{"id":"https://openalex.org/W2042141988","doi":"https://doi.org/10.1109/icassp.2014.6854051","title":"Joint noise adaptive training for robust automatic speech recognition","display_name":"Joint noise adaptive training for robust automatic speech recognition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2042141988","doi":"https://doi.org/10.1109/icassp.2014.6854051","mag":"2042141988"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"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":"Arun Narayanan","raw_affiliation_strings":["Department of Computer Science and Engineering","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering","institution_ids":[]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","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":["Department of Computer Science and Engineering","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering","institution_ids":[]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","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":99,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2504","last_page":"2508"},"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":0.9998999834060669,"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/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":0.791580080986023},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7485498189926147},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6176387667655945},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5711929798126221},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5392507314682007},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5346791744232178},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5343754887580872},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5110303163528442},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49747708439826965},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4930550754070282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4721876382827759},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.44757771492004395},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4194851517677307},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38221868872642517},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1729925274848938},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09094056487083435}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791580080986023},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7485498189926147},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6176387667655945},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5711929798126221},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5392507314682007},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5346791744232178},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5343754887580872},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5110303163528442},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49747708439826965},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4930550754070282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4721876382827759},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.44757771492004395},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4194851517677307},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38221868872642517},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1729925274848938},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09094056487083435},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1599512239","https://openalex.org/W1904365287","https://openalex.org/W1964118201","https://openalex.org/W1976637928","https://openalex.org/W1993882792","https://openalex.org/W2008971146","https://openalex.org/W2035576074","https://openalex.org/W2041638389","https://openalex.org/W2047919706","https://openalex.org/W2052667477","https://openalex.org/W2062164080","https://openalex.org/W2067117291","https://openalex.org/W2114016253","https://openalex.org/W2114719288","https://openalex.org/W2122009793","https://openalex.org/W2137075158","https://openalex.org/W2140595311","https://openalex.org/W2141411743","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2290318471","https://openalex.org/W2334833135","https://openalex.org/W2394967684","https://openalex.org/W2490695385","https://openalex.org/W2561557072","https://openalex.org/W2611466149","https://openalex.org/W2748434850","https://openalex.org/W4233392025"],"related_works":["https://openalex.org/W2022538999","https://openalex.org/W1955763106","https://openalex.org/W2002243964","https://openalex.org/W3090086172","https://openalex.org/W3171883019","https://openalex.org/W1585241115","https://openalex.org/W2120213246","https://openalex.org/W1564179349","https://openalex.org/W2025188156","https://openalex.org/W4312751558"],"abstract_inverted_index":{"We":[0],"explore":[1],"time-frequency":[2],"masking":[3],"to":[4,36,58],"improve":[5],"noise":[6,28],"robust":[7],"automatic":[8],"speech":[9,26],"recognition.":[10],"Apart":[11],"from":[12],"its":[13],"use":[14,19],"as":[15,33,67],"a":[16,37,46,68,75],"frontend,":[17],"we":[18,73],"it":[20],"for":[21],"providing":[22],"smooth":[23],"estimates":[24],"of":[25],"and":[27,83],"which":[29],"are":[30],"then":[31],"passed":[32],"additional":[34],"features":[35],"deep":[38],"neural":[39],"network":[40],"(DNN)":[41],"based":[42],"acoustic":[43,84],"model.":[44],"Such":[45],"system":[47,88,93],"improves":[48,81],"performance":[49],"on":[50,94],"the":[51,59,90],"Aurora-4":[52],"dataset":[53],"by":[54,97],"10.5%":[55],"(relative)":[56],"compared":[57],"previous":[60,91],"best":[61,92],"published":[62],"results.":[63],"By":[64],"formulating":[65],"separation":[66,82],"supervised":[69],"mask":[70],"estimation":[71],"problem,":[72],"develop":[74],"unified":[76],"DNN":[77],"framework":[78],"that":[79],"jointly":[80],"modeling.":[85],"Our":[86],"final":[87],"outperforms":[89],"CHiME-2":[95],"corpus":[96],"22.1%":[98],"(relative).":[99]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}