{"id":"https://openalex.org/W2052697931","doi":"https://doi.org/10.1109/slt.2014.7078558","title":"Phonetics embedding learning with side information","display_name":"Phonetics embedding learning with side information","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2052697931","doi":"https://doi.org/10.1109/slt.2014.7078558","mag":"2052697931"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/dataset/Phonetics_Embedding_Learning_with_Side_Information/1277821","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041907084","display_name":"Gabriel Synnaeve","orcid":"https://orcid.org/0000-0003-1715-3356"},"institutions":[{"id":"https://openalex.org/I90669466","display_name":"\u00c9cole des hautes \u00e9tudes en sciences sociales","ror":"https://ror.org/02d9dg697","country_code":"FR","type":"facility","lineage":["https://openalex.org/I90669466"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Gabriel Synnaeve","raw_affiliation_strings":["LSCP, IEC ENS/EHESS/CNRS, Paris, France"],"affiliations":[{"raw_affiliation_string":"LSCP, IEC ENS/EHESS/CNRS, Paris, France","institution_ids":["https://openalex.org/I90669466","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110391017","display_name":"Thomas Schatz","orcid":null},"institutions":[{"id":"https://openalex.org/I90669466","display_name":"\u00c9cole des hautes \u00e9tudes en sciences sociales","ror":"https://ror.org/02d9dg697","country_code":"FR","type":"facility","lineage":["https://openalex.org/I90669466"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Schatz","raw_affiliation_strings":["LSCP, IEC ENS/EHESS/CNRS, Paris, France"],"affiliations":[{"raw_affiliation_string":"LSCP, IEC ENS/EHESS/CNRS, Paris, France","institution_ids":["https://openalex.org/I90669466","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007620149","display_name":"Emmanuel Dupoux","orcid":"https://orcid.org/0000-0002-7814-2952"},"institutions":[{"id":"https://openalex.org/I90669466","display_name":"\u00c9cole des hautes \u00e9tudes en sciences sociales","ror":"https://ror.org/02d9dg697","country_code":"FR","type":"facility","lineage":["https://openalex.org/I90669466"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Dupoux","raw_affiliation_strings":["LSCP, IEC ENS/EHESS/CNRS, Paris, France"],"affiliations":[{"raw_affiliation_string":"LSCP, IEC ENS/EHESS/CNRS, Paris, France","institution_ids":["https://openalex.org/I90669466","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041907084"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I90669466"],"apc_list":null,"apc_paid":null,"fwci":12.6604,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.98697797,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"3","issue":null,"first_page":"106","last_page":"111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9990000128746033,"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":0.7992895245552063},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7243553400039673},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6905574202537537},{"id":"https://openalex.org/keywords/abx-test","display_name":"ABX test","score":0.5903816819190979},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5414424538612366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5339867472648621},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5290571451187134},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4755494296550751},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4647255539894104},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44901108741760254},{"id":"https://openalex.org/keywords/phonetics","display_name":"Phonetics","score":0.4329114258289337},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3927238881587982},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3214040696620941},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3108524978160858},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10379534959793091}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992895245552063},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7243553400039673},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6905574202537537},{"id":"https://openalex.org/C60962613","wikidata":"https://www.wikidata.org/wiki/Q287654","display_name":"ABX test","level":2,"score":0.5903816819190979},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5414424538612366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5339867472648621},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5290571451187134},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4755494296550751},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4647255539894104},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44901108741760254},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.4329114258289337},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3927238881587982},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3214040696620941},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3108524978160858},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10379534959793091},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt.2014.7078558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/1277821","is_oa":true,"landing_page_url":"https://figshare.com/articles/dataset/Phonetics_Embedding_Learning_with_Side_Information/1277821","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},{"id":"doi:10.6084/m9.figshare.1277821.v1","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.1277821.v1","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/1277821","is_oa":true,"landing_page_url":"https://figshare.com/articles/dataset/Phonetics_Embedding_Learning_with_Side_Information/1277821","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"},{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W30845872","https://openalex.org/W52412328","https://openalex.org/W1576278180","https://openalex.org/W1993755070","https://openalex.org/W1997460147","https://openalex.org/W2025482506","https://openalex.org/W2029582325","https://openalex.org/W2035424729","https://openalex.org/W2038056950","https://openalex.org/W2054948443","https://openalex.org/W2078993594","https://openalex.org/W2114347655","https://openalex.org/W2117154949","https://openalex.org/W2127589108","https://openalex.org/W2136549906","https://openalex.org/W2138621090","https://openalex.org/W2142152793","https://openalex.org/W2143612262","https://openalex.org/W2153767712","https://openalex.org/W2162505970","https://openalex.org/W2171590421","https://openalex.org/W2252172689","https://openalex.org/W2395899413","https://openalex.org/W2407712691","https://openalex.org/W4285719527","https://openalex.org/W6602180557","https://openalex.org/W6657703491","https://openalex.org/W6670693114","https://openalex.org/W6677328822"],"related_works":["https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W151018310","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W4385611764","https://openalex.org/W2519224033"],"abstract_inverted_index":{"We":[0],"show":[1],"that":[2],"it":[3],"is":[4,71,98,107],"possible":[5],"to":[6,25,50,63,88,109],"learn":[7],"an":[8,81,101],"efficient":[9],"acoustic":[10,69],"model":[11,70,97],"using":[12,80],"only":[13,37],"a":[14,84,125],"small":[15],"amount":[16],"of":[17,44,57,91],"easily":[18],"available":[19],"word-level":[20],"similarity":[21],"annotations.":[22],"In":[23],"contrast":[24],"the":[26,36,89,92],"detailed":[27],"phonetic":[28],"labeling":[29],"required":[30],"by":[31,73],"classical":[32],"speech":[33,45,58,119],"recognition":[34],"technologies,":[35],"information":[38],"our":[39],"method":[40],"requires":[41],"are":[42,48,61],"pairs":[43,56],"excerpts":[46,59],"which":[47,60],"known":[49,62],"be":[51,64],"similar":[52],"(same":[53],"word)":[54],"and":[55,76,83,106],"different":[65],"(different":[66],"words).":[67],"An":[68],"obtained":[72],"training":[74],"shallow":[75],"deep":[77],"neural":[78,130],"networks,":[79],"architecture":[82],"cost":[85],"function":[86],"well-adapted":[87],"nature":[90],"provided":[93],"information.":[94],"The":[95],"resulting":[96],"evaluated":[99],"in":[100],"ABX":[102,114],"minimal-pair":[103],"discrimination":[104],"task":[105],"shown":[108],"perform":[110],"much":[111],"better":[112],"(11.8%":[113],"error":[115],"rate)":[116],"than":[117],"raw":[118],"features":[120],"(19.6%),":[121],"not":[122],"far":[123],"from":[124],"fully":[126],"supervised":[127],"baseline":[128],"(best":[129],"network:":[131],"9.2%,":[132],"HMM-GMM:":[133],"11%).":[134]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}