{"id":"https://openalex.org/W4226093532","doi":"https://doi.org/10.1109/asru51503.2021.9688225","title":"Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora","display_name":"Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4226093532","doi":"https://doi.org/10.1109/asru51503.2021.9688225"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688225","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5065795147","display_name":"Szu-Jui Chen","orcid":"https://orcid.org/0000-0002-6406-9280"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Szu-Jui Chen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas,Dallas,TX,75080"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas,Dallas,TX,75080","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654154","display_name":"Wei Xia","orcid":"https://orcid.org/0000-0003-3157-6988"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xia","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas,Dallas,TX,75080"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas,Dallas,TX,75080","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas,Dallas,TX,75080"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas,Dallas,TX,75080","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065795147"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5026,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68367919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T11309","display_name":"Music 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.741828203201294},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6243863105773926},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5784014463424683},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5754680037498474},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5115245580673218},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5109218955039978},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5077613592147827},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.4751322567462921},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4671193063259125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4589361846446991},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4295644462108612},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.394680917263031},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3465227484703064},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2298191785812378},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22411131858825684},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07274362444877625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741828203201294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6243863105773926},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5784014463424683},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5754680037498474},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5115245580673218},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5109218955039978},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5077613592147827},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.4751322567462921},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4671193063259125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4589361846446991},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4295644462108612},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.394680917263031},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3465227484703064},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2298191785812378},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22411131858825684},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07274362444877625},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688225","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1499999342","https://openalex.org/W1524333225","https://openalex.org/W1992475611","https://openalex.org/W1992595735","https://openalex.org/W2062164080","https://openalex.org/W2080921589","https://openalex.org/W2115086266","https://openalex.org/W2122699724","https://openalex.org/W2150769028","https://openalex.org/W2159736522","https://openalex.org/W2251711535","https://openalex.org/W2400997536","https://openalex.org/W2406264770","https://openalex.org/W2491899193","https://openalex.org/W2526050071","https://openalex.org/W2559260703","https://openalex.org/W2593116425","https://openalex.org/W2625954004","https://openalex.org/W2767754137","https://openalex.org/W2802422770","https://openalex.org/W2802973008","https://openalex.org/W2885724687","https://openalex.org/W2888867175","https://openalex.org/W2889041236","https://openalex.org/W2962892438","https://openalex.org/W3006926732","https://openalex.org/W3097257401","https://openalex.org/W3097573669","https://openalex.org/W3097636940","https://openalex.org/W6631362777","https://openalex.org/W6691575401","https://openalex.org/W6739390138","https://openalex.org/W6784855336"],"related_works":["https://openalex.org/W2962874523","https://openalex.org/W4288040805","https://openalex.org/W2125329182","https://openalex.org/W2935794029","https://openalex.org/W2050397613","https://openalex.org/W2972574141","https://openalex.org/W2100768664","https://openalex.org/W2927191280","https://openalex.org/W2072788898","https://openalex.org/W2971257213"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,102,141,164],"propose":[4],"to":[5,42,55,89],"investigate":[6],"triplet":[7,35,119],"loss":[8,36,120],"for":[9,17,39,150,184],"the":[10,44,56,67,82,86,118,151,157,167,171],"purpose":[11],"of":[12,47,73,81,156,175],"an":[13],"alternative":[14],"feature":[15],"representation":[16],"ASR.":[18],"We":[19],"consider":[20],"a":[21,30,125,143,179],"general":[22],"non-semantic":[23],"speech":[24],"representation,":[25],"which":[26,71],"is":[27,52,121],"trained":[28],"with":[29,64],"self-supervised":[31],"criteria":[32],"based":[33,96,107],"on":[34,66,97,170],"called":[37],"TRILL,":[38],"acoustic":[40,45,98,114],"modeling":[41],"represent":[43],"characteristics":[46],"each":[48],"audio.":[49],"This":[50],"strategy":[51],"then":[53],"applied":[54],"CHiME-4":[57,176],"corpus":[58,70],"and":[59,134,145,153,177],"CRSS-UTDallas":[60],"Fearless":[61,158],"Steps":[62,159],"Corpus,":[63],"emphasis":[65],"100-hour":[68],"challenge":[69],"consists":[72],"5":[74],"selected":[75],"NASA":[76],"Apollo-11":[77],"channels.":[78],"An":[79],"analysis":[80],"extracted":[83],"embeddings":[84],"provides":[85],"foundation":[87],"needed":[88],"characterize":[90],"training":[91],"utterances":[92],"into":[93],"distinct":[94],"groups":[95],"distinguishing":[99],"properties.":[100],"Moreover,":[101],"also":[103],"demonstrate":[104],"that":[105,117],"triplet-loss":[106],"embedding":[108],"performs":[109],"better":[110],"than":[111,124],"i-Vector":[112],"in":[113],"modeling,":[115,137],"confirming":[116],"more":[122],"effective":[123],"speaker":[126],"feature.":[127],"With":[128],"additional":[129],"techniques":[130],"such":[131],"as":[132],"pronunciation":[133],"silence":[135],"probability":[136],"plus":[138],"multi-style":[139],"training,":[140],"achieve":[142],"+5.42%":[144],"+3.18%":[146],"relative":[147,181],"WER":[148,182],"improvement":[149,183],"development":[152],"evaluation":[154],"sets":[155],"Corpus.":[160],"To":[161],"explore":[162],"generalization,":[163],"further":[165],"test":[166,186],"same":[168],"technique":[169],"1":[172],"channel":[173],"track":[174],"observe":[178],"+11.90%":[180],"real":[185],"data.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}