{"id":"https://openalex.org/W2141411743","doi":"https://doi.org/10.1109/icassp.2013.6639038","title":"Ideal ratio mask estimation using deep neural networks for robust speech recognition","display_name":"Ideal ratio mask estimation using deep neural networks for robust speech recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2141411743","doi":"https://doi.org/10.1109/icassp.2013.6639038","mag":"2141411743"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/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":true,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"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, Center for Cognitive Science, Ohio State University, Columbus, OH, USA","Center for Cognitive Sci., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Center for Cognitive Science, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Center for Cognitive Sci., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000078382"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":28.9405,"has_fulltext":false,"cited_by_count":550,"citation_normalized_percentile":{"value":0.99815509,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7092","last_page":"7096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9984999895095825,"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":0.8198584318161011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7603190541267395},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6392296552658081},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5628737807273865},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.558119535446167},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5542412400245667},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5469539165496826},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5232757329940796},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4869924485683441},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47307926416397095},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.47031083703041077},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.46301671862602234},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4601818323135376},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45622357726097107},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44688481092453003},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.43109366297721863},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.42805173993110657},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4260020852088928},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.42079994082450867},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2725672721862793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.179539293050766},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12619194388389587}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8198584318161011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603190541267395},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6392296552658081},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5628737807273865},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.558119535446167},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5542412400245667},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5469539165496826},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5232757329940796},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4869924485683441},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47307926416397095},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.47031083703041077},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.46301671862602234},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4601818323135376},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45622357726097107},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44688481092453003},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.43109366297721863},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.42805173993110657},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4260020852088928},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.42079994082450867},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2725672721862793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.179539293050766},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12619194388389587},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.881","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Narayanan-Wang2.icassp13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W75153181","https://openalex.org/W160800111","https://openalex.org/W1495679096","https://openalex.org/W1635512741","https://openalex.org/W1989364685","https://openalex.org/W2002342963","https://openalex.org/W2027701650","https://openalex.org/W2034040413","https://openalex.org/W2086139506","https://openalex.org/W2126597753","https://openalex.org/W2130020166","https://openalex.org/W2136922672","https://openalex.org/W2137075158","https://openalex.org/W2138456300","https://openalex.org/W2146083413","https://openalex.org/W2150866759","https://openalex.org/W2155445312","https://openalex.org/W2163648514","https://openalex.org/W2168379380","https://openalex.org/W2334833135","https://openalex.org/W2490695385","https://openalex.org/W2561557072","https://openalex.org/W2619993508","https://openalex.org/W4233392025","https://openalex.org/W4245919820","https://openalex.org/W6603045223","https://openalex.org/W6684924409"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W2074132948","https://openalex.org/W2160511961"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,16,32,60,85,131],"feature":[3,67],"enhancement":[4,83],"algorithm":[5,14],"to":[6,44,55],"improve":[7],"robust":[8,78],"automatic":[9],"speech":[10],"recognition":[11],"(ASR).":[12],"The":[13,50],"estimates":[15],"smoothed":[17],"ideal":[18,47],"ratio":[19],"mask":[20],"(IRM)":[21],"in":[22,91,101,140],"the":[23,46,72,76,81,111,116,127],"Mel":[24,62],"frequency":[25,142],"domain":[26],"using":[27,97,115],"deep":[28],"neural":[29],"networks":[30],"and":[31,104],"set":[33],"of":[34,75,88,93,107,122,135],"time-frequency":[35],"unit":[36],"level":[37],"features":[38],"that":[39],"has":[40],"previously":[41],"been":[42],"used":[43,54],"estimate":[45],"binary":[48],"mask.":[49],"estimated":[51],"IRM":[52],"is":[53],"filter":[56],"out":[57],"noise":[58],"from":[59],"noisy":[61,73],"spectrogram":[63],"before":[64],"performing":[65],"cepstral":[66],"extraction":[68],"for":[69],"ASR.":[70],"On":[71],"subset":[74],"Aurora-4":[77],"ASR":[79,98],"corpus,":[80],"proposed":[82,128],"obtains":[84,130],"relative":[86],"improvement":[87,106],"over":[89,108],"38%":[90],"terms":[92,121],"word":[94],"error":[95,134],"rates":[96],"models":[99,112],"trained":[100,114],"clean":[102],"conditions,":[103],"an":[105],"14%":[109],"when":[110],"are":[113],"multi-condition":[117],"training":[118],"data.":[119],"In":[120],"instantaneous":[123],"SNR":[124],"estimation":[125],"performance,":[126],"system":[129],"mean":[132],"absolute":[133],"less":[136],"than":[137],"4":[138],"dB":[139],"most":[141],"channels.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":46},{"year":2022,"cited_by_count":47},{"year":2021,"cited_by_count":59},{"year":2020,"cited_by_count":93},{"year":2019,"cited_by_count":64},{"year":2018,"cited_by_count":61},{"year":2017,"cited_by_count":43},{"year":2016,"cited_by_count":34},{"year":2015,"cited_by_count":34},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}