{"id":"https://openalex.org/W2891219041","doi":"https://doi.org/10.1109/icassp.2018.8461663","title":"Mask Weighted Stft Ratios for Relative Transfer Function Estimation and ITS Application to Robust ASR","display_name":"Mask Weighted Stft Ratios for Relative Transfer Function Estimation and ITS Application to Robust ASR","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891219041","doi":"https://doi.org/10.1109/icassp.2018.8461663","mag":"2891219041"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"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":"Zhong-Qiu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The ohio State University, 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":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101607498"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":3.6331,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.94119207,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5619","last_page":"5623"},"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6367061138153076},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.564355731010437},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5421257615089417},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5093889832496643},{"id":"https://openalex.org/keywords/transfer-function","display_name":"Transfer function","score":0.5080130100250244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49474141001701355},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.48767364025115967},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48692500591278076},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4573393166065216},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.43365752696990967},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.431782603263855},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4277970492839813},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.419970840215683},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4175880551338196},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.41392892599105835},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.30262190103530884},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.2848129868507385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15921294689178467},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14764347672462463},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0997367799282074},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.07268616557121277}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6367061138153076},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.564355731010437},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5421257615089417},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5093889832496643},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.5080130100250244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49474141001701355},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.48767364025115967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48692500591278076},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4573393166065216},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43365752696990967},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.431782603263855},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4277970492839813},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.419970840215683},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4175880551338196},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.41392892599105835},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.30262190103530884},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.2848129868507385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15921294689178467},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14764347672462463},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0997367799282074},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.07268616557121277},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1987906574","https://openalex.org/W2061074721","https://openalex.org/W2069681747","https://openalex.org/W2144244295","https://openalex.org/W2148613904","https://openalex.org/W2168379380","https://openalex.org/W2168729028","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2289480995","https://openalex.org/W2289731793","https://openalex.org/W2291652038","https://openalex.org/W2296167893","https://openalex.org/W2397728357","https://openalex.org/W2398042854","https://openalex.org/W2398264106","https://openalex.org/W2517616541","https://openalex.org/W2539797148","https://openalex.org/W2559260703","https://openalex.org/W2559809918","https://openalex.org/W2561557072","https://openalex.org/W2635471793","https://openalex.org/W2641129314","https://openalex.org/W2698117193","https://openalex.org/W2718052359","https://openalex.org/W2891984996","https://openalex.org/W2949117887","https://openalex.org/W2951660826","https://openalex.org/W2962866211","https://openalex.org/W2966212213","https://openalex.org/W3112742522","https://openalex.org/W6696273679","https://openalex.org/W6696868244","https://openalex.org/W6712476441","https://openalex.org/W6728770099","https://openalex.org/W6739427221","https://openalex.org/W6739504299","https://openalex.org/W6740199906","https://openalex.org/W6740374833","https://openalex.org/W6755174555","https://openalex.org/W6766475400","https://openalex.org/W6787533431"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W2767070583","https://openalex.org/W1980506188","https://openalex.org/W2380771148","https://openalex.org/W2396048001","https://openalex.org/W2402466562","https://openalex.org/W4240587264","https://openalex.org/W2109356272","https://openalex.org/W2348931051"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"based":[2,121,134],"single-channel":[3],"time-frequency":[4],"(T-F)":[5],"masking":[6],"has":[7],"shown":[8],"considerable":[9],"potential":[10],"for":[11,29,86],"beamforming":[12],"and":[13,39,93,129],"robust":[14,87],"ASR.":[15,88],"This":[16],"paper":[17],"proposes":[18],"a":[19,36,40,50,104,109,113],"simple":[20],"but":[21],"novel":[22],"relative":[23],"transfer":[24],"function":[25],"(RTF)":[26],"estimation":[27],"algorithm":[28],"microphone":[30],"arrays,":[31],"where":[32],"the":[33,54,57,65,70,91,97],"RTF":[34],"between":[35],"reference":[37],"signal":[38,42],"non-reference":[41],"at":[43],"each":[44],"frequency":[45],"band":[46],"is":[47,74,83],"estimated":[48,75],"as":[49],"weighted":[51,105],"average":[52],"of":[53,56,64,96,125],"ratios":[55],"two":[58,130],"STFT":[59],"(short-time":[60],"Fourier":[61],"transform)":[62],"coefficients":[63],"speech-dominant":[66],"T-F":[67,78],"units.":[68,79],"Similarly,":[69],"noise":[71],"covariance":[72],"matrix":[73],"from":[76],"noise-dominant":[77],"An":[80],"MVDR":[81,119,131],"beamformer":[82,120],"then":[84],"constructed":[85],"Experiments":[89],"on":[90,122,135],"two-":[92],"six-channel":[94],"track":[95],"CHiME-4":[98],"challenge":[99],"show":[100],"consistent":[101],"improvement":[102],"over":[103],"delay-and-sum":[106],"(WDAS)":[107],"beamformer,":[108,112],"generalized":[110],"eigenvector":[111],"parameterized":[114],"multi-channel":[115],"Wiener":[116],"filter,":[117],"an":[118],"conventional":[123],"direction":[124],"arrival":[126],"(DOA)":[127],"estimation,":[128],"beamformers":[132],"both":[133],"eigendecomposition.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}