{"id":"https://openalex.org/W2009388533","doi":"https://doi.org/10.1109/icassp.2013.6639335","title":"Zero resource spoken audio corpus analysis","display_name":"Zero resource spoken audio corpus analysis","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2009388533","doi":"https://doi.org/10.1109/icassp.2013.6639335","mag":"2009388533"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5004717608","display_name":"David Harwath","orcid":"https://orcid.org/0000-0003-0206-0253"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David F. Harwath","raw_affiliation_strings":["Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, US","MIT Lincoln Lab. Lexington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, US","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"raw_affiliation_string":"MIT Lincoln Lab. Lexington, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114018312","display_name":"Timothy J. Hazen","orcid":"https://orcid.org/0009-0006-1413-9590"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy J. Hazen","raw_affiliation_strings":["Lincoln Laboratory, Massachusetts Institute of Technology, Lexington, MA, USA","MIT Lincoln Lab. Lexington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lincoln Laboratory, Massachusetts Institute of Technology, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"raw_affiliation_string":"MIT Lincoln Lab. Lexington, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"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/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James R. Glass","raw_affiliation_strings":["CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA","MIT CSAIL,Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"MIT CSAIL,Cambridge,MA,USA","institution_ids":["https://openalex.org/I4405258931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8555","last_page":"8559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9944999814033508,"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":0.9927999973297119,"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":0.8005038499832153},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.8001224994659424},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6694602370262146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6393001079559326},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5783842206001282},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5636704564094543},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5627390742301941},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5470436811447144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49751952290534973},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.4440366327762604},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.4187164306640625},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36772608757019043},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.29706794023513794},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.22450578212738037},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1498194932937622},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08016040921211243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8005038499832153},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.8001224994659424},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6694602370262146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6393001079559326},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5783842206001282},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5636704564094543},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5627390742301941},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5470436811447144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49751952290534973},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.4440366327762604},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.4187164306640625},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36772608757019043},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.29706794023513794},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.22450578212738037},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1498194932937622},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08016040921211243},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.307.604","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.307.604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://groups.csail.mit.edu/sls/publications/2013/Harwath_ICASSP-2013.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307943","display_name":"Raytheon Company","ror":"https://ror.org/0354t7b78"},{"id":"https://openalex.org/F4320317847","display_name":"Raytheon Technologies","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W66167291","https://openalex.org/W97072897","https://openalex.org/W1612003148","https://openalex.org/W1880262756","https://openalex.org/W1969608442","https://openalex.org/W2055408826","https://openalex.org/W2056616734","https://openalex.org/W2057007397","https://openalex.org/W2062914951","https://openalex.org/W2079460648","https://openalex.org/W2096298528","https://openalex.org/W2099415988","https://openalex.org/W2100768664","https://openalex.org/W2112107221","https://openalex.org/W2114347655","https://openalex.org/W2117041980","https://openalex.org/W2125247927","https://openalex.org/W2126377586","https://openalex.org/W2154093685","https://openalex.org/W2164998314","https://openalex.org/W2296730072","https://openalex.org/W2399869768","https://openalex.org/W2401464865","https://openalex.org/W2407964052","https://openalex.org/W4237791300","https://openalex.org/W6602705600","https://openalex.org/W6636440780","https://openalex.org/W6675022971"],"related_works":["https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W4243125559","https://openalex.org/W1541790149","https://openalex.org/W4241778367","https://openalex.org/W2752054555","https://openalex.org/W2527828870","https://openalex.org/W2184127972","https://openalex.org/W4214489098","https://openalex.org/W46679383"],"abstract_inverted_index":{"Zero-resource":[0],"speech":[1,11],"processing":[2],"involves":[3],"the":[4,19,27,72,93,98,104,115,120],"automatic":[5],"analysis":[6],"of":[7,10,21,26,77,114,119],"a":[8,14,53,67],"collection":[9],"data":[12],"in":[13,46,64],"completely":[15],"unsupervised":[16],"fashion":[17],"without":[18],"benefit":[20],"any":[22],"transcriptions":[23],"or":[24],"annotations":[25],"data.":[28],"In":[29],"this":[30,108],"paper,":[31],"our":[32,90],"zero-resource":[33],"system":[34,51,91],"seeks":[35],"to":[36],"automatically":[37],"discover":[38],"important":[39],"words,":[40],"phrases":[41],"and":[42,74,100],"topical":[43,117],"themes":[44,118],"present":[45],"an":[47,86],"audio":[48,121],"corpus.":[49],"This":[50],"employs":[52],"segmental":[54],"dynamic":[55],"time":[56],"warping":[57],"(S-DTW)":[58],"algorithm":[59],"for":[60],"acoustic":[61,112],"pattern":[62,80],"discovery":[63],"conjunction":[65],"with":[66,103],"probabilistic":[68],"model":[69],"which":[70],"treats":[71],"topic":[73],"pseudo-word":[75],"identity":[76],"each":[78],"discovered":[79,105],"as":[81],"hidden":[82],"variables.":[83],"By":[84],"applying":[85],"Expectation-Maximization":[87],"(EM)":[88],"algorithm,":[89],"estimates":[92],"latent":[94],"probability":[95],"distributions":[96],"over":[97],"pseudo-words":[99],"topics":[101],"associated":[102],"patterns.":[106],"Using":[107],"information,":[109],"we":[110],"produce":[111],"summaries":[113],"dominant":[116],"document":[122],"collection.":[123]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
