{"id":"https://openalex.org/W2892027981","doi":"https://doi.org/10.1109/icassp.2018.8461380","title":"Spectro-Temporal Neural Factorization for Speech Dereverberation","display_name":"Spectro-Temporal Neural Factorization for Speech Dereverberation","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2892027981","doi":"https://doi.org/10.1109/icassp.2018.8461380","mag":"2892027981"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461380","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":"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/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087444767","display_name":"Kuan\u2010Ting Kuo","orcid":"https://orcid.org/0009-0001-2895-1698"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Ting Kuo","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5449","last_page":"5453"},"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":0.9976999759674072,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7642296552658081},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.7289575338363647},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6672230958938599},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6391142010688782},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5127178430557251},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.48548629879951477},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47963982820510864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4636785686016083},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.4305137097835541},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4204615652561188},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.379598468542099}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642296552658081},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.7289575338363647},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6672230958938599},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6391142010688782},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5127178430557251},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.48548629879951477},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47963982820510864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4636785686016083},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.4305137097835541},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4204615652561188},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.379598468542099},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461380","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":[{"display_name":"Peace, Justice and strong institutions","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1246381107","https://openalex.org/W1989314204","https://openalex.org/W2006129368","https://openalex.org/W2013912476","https://openalex.org/W2014506068","https://openalex.org/W2054788726","https://openalex.org/W2064675550","https://openalex.org/W2108597378","https://openalex.org/W2112796928","https://openalex.org/W2125114513","https://openalex.org/W2147166770","https://openalex.org/W2183821610","https://openalex.org/W2404724332","https://openalex.org/W2517732577","https://openalex.org/W2554816638","https://openalex.org/W2606967921","https://openalex.org/W2749034910","https://openalex.org/W2771697229","https://openalex.org/W6647660671","https://openalex.org/W6664067876","https://openalex.org/W6713304378","https://openalex.org/W6726173995","https://openalex.org/W6729912669","https://openalex.org/W6743042433","https://openalex.org/W6745960141"],"related_works":["https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W34555840","https://openalex.org/W2146544734"],"abstract_inverted_index":{"This":[0],"study":[1],"presents":[2],"a":[3,12,22,29,75,133],"spectro-temporal":[4,16,76,120],"neural":[5,30,86,107,117],"factorization":[6,77],"(STNF)":[7],"for":[8,129,170],"speech":[9,18,38,171],"dereverberation.":[10,172],"Traditionally,":[11],"contextual":[13,59],"window":[14],"of":[15,36,159,166],"reverberant":[17],"was":[19,26],"unfolded":[20],"into":[21,28],"one-way":[23,106],"vector":[24],"which":[25],"fed":[27],"network":[31,87,108],"to":[32,80,111,126,145],"estimate":[33],"the":[34,49,82,95,112,147,157,160,164],"spectra":[35],"source":[37],"at":[39],"each":[40],"time":[41,67],"frame.":[42],"Model":[43],"parameters":[44],"were":[45],"trained":[46],"by":[47,138],"using":[48],"vectorized":[50],"error":[51,92],"backpropagation":[52,93],"algorithm.":[53],"System":[54],"performance":[55],"is":[56,78,109,135],"constrained":[57],"because":[58],"correlations":[60],"and":[61,66,97,124,163],"common":[62],"factors":[63],"in":[64,85,105,115],"frequency":[65],"horizons":[68],"are":[69,101,122],"disregarded.":[70],"To":[71],"compensate":[72],"this":[73],"weakness,":[74],"incorporated":[79],"preserve":[81],"structural":[83],"information":[84],"training":[88],"based":[89],"on":[90,152],"bi-factorized":[91,116],"where":[94],"spectral":[96],"temporal":[98,148],"factor":[99],"matrices":[100],"estimated.":[102],"Affine":[103],"transformation":[104],"generalized":[110],"bilinear":[113],"decomposition":[114],"network.":[118],"The":[119],"features":[121,162,169],"extracted":[123],"forwarded":[125],"fully-connected":[127],"layers":[128],"regression":[130],"outputs.":[131],"Such":[132],"STNF":[134],"further":[136],"improved":[137],"merging":[139],"with":[140],"long":[141],"short-term":[142],"memory":[143],"layer":[144],"capture":[146],"features.":[149],"Experiments":[150],"results":[151],"2014":[153],"REVERB":[154],"Challenge":[155],"demonstrate":[156],"meaningfulness":[158],"factorized":[161],"merit":[165],"integrating":[167],"these":[168]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}