{"id":"https://openalex.org/W2405504744","doi":"https://doi.org/10.21437/icslp.2002-46","title":"Building an ASR system for noisy environments: SRIs 2001 SPINE evaluation system","display_name":"Building an ASR system for noisy environments: SRIs 2001 SPINE evaluation system","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W2405504744","doi":"https://doi.org/10.21437/icslp.2002-46","mag":"2405504744"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-46","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-46","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","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/A5108508738","display_name":"Venkata Ramana Rao Gadde","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Venkata Ramana Rao Gadde","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060715364","display_name":"Dimitra Vergyri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitra Vergyri","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101494873","display_name":"Jing Zheng","orcid":"https://orcid.org/0000-0003-2724-8471"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023103090","display_name":"Kemal S\u00f6nmez","orcid":"https://orcid.org/0000-0002-2816-6438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kemal S\u00f6nmez","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046717231","display_name":"Anand Venkataraman","orcid":"https://orcid.org/0000-0001-6303-4820"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anand Venkataraman","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5108508738"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.60045788,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91380359,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1577","last_page":"1580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9976999759674072,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9887999892234802,"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":0.8246790766716003},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5974266529083252},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5704566240310669},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5624851584434509},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5529873967170715},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4530552923679352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44980987906455994},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42758530378341675},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4156588912010193},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3362427353858948},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07741090655326843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246790766716003},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5974266529083252},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5704566240310669},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5624851584434509},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5529873967170715},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4530552923679352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44980987906455994},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42758530378341675},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4156588912010193},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3362427353858948},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07741090655326843},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.2002-46","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-46","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W127652782","https://openalex.org/W1904457459","https://openalex.org/W2002342963","https://openalex.org/W2090861223","https://openalex.org/W2097978681","https://openalex.org/W2104663520","https://openalex.org/W2105613081","https://openalex.org/W2126597185","https://openalex.org/W2594610113"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W2953716828","https://openalex.org/W2469820710","https://openalex.org/W2152642030"],"abstract_inverted_index":{"We":[0,104,150,170,193,214],"describe":[1,105,460],"SRI\u2019s":[2,106],"recognition":[3,21,137,244,256],"system":[4,66,102,108,138,146,181,427,470],"as":[5,155,265,272,313,449],"used":[6,178,321],"in":[7,12,24,114,179,245,267,376,479],"the":[8,42,63,110,123,128,153,164,173,184,188,191,196,202,206,210,220,230,237,240,253,299,316,364,372,396,403,412,416,450,457,473,480],"2001":[9,112,211,481],"DARPA":[10],"Speech":[11,113],"Noisy":[13,115],"Environments":[14,116],"(SPINE)":[15,117],"evaluation.":[16,213,483],"The":[17,28,119,249,280,302,319],"SPINE":[18,165,212,222,357,482],"task":[19,29,166,185,227,254,417],"involves":[20],"of":[22,36,54,73,79,85,122,133,190,209,219,239,242,252,257,262,283,325,340,363,394,406,433,446,453],"speech":[23,38,136,243,258,370],"simulated":[25],"military":[26,246,269,294],"environments.":[27,248],"had":[30],"some":[31,359,377],"unique":[32,360],"challenges,":[33],"including":[34,82],"segmentation":[35,94,434],"foreground":[37,369],"from":[39,57,371],"noisy":[40,50,355,373],"background,":[41,374],"need":[43],"for":[44,67,109,147,315,410,422,426],"robust":[45,387,436],"acoustic":[46,388,437],"models":[47,56],"to":[48,126,163,235,332,351,367,385],"handle":[49],"speech,":[51],"and":[52,95,97,101,131,139,167,176,182,205,276,307,329,391,435,438,463],"development":[53],"language":[55,91,320,413,439],"limited":[58,334,404],"training":[59,407,411],"data.":[60],"In":[61,456],"developing":[62],"SRI":[64],"evaluation":[65,107,207],"this":[68,333],"task,":[69],"we":[70,158,441,459],"addressed":[71],"each":[72],"these":[74,431,461],"challenges":[75,419],"using":[76],"a":[77,134,145,160,217,224,289,323,444,469],"combination":[78,103],"state-of-the-art":[80],"techniques,":[81],"several":[83],"types":[84],"feature":[86],"normalization,":[87],"model":[88],"adaptation,":[89],"class-based":[90],"modeling,":[92,440],"multi-pass":[93],"recognition,":[96],"word":[98,475],"posterior-based":[99],"decoding":[100],"October":[111],"task.":[118],"main":[120],"aim":[121],"paper":[124,154],"is":[125,223,255],"present":[127,172,195],"key":[129,174],"algorithms":[130,177,448],"components":[132,175,462],"state-of-art":[135],"how":[140,183,464],"they":[141,465],"were":[142,466],"combined":[143],"into":[144,298,468],"optimal":[148],"performance.":[149],"have":[151],"organized":[152],"follows.":[156],"First,":[157],"provide":[159],"brief":[161],"introduction":[162],"its":[168,352],"challenges.":[169,361],"then":[171,194],"our":[180,454],"features":[186],"guided":[187],"design":[189],"system.":[192,455],"results":[197],"on":[198,354,443],"two":[199,286],"test":[200,236],"sets,":[201],"dry":[203],"run":[204],"sets":[208],"conclude":[215],"with":[216,259,292],"discussion":[218],"results.":[221],"relatively":[225],"new":[226],"developed":[228],"by":[229],"Naval":[231],"Research":[232],"Laboratory":[233],"(NRL)":[234],"state":[238],"art":[241],"noise":[247,264],"primary":[250],"challenge":[251,383,401],"significant":[260],"amounts":[261],"background":[263,380],"found":[266],"various":[268],"environments,":[270,356,378],"such":[271],"fighter":[273,310],"jet":[274],"cockpits":[275],"aircraft":[277],"carrier":[278],"flightdecks.":[279],"data":[281],"consists":[282],"dialogs":[284],"between":[285],"participants":[287],"playing":[288],"battleship-like":[290],"game,":[291],"recorded":[293],"noises":[295],"played":[296],"back":[297],"recording":[300],"environment.":[301],"players":[303],"use":[304],"realistic":[305],"microphones":[306],"headgear":[308],"(e.g.,":[309],"pilot":[311],"helmets)":[312],"appropriate":[314],"different":[317],"scenarios.":[318],"comprises":[322],"mix":[324],"commands,":[326],"status":[327],"reports,":[328],"confirmations":[330],"specific":[331],"domain,":[335],"involving":[336],"an":[337],"active":[338],"vocabulary":[339],"about":[341],"2000":[342],"words.":[343],"More":[344],"details":[345],"are":[346],"available":[347],"at":[348],"[1].":[349],"Due":[350],"focus":[353],"posed":[358,418],"One":[362],"difffculties":[365],"was":[366,384,402],"segment":[368],"which,":[375],"included":[379],"speech.":[381,398],"Another":[382],"develop":[386],"features,":[389],"models,":[390],"techniques":[392],"capable":[393],"recognizing":[395],"noise-degraded":[397],"Yet":[399],"another":[400],"amount":[405],"data,":[408],"particluarly":[409],"model.":[414],"Thus,":[415],"not":[420],"only":[421],"research,":[423],"but":[424],"also":[425],"development.":[428],"To":[429],"solve":[430],"issues":[432],"drew":[442],"number":[445],"stateof-the-art":[447],"building":[451],"blocks":[452],"following,":[458],"integrated":[467],"that":[471],"achieved":[472],"lowest":[474],"error":[476],"rate":[477],"(WER)":[478]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}