{"id":"https://openalex.org/W2059652594","doi":"https://doi.org/10.1109/asru.2013.6707765","title":"Fixed-dimensional acoustic embeddings of variable-length segments in low-resource settings","display_name":"Fixed-dimensional acoustic embeddings of variable-length segments in low-resource settings","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2059652594","doi":"https://doi.org/10.1109/asru.2013.6707765","mag":"2059652594"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","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/A5112870105","display_name":"Keith Levin","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Keith Levin","raw_affiliation_strings":["Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015752834","display_name":"Katharine E. Henry","orcid":"https://orcid.org/0000-0002-0446-9717"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katharine Henry","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103622427","display_name":"Aren Jansen","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aren Jansen","raw_affiliation_strings":["Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"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, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112870105"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":5.7881,"has_fulltext":false,"cited_by_count":129,"citation_normalized_percentile":{"value":0.96535025,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"410","last_page":"415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9969000220298767,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"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/dynamic-time-warping","display_name":"Dynamic time warping","score":0.916043758392334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7569959759712219},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6264212727546692},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6239639520645142},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.5939986705780029},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5380243062973022},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48549583554267883},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.483975887298584},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4615803360939026},{"id":"https://openalex.org/keywords/distance-measures","display_name":"Distance measures","score":0.4576420485973358},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.43229275941848755},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4217885732650757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41880321502685547},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24266543984413147},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17667490243911743},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08818870782852173}],"concepts":[{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.916043758392334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569959759712219},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6264212727546692},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6239639520645142},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.5939986705780029},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5380243062973022},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48549583554267883},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.483975887298584},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4615803360939026},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.4576420485973358},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.43229275941848755},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4217885732650757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41880321502685547},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24266543984413147},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17667490243911743},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08818870782852173},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2013.6707765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.702.3437","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.702.3437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ttic.uchicago.edu/%7Eklivescu/papers/levin_etal_asru2013.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W137541753","https://openalex.org/W1576613474","https://openalex.org/W1579848672","https://openalex.org/W1583581687","https://openalex.org/W1974540032","https://openalex.org/W1978741356","https://openalex.org/W1984857732","https://openalex.org/W2023952145","https://openalex.org/W2025482506","https://openalex.org/W2053186076","https://openalex.org/W2057007397","https://openalex.org/W2097207027","https://openalex.org/W2097308346","https://openalex.org/W2097527229","https://openalex.org/W2104290444","https://openalex.org/W2110889574","https://openalex.org/W2111732304","https://openalex.org/W2114347655","https://openalex.org/W2117459613","https://openalex.org/W2126203737","https://openalex.org/W2147717514","https://openalex.org/W2151660570","https://openalex.org/W2157444450","https://openalex.org/W2158139921","https://openalex.org/W2164365067","https://openalex.org/W2170580867","https://openalex.org/W2395342389","https://openalex.org/W2397535009","https://openalex.org/W2407151108","https://openalex.org/W2407964052","https://openalex.org/W2569190383","https://openalex.org/W2799046698","https://openalex.org/W2997701990","https://openalex.org/W3148981562","https://openalex.org/W6634500723","https://openalex.org/W6675747103","https://openalex.org/W6683161245","https://openalex.org/W6683338658","https://openalex.org/W6714100551"],"related_works":["https://openalex.org/W2133184712","https://openalex.org/W3118503757","https://openalex.org/W3111157199","https://openalex.org/W2174518382","https://openalex.org/W2760717005","https://openalex.org/W2163118894","https://openalex.org/W58346954","https://openalex.org/W4281630436","https://openalex.org/W2014214435","https://openalex.org/W4391124606"],"abstract_inverted_index":{"Measures":[0],"of":[1,47,53,65,69,105],"acoustic":[2,14,112,132],"similarity":[3],"between":[4],"words":[5],"or":[6,82,143],"other":[7],"units":[8],"are":[9],"critical":[10],"for":[11,88],"segmental":[12,111],"exemplar-based":[13],"models,":[15],"spoken":[16],"term":[17],"discovery,":[18],"and":[19,58,102,121,127],"query-by-example":[20],"search.":[21],"Dynamic":[22],"time":[23],"warping":[24],"(DTW)":[25],"alignment":[26],"cost":[27],"has":[28,37],"been":[29],"the":[30,51,63,146],"most":[31],"commonly":[32],"used":[33],"measure,":[34],"but":[35],"it":[36],"well-known":[38],"inadequacies.":[39],"Some":[40],"recently":[41],"proposed":[42],"alternatives":[43],"require":[44],"large":[45],"amounts":[46],"training":[48],"data.":[49],"In":[50,114],"interest":[52],"finding":[54],"more":[55],"efficient,":[56],"accurate,":[57],"low-resource":[59,150],"alternatives,":[60],"we":[61,117],"consider":[62],"problem":[64,126],"embedding":[66,139],"speech":[67],"segments":[68],"arbitrary":[70],"length":[71],"into":[72],"fixed-dimensional":[73],"spaces":[74],"in":[75,149],"which":[76],"simple":[77],"distances":[78],"(such":[79],"as":[80,85],"cosine":[81],"Euclidean)":[83],"serve":[84],"a":[86],"proxy":[87],"linguistically":[89],"meaningful":[90],"(phonetic,":[91],"lexical,":[92],"etc.)":[93],"dissimilarities.":[94],"Such":[95],"embeddings":[96],"would":[97],"enable":[98],"efficient":[99],"audio":[100],"indexing":[101],"permit":[103],"application":[104],"standard":[106],"distance":[107],"learning":[108],"techniques":[109],"to":[110,124],"modeling.":[113],"this":[115,125],"paper,":[116],"explore":[118],"several":[119,138],"supervised":[120],"unsupervised":[122],"approaches":[123],"evaluate":[128],"them":[129],"on":[130],"an":[131],"word":[133],"discrimination":[134],"task.":[135],"We":[136],"identify":[137],"algorithms":[140],"that":[141],"match":[142],"improve":[144],"upon":[145],"DTW":[147],"baseline":[148],"settings.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}