{"id":"https://openalex.org/W2893370043","doi":"https://doi.org/10.1109/slt.2018.8639632","title":"An Exploration of Mimic Architectures for Residual Network Based Spectral Mapping","display_name":"An Exploration of Mimic Architectures for Residual Network Based Spectral Mapping","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2893370043","doi":"https://doi.org/10.1109/slt.2018.8639632","mag":"2893370043"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5055583643","display_name":"Peter Plantinga","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Plantinga","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089667871","display_name":"Deblin Bagchi","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deblin Bagchi","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"550","last_page":"557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9991000294685364,"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":0.8113869428634644},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7225543260574341},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7120023965835571},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6475157737731934},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5896314382553101},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5824047327041626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5722328424453735},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45404258370399475},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4371100664138794},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4198979139328003},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41530242562294006},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07894459366798401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8113869428634644},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7225543260574341},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7120023965835571},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6475157737731934},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5896314382553101},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5824047327041626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5722328424453735},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45404258370399475},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4371100664138794},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4198979139328003},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41530242562294006},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07894459366798401},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/slt.2018.8639632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1600744878","https://openalex.org/W1821462560","https://openalex.org/W1897240248","https://openalex.org/W2005708641","https://openalex.org/W2006129368","https://openalex.org/W2035576074","https://openalex.org/W2057826000","https://openalex.org/W2101045344","https://openalex.org/W2134797427","https://openalex.org/W2143612262","https://openalex.org/W2144786298","https://openalex.org/W2176412452","https://openalex.org/W2194775991","https://openalex.org/W2253986341","https://openalex.org/W2285420822","https://openalex.org/W2288645994","https://openalex.org/W2291652038","https://openalex.org/W2296167893","https://openalex.org/W2398826216","https://openalex.org/W2399557756","https://openalex.org/W2402040300","https://openalex.org/W2516342150","https://openalex.org/W2519224033","https://openalex.org/W2530876040","https://openalex.org/W2541674938","https://openalex.org/W2587717635","https://openalex.org/W2682975603","https://openalex.org/W2962946266","https://openalex.org/W2962998773","https://openalex.org/W2963285578","https://openalex.org/W2963410064","https://openalex.org/W2963453742","https://openalex.org/W2964121744","https://openalex.org/W2964137095","https://openalex.org/W2966212213","https://openalex.org/W4293390340","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6638523607","https://openalex.org/W6679909955","https://openalex.org/W6685562342","https://openalex.org/W6712560600","https://openalex.org/W6712706723","https://openalex.org/W6712847557","https://openalex.org/W6713132643","https://openalex.org/W6726607834","https://openalex.org/W6729059855","https://openalex.org/W6766475400"],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W2949601986","https://openalex.org/W2788972299","https://openalex.org/W2498789492","https://openalex.org/W2521347458","https://openalex.org/W2729981612","https://openalex.org/W4233449973","https://openalex.org/W2925692864","https://openalex.org/W2972212393","https://openalex.org/W2977327189"],"abstract_inverted_index":{"Spectral":[0],"mapping":[1,27,110],"uses":[2],"a":[3,70,75,119,126,148],"deep":[4],"neural":[5],"network":[6,44,77],"(DNN)":[7],"to":[8,14,46,82,112,117],"map":[9],"directly":[10],"from":[11,34,135],"noisy":[12],"speech":[13],"clean":[15,40,87],"speech.":[16,41,88],"Our":[17,114],"previous":[18],"study":[19],"[1]":[20],"found":[21],"that":[22,78,121],"the":[23,48,52,57,83,98,106,132,141,154],"performance":[24,107],"of":[25,85,108,150],"spectral":[26,53,72,109],"improves":[28],"greatly":[29],"when":[30],"using":[31,163],"helpful":[32],"cues":[33],"an":[35],"acoustic":[36],"model":[37,120,137],"trained":[38],"on":[39],"The":[42],"mapper":[43,73],"learns":[45],"mimic":[47,99],"input":[49],"favored":[50],"by":[51],"classifier":[54],"and":[55,146],"cleans":[56],"features":[58,133],"accordingly.":[59],"In":[60],"this":[61],"study,":[62],"we":[63,68],"explore":[64],"two":[65],"new":[66],"innovations:":[67],"replace":[69],"DNN-based":[71],"with":[74],"residual":[76],"is":[79,116,153],"more":[80],"attuned":[81],"goal":[84,115],"predicting":[86],"We":[89],"also":[90],"examine":[91],"how":[92],"integrating":[93],"long":[94],"term":[95],"context":[96],"in":[97],"criterion":[100],"(via":[101],"wide-residual":[102],"biL-STM":[103],"networks)":[104],"affects":[105],"compared":[111],"DNNs.":[113],"derive":[118],"can":[122],"be":[123],"used":[124],"as":[125],"preprocessor":[127],"for":[128,160],"any":[129],"recognition":[130],"system;":[131],"derived":[134],"our":[136],"are":[138],"passed":[139],"through":[140],"standard":[142],"Kaldi":[143],"ASR":[144],"pipeline":[145],"achieve":[147],"WER":[149],"9.3%,":[151],"which":[152],"lowest":[155],"recorded":[156],"word":[157],"error":[158],"rate":[159],"CHiME-2":[161],"dataset":[162],"only":[164],"feature":[165],"adaptation.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}