{"id":"https://openalex.org/W1516630152","doi":"https://doi.org/10.1109/icassp.2015.7178800","title":"A deep neural network for time-domain signal reconstruction","display_name":"A deep neural network for time-domain signal reconstruction","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1516630152","doi":"https://doi.org/10.1109/icassp.2015.7178800","mag":"1516630152"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178800","doi":"https://doi.org/10.1109/icassp.2015.7178800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178800","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"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/A5100375981","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0002-3060-4345","observed_orcids":["https://orcid.org/0000-0002-3060-4345"]},"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":"Yuxuan Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"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","observed_orcids":["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","Department of Computer Science and Engineering, The Ohio State University, USA;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, 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":9.7549,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.98791156,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4390","last_page":"4394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9940999746322632,"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":0.9940999746322632,"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":0.0044999998062849045,"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":0.0007999999797903001,"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/time-domain-signal-reconstruction","display_name":"time-domain signal reconstruction","score":0.9120000004768372},{"id":"https://openalex.org/keywords/speech-resynthesis","display_name":"speech resynthesis","score":0.8740000128746033},{"id":"https://openalex.org/keywords/joint-training","display_name":"joint training","score":0.7360000014305115},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.902999997138977},{"id":"https://openalex.org/keywords/objective-quality","display_name":"objective quality","score":0.5699999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7902730703353882},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7680337429046631},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6004020571708679},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5724921822547913},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.5288642048835754},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5174185037612915},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48489147424697876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4811928868293762},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4321343004703522},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.4302448332309723},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.419036328792572},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41358494758605957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36593982577323914},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.354892760515213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1405090093612671},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1082526445388794},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08654749393463135},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178800","doi":"https://doi.org/10.1109/icassp.2015.7178800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178800","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1495679096","https://openalex.org/W1538759723","https://openalex.org/W1904365287","https://openalex.org/W1963970749","https://openalex.org/W1979099822","https://openalex.org/W1989364685","https://openalex.org/W2042141988","https://openalex.org/W2057200980","https://openalex.org/W2057889776","https://openalex.org/W2068144845","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2146502635","https://openalex.org/W2168379380","https://openalex.org/W2619993508","https://openalex.org/W3127686677","https://openalex.org/W4231807801","https://openalex.org/W4245919820","https://openalex.org/W6632305550"],"related_works":["https://openalex.org/W3110007102","https://openalex.org/W2587038580","https://openalex.org/W2613769592","https://openalex.org/W1569068623","https://openalex.org/W2609317876","https://openalex.org/W2046869671","https://openalex.org/W3112042639","https://openalex.org/W2698117193","https://openalex.org/W2396837968","https://openalex.org/W2897725921"],"abstract_inverted_index":{"Supervised":[0],"speech":[1,24,51,80,111],"separation":[2,45,106],"has":[3],"achieved":[4],"considerable":[5],"success":[6,42],"recently.":[7],"Typically,":[8],"a":[9,33,36,58,100],"deep":[10,60],"neural":[11],"network":[12,61],"(DNN)":[13],"is":[14,25],"used":[15],"to":[16,32],"estimate":[17],"an":[18,70],"ideal":[19],"time-frequency":[20],"mask,":[21],"and":[22,82,113],"clean":[23,67],"produced":[26],"by":[27],"feeding":[28],"the":[29,41,65,91],"mask-weighted":[30],"output":[31],"resynthesizer":[34],"in":[35,48,108],"subsequent":[37],"step.":[38],"So":[39],"far,":[40],"of":[43,79],"DNN-based":[44],"lies":[46],"mainly":[47],"improving":[49],"human":[50],"intelligibility.":[52],"In":[53],"this":[54],"work,":[55],"we":[56],"propose":[57],"new":[59],"that":[62],"directly":[63],"reconstructs":[64],"time-domain":[66],"signal":[68],"through":[69],"inverse":[71],"fast":[72],"Fourier":[73],"transform":[74],"layer.":[75],"The":[76,95],"joint":[77],"training":[78],"resynthesis":[81],"mask":[83],"estimation":[84],"yields":[85],"improved":[86],"objective":[87,92,110],"quality":[88],"while":[89],"maintaining":[90],"intelligibility":[93,112],"performance.":[94],"proposed":[96],"system":[97,107],"significantly":[98],"outperforms":[99],"recent":[101],"non-negative":[102],"matrix":[103],"factorization":[104],"based":[105],"both":[109],"quality.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}