{"id":"https://openalex.org/W2127533594","doi":"https://doi.org/10.1109/asru.2007.4430187","title":"Fast audio search using vector space modelling","display_name":"Fast audio search using vector space modelling","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2127533594","doi":"https://doi.org/10.1109/asru.2007.4430187","mag":"2127533594"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","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/A5034852758","display_name":"Brett Matthews","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brett Matthews","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM TJ Watson Research Center, Yorktown Heights"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110218731","display_name":"Upendra V. Chaudhari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Upendra Chaudhari","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM TJ Watson Research Center, Yorktown Heights"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM TJ Watson Research Center, Yorktown Heights"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"641","last_page":"646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9987000226974487,"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":0.9951000213623047,"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":0.8605037927627563},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6316735148429871},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.625680685043335},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5713672637939453},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5403663516044617},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47148987650871277},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4336153566837311},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4316260814666748},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.4310576319694519},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4157482981681824},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.41034963726997375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36707639694213867},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3496767580509186},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.17996910214424133},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1741228997707367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8605037927627563},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6316735148429871},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.625680685043335},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5713672637939453},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5403663516044617},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47148987650871277},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4336153566837311},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4316260814666748},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.4310576319694519},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4157482981681824},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.41034963726997375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36707639694213867},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3496767580509186},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.17996910214424133},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1741228997707367},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2007.4430187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"},{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W49437105","https://openalex.org/W183136171","https://openalex.org/W1612003148","https://openalex.org/W2015688877","https://openalex.org/W2076471919","https://openalex.org/W2104765974","https://openalex.org/W2106284094","https://openalex.org/W2106569340","https://openalex.org/W2115220208","https://openalex.org/W2118714763","https://openalex.org/W2122739968","https://openalex.org/W2155427043","https://openalex.org/W2163319543","https://openalex.org/W6602023532","https://openalex.org/W6636440780","https://openalex.org/W6675543910","https://openalex.org/W6677196735"],"related_works":["https://openalex.org/W2106922437","https://openalex.org/W2807901368","https://openalex.org/W2158491338","https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2133733652","https://openalex.org/W2183320216","https://openalex.org/W2978829158"],"abstract_inverted_index":{"Many":[0],"techniques":[1],"for":[2,32,53,68,75,115],"retrieving":[3],"arbitrary":[4],"content":[5],"from":[6],"audio":[7,34,51,93],"have":[8],"been":[9],"developed":[10],"to":[11,20,44,97],"leverage":[12],"the":[13,98,116],"important":[14],"challenge":[15],"of":[16,24,49,58,119],"providing":[17],"fast":[18,33],"access":[19],"very":[21],"large":[22],"volumes":[23],"multimedia":[25],"data.":[26],"We":[27,78,90,106],"present":[28],"a":[29,37,46,54,65,72,112,123],"two-stage":[30],"method":[31],"search,":[35],"where":[36],"vector-space":[38],"modelling":[39],"approach":[40],"is":[41,61],"first":[42],"used":[43],"retrieve":[45],"short":[47],"list":[48,57],"candidate":[50,59],"segments":[52,60],"query.":[55],"The":[56],"then":[62],"searched":[63],"using":[64],"word-based":[66],"index":[67,74],"known":[69],"words":[70],"and":[71,83,88],"phone-based":[73],"out-of-vocabulary":[76],"words.":[77],"explore":[79],"various":[80],"system":[81,95,121],"configurations":[82],"examine":[84],"trade-offs":[85],"between":[86],"speed":[87],"accuracy.":[89,128],"evaluate":[91],"our":[92,120],"search":[94,117],"according":[96],"NIST":[99],"2006":[100],"Spoken":[101],"Term":[102],"Detection":[103],"evaluation":[104],"initiative.":[105],"find":[107],"that":[108],"we":[109],"can":[110],"obtain":[111],"30-times":[113],"speedup":[114],"phase":[118],"with":[122],"10%":[124],"relative":[125],"loss":[126],"in":[127]},"counts_by_year":[{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}