{"id":"https://openalex.org/W1572221186","doi":"https://doi.org/10.1109/icassp.1986.1169210","title":"Optimal and suboptimal training strategies for automatic speech recognition in noise, and the effects of adaptation on performance","display_name":"Optimal and suboptimal training strategies for automatic speech recognition in noise, and the effects of adaptation on performance","publication_year":2005,"publication_date":"2005-03-24","ids":{"openalex":"https://openalex.org/W1572221186","doi":"https://doi.org/10.1109/icassp.1986.1169210","mag":"1572221186"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1986.1169210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1986.1169210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '86. 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/A5070855105","display_name":"James Baker","orcid":"https://orcid.org/0000-0002-2682-6922"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"J. Baker","raw_affiliation_strings":["Dragon Systems, Inc., Newtown, MA, USA"],"affiliations":[{"raw_affiliation_string":"Dragon Systems, Inc., Newtown, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016612157","display_name":"David Pinto","orcid":"https://orcid.org/0000-0002-8516-5925"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D. Pinto","raw_affiliation_strings":["Dragon Systems, Inc., Newtown, MA, USA"],"affiliations":[{"raw_affiliation_string":"Dragon Systems, Inc., Newtown, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070855105"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.07625677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"745","last_page":"748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9925000071525574,"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":0.9925000071525574,"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":0.9850000143051147,"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/speech-recognition","display_name":"Speech recognition","score":0.7669641375541687},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.7298811078071594},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6804662942886353},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6693004369735718},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6649577021598816},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.5538095235824585},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4835967421531677},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4575859606266022},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4504932463169098},{"id":"https://openalex.org/keywords/ambient-noise-level","display_name":"Ambient noise level","score":0.4107840061187744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2320435643196106},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07793697714805603},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07551988959312439},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0642627477645874}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7669641375541687},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7298811078071594},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6804662942886353},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6693004369735718},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6649577021598816},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.5538095235824585},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4835967421531677},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4575859606266022},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4504932463169098},{"id":"https://openalex.org/C205312793","wikidata":"https://www.wikidata.org/wiki/Q16002801","display_name":"Ambient noise level","level":3,"score":0.4107840061187744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2320435643196106},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07793697714805603},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07551988959312439},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0642627477645874},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1986.1169210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1986.1169210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1927915579","https://openalex.org/W2065625684","https://openalex.org/W2108389368"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W4253186488","https://openalex.org/W2044344400","https://openalex.org/W1996938127","https://openalex.org/W2083611981","https://openalex.org/W2072507639","https://openalex.org/W2043380045","https://openalex.org/W4231814374","https://openalex.org/W2155964760","https://openalex.org/W1977167953"],"abstract_inverted_index":{"The":[0,129,165],"quality":[1],"of":[2,10,33,46,84,106,153,167,170,178,190,229,232,250],"operational":[3],"speech":[4,147],"recognition":[5,148,176,212,252],"performance":[6,177,233],"in":[7,43,55,139],"the":[8,19,50,66,173,183,188,209,224,230,248,251],"presence":[9],"variable":[11],"ambient":[12,111],"noise":[13,112,226],"can":[14,240],"be":[15,241],"significantly":[16],"affected":[17],"by":[18,30,243],"conditions":[20,239],"under":[21],"which":[22],"patterns":[23,35],"are":[24,40,221],"initially":[25],"trained,":[26],"as":[27,29,263],"well":[28],"subsequent":[31],"modifications":[32],"these":[34],"through":[36],"\"adaptation\".":[37],"These":[38],"effects":[39,174,189],"clearly":[41],"evidenced":[42],"a":[44,125,193],"series":[45,169],"experiments":[47,171],"conducted":[48],"using":[49],"Dragon":[51],"Systems":[52],"Speech":[53],"Driver":[54],"conjunction":[56],"with":[57,65,114,124,255],"DragonLAB":[58],"(an":[59],"experimenter's":[60],"workstation":[61],"facility),":[62],"commercially":[63],"available":[64],"IBM":[67,80],"PC":[68],"Voice":[69,73],"Communications":[70],"Option":[71],"and":[72,92,97,108,120,157,187,200,206,218,237],"Recognition":[74],"Tool":[75],"Kit,":[76],"running":[77],"on":[78,175,182],"an":[79,115],"PC/AT.":[81],"For":[82,203],"each":[83,105,256],"two":[85],"discrete":[86],"command/control":[87],"vocabularies,":[88,208],"\"Menu\"":[89],"(24":[90],"words)":[91],"\"DOS\"":[93],"(29":[94],"words),":[95],"training":[96,156,180,217,236,265],"multiple":[98],"test":[99,158,185,219,238,258],"session":[100],"recordings":[101],"were":[102,160],"made":[103],"at":[104,121,223],"55":[107],"65":[109],"dB":[110,123],"levels":[113],"inexpensive":[116],"cassette":[117],"tape-recorder":[118],"microphone,":[119],"85":[122],"close-talking":[126],"noise-cancelling":[127],"microphone.":[128],"seven":[130],"American":[131],"English-speaking":[132],"subjects":[133],"(4":[134],"male,":[135],"3":[136],"female)":[137],"included":[138],"this":[140,163,168],"database,":[141],"exhibit":[142],"diverse":[143],"voice":[144],"qualities,":[145],"dialects,":[146],"familiarity,":[149],"etc.":[150],"A":[151],"total":[152],"over":[154],"20,000":[155],"utterances":[159],"collected":[161],"for":[162,198],"database.":[164],"results":[166],"demonstrates":[172],"different":[179,235],"stes":[181],"same":[184,225],"sets,":[186],"adaptation":[191,246],"(in":[192],"supervised":[194,245],"learning":[195],"mode),":[196],"both":[197,207],"speaker-dependent":[199],"cross-speaker":[201],"modes.":[202],"all":[204],"speakers":[205],"best":[210],"speaker-depentent":[211],"is":[213],"consistently":[214],"obtained":[215],"when":[216],"materials":[220],"recorded":[222],"level.":[227],"Much":[228],"deterioration":[231],"across":[234],"reduced":[242],"employing":[244],"during":[247],"course":[249],"tests":[253],"themselves,":[254],"new":[257],"token":[259],"subsequently":[260],"being":[261],"used":[262],"additional":[264],"to":[266],"adapt":[267],"its":[268],"model.":[269]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}