{"id":"https://openalex.org/W2102750383","doi":"https://doi.org/10.1109/icassp.2004.1326010","title":"A detection based approach to robust speech understanding","display_name":"A detection based approach to robust speech understanding","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2102750383","doi":"https://doi.org/10.1109/icassp.2004.1326010","mag":"2102750383"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5049077025","display_name":"Kuansan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kuansan Wang","raw_affiliation_strings":["Speech Technology Group, Microsoft Research Limited, Redmond, WA, USA","Speech Technology Group, Microsoft Research, Redmond, WA USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Speech Technology Group, Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Speech Technology Group, Microsoft Research, Redmond, WA USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5049077025"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.8573,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73959858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9976999759674072,"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":0.8473440408706665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7232651710510254},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49787306785583496},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47817641496658325},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47461381554603577},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.4641270637512207},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4638882279396057},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46361997723579407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4595230519771576},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4545556306838989},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.43791505694389343},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.431460440158844},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42611774802207947},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4201808571815491},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4166381061077118},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2071768045425415},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08173820376396179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8473440408706665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7232651710510254},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49787306785583496},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47817641496658325},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47461381554603577},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4641270637512207},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4638882279396057},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46361997723579407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4595230519771576},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4545556306838989},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.43791505694389343},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.431460440158844},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42611774802207947},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4201808571815491},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4166381061077118},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2071768045425415},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08173820376396179},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1326010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.939.7101","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.939.7101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/77493/2004-wang-icassp.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W46190896","https://openalex.org/W88864901","https://openalex.org/W595249637","https://openalex.org/W1560013842","https://openalex.org/W1608512004","https://openalex.org/W2102512139","https://openalex.org/W2113614827","https://openalex.org/W2119820672","https://openalex.org/W2122516409","https://openalex.org/W2134587001","https://openalex.org/W2141354973","https://openalex.org/W2163599171","https://openalex.org/W2167845555","https://openalex.org/W4285719527","https://openalex.org/W7073833573"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2545741539","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W4200596008"],"abstract_inverted_index":{"Field":[0],"speech":[1,11,55,64,126,167],"data":[2,41],"pose":[3],"great":[4],"challenges":[5],"to":[6,28,38,60,76,91,123,133],"statistical":[7],"modeling":[8],"because":[9],"the":[10,54,62,68,80,92,100,103,109,113,121,134,143,152,155],"signal":[12],"is":[13,35,74],"often":[14],"intermixed":[15],"with":[16,79,159],"extraneous":[17],"sounds":[18],"and":[19,65,137,164],"other":[20,165],"environmental":[21],"noise":[22],"either":[23],"that":[24],"are":[25,140,169],"too":[26,36],"difficult":[27],"compensate":[29],"dynamically":[30],"or":[31],"for":[32,42,84,106,146],"which":[33,53],"it":[34],"expensive":[37],"collect":[39],"sufficient":[40],"proper":[43],"offline":[44],"training.":[45],"We":[46],"propose":[47],"a":[48,85,124],"detection":[49,110],"based":[50],"method":[51,73],"in":[52,157],"recognizer":[56],"can":[57],"sharply":[58],"tune":[59],"only":[61],"\"meaningful\"":[63],"gracefully":[66],"ignore":[67],"\"unwanted\"":[69],"audio":[70],"segments.":[71],"The":[72],"designed":[75],"be":[77],"integrated":[78],"frame":[81],"synchronous":[82],"search":[83],"single":[86],"pass":[87],"processing.":[88],"In":[89],"contrast":[90],"conventional":[93],"keyword":[94],"spotting":[95],"techniques,":[96],"this":[97],"integration":[98],"allows":[99],"use":[101],"of":[102,154,161],"language":[104],"model":[105],"better":[107],"predicting":[108],"targets":[111],"during":[112],"search.":[114],"To":[115],"study":[116],"its":[117],"efficacy,":[118],"we":[119],"apply":[120],"framework":[122],"spontaneous":[125,166],"understanding":[127],"application":[128,138],"where":[129],"cohesive":[130],"phrases":[131,163],"congruent":[132],"domain":[135,162],"semantics":[136],"context":[139],"used":[141],"as":[142],"salient":[144],"feature":[145],"selective":[147],"hearing.":[148],"Experimental":[149],"results":[150],"on":[151],"effectiveness":[153],"system":[156],"dealing":[158],"out":[160],"effects":[168],"encouraging.":[170]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}