{"id":"https://openalex.org/W2399557756","doi":"https://doi.org/10.21437/interspeech.2015-536","title":"Deep neural network based spectral feature mapping for robust speech recognition","display_name":"Deep neural network based spectral feature mapping for robust speech recognition","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2399557756","doi":"https://doi.org/10.21437/interspeech.2015-536","mag":"2399557756"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-536","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-536","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/A5101924647","display_name":"Kun Han","orcid":"https://orcid.org/0000-0003-2148-7594"},"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":"Kun Han","raw_affiliation_strings":["Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319167","display_name":"Yanzhang He","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":"Yanzhang He","raw_affiliation_strings":["Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","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":["Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"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":"DeLiang Wang","raw_affiliation_strings":["Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":56,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2484","last_page":"2488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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/spectrogram","display_name":"Spectrogram","score":0.8646681904792786},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.782103419303894},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6984254717826843},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6079359650611877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5369775891304016},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5353686213493347},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5041877031326294},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.503034770488739},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4949132800102234},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4873729348182678},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4537040591239929},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.37261509895324707},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12950202822685242},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07810288667678833}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8646681904792786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782103419303894},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6984254717826843},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6079359650611877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5369775891304016},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5353686213493347},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5041877031326294},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.503034770488739},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4949132800102234},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4873729348182678},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4537040591239929},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.37261509895324707},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12950202822685242},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07810288667678833},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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:10.21437/interspeech.2015-536","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-536","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1591676560","https://openalex.org/W1973681148","https://openalex.org/W1993882792","https://openalex.org/W2006129368","https://openalex.org/W2009934439","https://openalex.org/W2042071805","https://openalex.org/W2042141988","https://openalex.org/W2062164080","https://openalex.org/W2063224314","https://openalex.org/W2078528584","https://openalex.org/W2101045344","https://openalex.org/W2114016253","https://openalex.org/W2115730999","https://openalex.org/W2136922672","https://openalex.org/W2144786298","https://openalex.org/W2146502635","https://openalex.org/W2296581541","https://openalex.org/W2328757576","https://openalex.org/W2397728357","https://openalex.org/W2402901296","https://openalex.org/W2405774341"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2016904525"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,32],"recognition":[2],"(ASR)":[3],"systems":[4,88],"suffer":[5],"from":[6,30,74],"performance":[7],"degradation":[8],"under":[9,95],"noisy":[10,75,97],"and":[11,43,52,62,98,101,113],"reverberant":[12,99],"conditions.":[13],"In":[14],"this":[15],"work,":[16],"we":[17],"explore":[18],"a":[19,65],"deep":[20],"neural":[21],"network":[22],"(DNN)":[23],"based":[24,38],"approach":[25],"for":[26,49],"spectral":[27,47],"feature":[28,59],"mapping":[29,39,60],"corrupted":[31],"to":[33,68],"clean":[34,46,70],"speech.":[35],"The":[36,82],"DNN":[37,66],"substantially":[40],"reduces":[41],"interference":[42],"produces":[44],"estimated":[45],"features":[48,92],"ASR":[50,87],"training":[51],"decoding.":[53],"We":[54],"experiment":[55],"with":[56,89,110],"several":[57],"different":[58],"approaches":[61],"demonstrate":[63],"that":[64,85],"trained":[67],"predict":[69],"log":[71],"filterbank":[72],"coefficients":[73],"spectrogram":[76],"directly":[77],"can":[78],"be":[79],"extremely":[80],"effective.":[81],"experiments":[83],"show":[84],"the":[86,103,107],"these":[90],"cleaned":[91],"perform":[93],"well":[94],"joint":[96],"conditions,":[100],"achieve":[102],"state-of-the-art":[104],"results":[105],"on":[106],"CHiME-2":[108],"corpus":[109],"stereo":[111],"(corrupted":[112],"clean)":[114],"data.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}