{"id":"https://openalex.org/W2126203737","doi":"https://doi.org/10.1109/asru.2009.5372931","title":"Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams","display_name":"Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2126203737","doi":"https://doi.org/10.1109/asru.2009.5372931","mag":"2126203737"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5372931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5372931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/73507","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101638717","display_name":"Yaodong Zhang","orcid":"https://orcid.org/0000-0002-6919-4291"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Yaodong Zhang","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","MIT Computer Science and Artificial Intelligence Laboratory, 32 Vassar Street, Cambridge, Massachusetts 02139, USA"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, 32 Vassar Street, Cambridge, Massachusetts 02139, USA","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"James R. Glass","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","MIT Computer Science and Artificial Intelligence Laboratory, 32 Vassar Street, Cambridge, Massachusetts 02139, USA"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, 32 Vassar Street, Cambridge, Massachusetts 02139, USA","institution_ids":["https://openalex.org/I4210164862"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101638717"],"corresponding_institution_ids":["https://openalex.org/I4210164862"],"apc_list":null,"apc_paid":null,"fwci":9.2846,"has_fulltext":false,"cited_by_count":338,"citation_normalized_percentile":{"value":0.98587533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9990000128746033,"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":0.9954000115394592,"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/keyword-spotting","display_name":"Keyword spotting","score":0.9275517463684082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7860703468322754},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.7058271765708923},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6802101135253906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6251134276390076},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5872236490249634},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5520199537277222},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5508003830909729},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.47225871682167053},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.43684443831443787},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4261133372783661},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42273223400115967},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40376773476600647},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.39786508679389954}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9275517463684082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860703468322754},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.7058271765708923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6802101135253906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6251134276390076},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5872236490249634},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5520199537277222},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5508003830909729},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.47225871682167053},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.43684443831443787},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4261133372783661},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42273223400115967},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40376773476600647},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.39786508679389954},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru.2009.5372931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5372931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.154.5969","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.154.5969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sls.csail.mit.edu/sls/publications/2009/ASRU09_Zhang.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/73507","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/73507","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/73507","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/73507","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W201187342","https://openalex.org/W1578200545","https://openalex.org/W1975113979","https://openalex.org/W1999121090","https://openalex.org/W2086891622","https://openalex.org/W2099415988","https://openalex.org/W2101536075","https://openalex.org/W2103371184","https://openalex.org/W2103933358","https://openalex.org/W2107076535","https://openalex.org/W2111732304","https://openalex.org/W2114347655","https://openalex.org/W2115220208","https://openalex.org/W2116969213","https://openalex.org/W2122797512","https://openalex.org/W2128160875","https://openalex.org/W2142570735","https://openalex.org/W2153426278","https://openalex.org/W2155427043","https://openalex.org/W2169384404","https://openalex.org/W2171019095","https://openalex.org/W2405666970","https://openalex.org/W6649874456","https://openalex.org/W6684930139"],"related_works":["https://openalex.org/W2388033618","https://openalex.org/W1494604982","https://openalex.org/W2171506966","https://openalex.org/W159541246","https://openalex.org/W2370736382","https://openalex.org/W2019287799","https://openalex.org/W2112950634","https://openalex.org/W1967145194","https://openalex.org/W2005217041","https://openalex.org/W2395491470"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,44],"present":[4],"an":[5],"unsupervised":[6,112],"learning":[7,113],"framework":[8,114],"to":[9,27,50,87],"address":[10],"the":[11,52,70,75,80,89,95,106,116],"problem":[12],"of":[13,41,73,110],"detecting":[14],"spoken":[15,39],"keywords.":[16],"Without":[17],"any":[18],"transcription":[19],"information,":[20],"a":[21,32,42,84],"Gaussian":[22,33,53],"Mixture":[23],"Model":[24],"is":[25,65],"trained":[26],"label":[28],"speech":[29],"frames":[30],"with":[31],"posteriorgram.":[34],"Given":[35],"one":[36],"or":[37],"more":[38,100],"examples":[40],"keyword,":[43],"use":[45],"segmental":[46],"dynamic":[47],"time":[48],"warping":[49],"compare":[51],"posteriorgrams":[54],"between":[55],"keyword":[56,62,117],"samples":[57],"and":[58,94,108],"test":[59,76],"utterances.":[60,77],"The":[61,103],"detection":[63],"result":[64],"then":[66],"obtained":[67],"by":[68],"ranking":[69],"distortion":[71],"scores":[72],"all":[74],"We":[78],"examine":[79],"TIMIT":[81],"corpus":[82,98],"as":[83],"development":[85],"set":[86],"tune":[88],"parameters":[90],"in":[91],"our":[92,111],"system,":[93],"MIT":[96],"Lecture":[97],"for":[99],"substantial":[101],"evaluation.":[102],"results":[104],"demonstrate":[105],"viability":[107],"effectiveness":[109],"on":[115],"spotting":[118],"task.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":38},{"year":2018,"cited_by_count":46},{"year":2017,"cited_by_count":42},{"year":2016,"cited_by_count":32},{"year":2015,"cited_by_count":38},{"year":2014,"cited_by_count":22},{"year":2013,"cited_by_count":28},{"year":2012,"cited_by_count":14}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}