{"id":"https://openalex.org/W2406753715","doi":"https://doi.org/10.21437/interspeech.2015-252","title":"Distance-aware DNNs for robust speech recognition","display_name":"Distance-aware DNNs for robust speech recognition","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2406753715","doi":"https://doi.org/10.21437/interspeech.2015-252","mag":"2406753715"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-252","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5003251887","display_name":"Yajie Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yajie Miao","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.0576,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.8962561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"761","last_page":"765"},"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":0.9994999766349792,"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":0.9994000196456909,"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":0.8111698627471924},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6467149257659912},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6285483837127686},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4720647633075714},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4656549096107483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4580492079257965},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44219541549682617},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4298834502696991},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3556992709636688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8111698627471924},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6467149257659912},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6285483837127686},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4720647633075714},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4656549096107483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4580492079257965},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44219541549682617},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4298834502696991},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3556992709636688},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2015-252","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.9563","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.9563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Eymiao/pub/is2015_robust.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W135040384","https://openalex.org/W567546468","https://openalex.org/W587565084","https://openalex.org/W1524333225","https://openalex.org/W1591607137","https://openalex.org/W1661756259","https://openalex.org/W1970088388","https://openalex.org/W1985368711","https://openalex.org/W1992475611","https://openalex.org/W1995562189","https://openalex.org/W2028706510","https://openalex.org/W2039716246","https://openalex.org/W2045317385","https://openalex.org/W2062164080","https://openalex.org/W2064675550","https://openalex.org/W2089917322","https://openalex.org/W2112739286","https://openalex.org/W2115730999","https://openalex.org/W2123237149","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2159948109","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2213952365","https://openalex.org/W2290318471","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2395655916","https://openalex.org/W2399877729","https://openalex.org/W2405706955","https://openalex.org/W2616139854"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W1769849273","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036"],"abstract_inverted_index":{"Distant":[0],"speech":[1],"recognition":[2],"(DSR)":[3],"remains":[4],"to":[5,23,52,65,113],"be":[6,39],"an":[7],"open":[8],"chal-lenge,":[9],"even":[10,43],"for":[11],"the":[12,34,54,67,76,93,100,119,134,138],"state-of-the-art":[13],"deep":[14],"neural":[15,164],"network":[16],"(DNN)":[17],"models.":[18,61],"Previous":[19],"work":[20],"has":[21],"attempted":[22],"improve":[24],"DNNs":[25,146],"un-der":[26],"constantly":[27],"distant":[28],"speech.":[29],"However,":[30],"in":[31,98,133,158],"real":[32],"applications,":[33],"speaker-microphone":[35,166],"distance":[36,125],"(SMD)":[37],"can":[38],"quite":[40],"dynamic,":[41],"varying":[42],"within":[44],"a":[45,81,88],"single":[46],"utterance.":[47],"This":[48],"paper":[49],"investigates":[50],"how":[51],"alleviate":[53],"impact":[55],"of":[56,75,95,145],"dynamic":[57],"SMD":[58,69,77,101,120,139,153],"on":[59,80,87],"DNN":[60,72,116],"Our":[62,129],"solution":[63],"is":[64,85],"incorporate":[66],"frame-level":[68],"information":[70,78],"into":[71],"training.":[73],"Generation":[74],"relies":[79],"universal":[82],"extractor":[83],"that":[84,132],"learned":[86],"meeting":[89],"corpus.":[90],"We":[91],"study":[92],"utility":[94],"different":[96],"architectures":[97],"instantiating":[99],"extractor.":[102],"On":[103],"our":[104],"target":[105],"acoustic":[106,169],"modeling":[107,170],"task,":[108],"two":[109],"approaches":[110],"are":[111],"proposed":[112],"build":[114],"distance-aware":[115],"models":[117],"using":[118],"information:":[121],"simple":[122],"concatenation":[123],"and":[124,155],"adaptive":[126],"training":[127],"(DAT).":[128],"experiments":[130],"show":[131],"sim-plest":[135],"case,":[136],"incorporating":[137],"descriptors":[140],"improves":[141],"word":[142],"error":[143],"rates":[144],"by":[147],"5.6":[148],"%":[149],"relative.":[150],"Further":[151],"optimizing":[152],"extraction":[154],"integration":[156],"results":[157],"more":[159],"gains.":[160],"Index":[161],"Terms:":[162],"Deep":[163],"networks,":[165],"dis-tance,":[167],"robust":[168]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}