{"id":"https://openalex.org/W2190506272","doi":"https://doi.org/10.1109/icassp.2016.7472619","title":"Deep convolutional acoustic word embeddings using word-pair side information","display_name":"Deep convolutional acoustic word embeddings using word-pair side information","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2190506272","doi":"https://doi.org/10.1109/icassp.2016.7472619","mag":"2190506272"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["CSTR and ILCC, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"CSTR and ILCC, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432591","display_name":"Weiran Wang","orcid":"https://orcid.org/0009-0000-0843-707X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiran Wang","raw_affiliation_strings":["Toyota Technological Institute at Chicago, USA"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, USA","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Toyota Technological Institute at Chicago, USA"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, USA","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040305929"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":38.5629,"has_fulltext":false,"cited_by_count":160,"citation_normalized_percentile":{"value":0.99746022,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4950","last_page":"4954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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":0.816842794418335},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7849785089492798},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7080895900726318},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5881173014640808},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5820677280426025},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5149419903755188},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4905790388584137},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4237402379512787},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.41489097476005554},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36237800121307373},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13100942969322205},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07320591807365417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816842794418335},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7849785089492798},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7080895900726318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5881173014640808},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5820677280426025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5149419903755188},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4905790388584137},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4237402379512787},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.41489097476005554},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36237800121307373},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13100942969322205},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07320591807365417},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1496120315","https://openalex.org/W1545920196","https://openalex.org/W1577418252","https://openalex.org/W1614298861","https://openalex.org/W1796128977","https://openalex.org/W1814992895","https://openalex.org/W1942713348","https://openalex.org/W1967924372","https://openalex.org/W2020607164","https://openalex.org/W2052697931","https://openalex.org/W2057007397","https://openalex.org/W2059652594","https://openalex.org/W2072054026","https://openalex.org/W2097207027","https://openalex.org/W2114347655","https://openalex.org/W2117459613","https://openalex.org/W2126203737","https://openalex.org/W2136189984","https://openalex.org/W2138621090","https://openalex.org/W2152175008","https://openalex.org/W2154093685","https://openalex.org/W2159775472","https://openalex.org/W2171590421","https://openalex.org/W2296681920","https://openalex.org/W2404799143","https://openalex.org/W2405533440","https://openalex.org/W2407151108","https://openalex.org/W6600284362","https://openalex.org/W6632653590","https://openalex.org/W6636510571","https://openalex.org/W6638159135","https://openalex.org/W6638493111","https://openalex.org/W6640777149","https://openalex.org/W6680450716","https://openalex.org/W6682450205","https://openalex.org/W6697456849","https://openalex.org/W6713256719","https://openalex.org/W6713710831"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W2340870721","https://openalex.org/W2358318464","https://openalex.org/W4293226380","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"been":[3],"revisiting":[4],"whole":[5],"words":[6],"as":[7,106],"the":[8,43,60,82,146,152],"basic":[9],"modelling":[10],"unit":[11],"in":[12,39,59,70,81],"speech":[13,34,104],"recognition":[14],"and":[15,67,108,121],"query":[16],"applications,":[17],"instead":[18],"of":[19,84,98,140],"phonetic":[20],"units.":[21],"Such":[22],"whole-word":[23],"segmental":[24],"systems":[25],"rely":[26],"on":[27,151],"a":[28,32,37,40,71,90,96,114],"function":[29],"that":[30,101,117],"maps":[31],"variable-length":[33],"segment":[35],"to":[36,49,88],"vector":[38],"fixed-dimensional":[41],"space;":[42],"resulting":[44],"acoustic":[45],"word":[46,56,72,86,128,153],"embeddings":[47],"need":[48],"allow":[50],"for":[51],"accurate":[52],"discrimination":[53,73,154],"between":[54],"different":[55],"types,":[57],"directly":[58],"embedding":[61],"space.":[62],"We":[63],"compare":[64],"several":[65],"old":[66],"new":[68],"approaches":[69],"task.":[74,155],"Our":[75],"best":[76,147],"approach":[77],"uses":[78],"side":[79],"information":[80],"form":[83],"known":[85],"pairs":[87,120,123],"train":[89],"Siamese":[91],"convolutional":[92],"neural":[93],"network":[94],"(CNN):":[95],"pair":[97],"tied":[99],"networks":[100],"take":[102],"two":[103],"segments":[105],"input":[107],"produce":[109],"their":[110],"embeddings,":[111],"trained":[112],"with":[113],"hinge":[115],"loss":[116],"separates":[118],"same-word":[119],"different-word":[122],"by":[124],"some":[125],"margin.":[126],"A":[127],"classifier":[129],"CNN":[130],"performs":[131],"similarly,":[132],"but":[133],"requires":[134],"much":[135],"stronger":[136],"supervision.":[137],"Both":[138],"types":[139],"CNNs":[141],"yield":[142],"large":[143],"improvements":[144],"over":[145],"previously":[148],"published":[149],"results":[150]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":29},{"year":2018,"cited_by_count":25},{"year":2017,"cited_by_count":23},{"year":2016,"cited_by_count":13}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}