org/W71795751","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1545920196","https://openalex.org/W1570013475","https://openalex.org/W1722621474","https://openalex.org/W1778492285","https://openalex.org/W1895577753","https://openalex.org/W1908676432","https://openalex.org/W1989042531","https://openalex.org/W2036572838","https://openalex.org/W2038056950","https://openalex.org/W2063303346","https://openalex.org/W2064675550","https://openalex.org/W2074546930","https://openalex.org/W2084734691","https://openalex.org/W2095705004","https://openalex.org/W2100768664","https://openalex.org/W2107038463","https://openalex.org/W2110485445","https://openalex.org/W2111732304","https://openalex.org/W2117786207","https://openalex.org/W2118004980","https://openalex.org/W2126377586","https://openalex.org/W2136549906","https://openalex.org/W2140826469","https://openalex.org/W2140991203","https://openalex.org/W2141994663","https://openalex.org/W2143612262","https://openalex.org/W2147527908","https://openalex.org/W2152824855","https://openalex.org/W2153767712","https://openalex.org/W2157331557","https://openalex.org/W2157427027","https://openalex.org/W2166270474","https://openalex.org/W2166391802","https://openalex.org/W2169895393","https://openalex.org/W2184045248","https://openalex.org/W2226889031","https://openalex.org/W2268270458","https://openalex.org/W2398490608","https://openalex.org/W2407614114","https://openalex.org/W2468716020","https://openalex.org/W2477383735","https://openalex.org/W2786608204","https://openalex.org/W2950178297","https://openalex.org/W2951527505","https://openalex.org/W2952343510","https://openalex.org/W2963735467","https://openalex.org/W2964121744","https://openalex.org/W3136512150","https://openalex.org/W4212993294","https://openalex.org/W4242487065","https://openalex.org/W4254816979"],"related_works":["https://openalex.org/W1558302546","https://openalex.org/W4214818988","https://openalex.org/W3037354152","https://openalex.org/W2168417340","https://openalex.org/W2402157757","https://openalex.org/W2738297198","https://openalex.org/W2992378684","https://openalex.org/W1886519670","https://openalex.org/W2964829415","https://openalex.org/W642007152"],"abstract_inverted_index":{"We":[0],"present":[1],"the":[2,13,32,39,111],"first":[3,112],"unsupervised":[4,114],"LSTM":[5],"speech":[6,28],"segmenter":[7],"as":[8],"a":[9,53,62],"cognitive":[10],"model":[11,38],"of":[12,15,34,56,77,126],"acquisition":[14],"words":[16],"from":[17],"unsegmented":[18],"input.":[19],"Cognitive":[20],"biases":[21,40],"toward":[22],"phonological":[23],"and":[24,88,123],"syntactic":[25],"predictability":[26],"in":[27,31,83],"are":[29],"rooted":[30],"limitations":[33],"human":[35],"memory":[36,44],"To":[37,106],"introduced":[41],"by":[42],"these":[43,95],"limitations,":[45],"our":[46,92,107],"system":[47,115],"uses":[48],"an":[49],"LSTMbased":[50],"encoder-decoder":[51],"with":[52],"small":[54],"number":[55],"hidden":[57],"units,":[58],"then":[59],"searches":[60],"for":[61],"segmentation":[63],"that":[64,79,91],"minimizes":[65],"autoencoding":[66],"loss.":[67],"Linguistically":[68],"meaningful":[69],"segments":[70],"(e.g.":[71],"words)":[72],"should":[73],"share":[74],"regular":[75],"patterns":[76,96],"features":[78],"facilitate":[80],"decoder":[81],"performance":[82],"comparison":[84],"to":[85,116,119],"random":[86],"segmentations,":[87],"we":[89],"show":[90],"learner":[93],"discovers":[94],"when":[97],"trained":[98],"on":[99],"either":[100],"phoneme":[101],"sequences":[102],"or":[103],"raw":[104],"acoustics.":[105],"knowledge,":[108],"ours":[109],"is":[110],"fully":[113],"be":[117],"able":[118],"segment":[120],"both":[121],"symbolic":[122],"acoustic":[124],"representations":[125],"speech.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}