{"id":"https://openalex.org/W2073612610","doi":"https://doi.org/10.1109/icassp.2014.6854965","title":"A feature study for classification-based speech separation at very low signal-to-noise ratio","display_name":"A feature study for classification-based speech separation at very low signal-to-noise ratio","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2073612610","doi":"https://doi.org/10.1109/icassp.2014.6854965","mag":"2073612610"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854965","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":"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/A5046063537","display_name":"Jitong Chen","orcid":"https://orcid.org/0000-0001-6084-043X"},"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":"Jitong Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, 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":"middle","author":{"id":"https://openalex.org/A5100375981","display_name":"Yuxuan Wang","orcid":"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","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, 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":["Center for Cognitive and Brain Sciences, The Ohio State University, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, 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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046063537"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":4.6584,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.9561368,"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":"7039","last_page":"7043"},"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":0.9994000196456909,"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":0.9983000159263611,"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/speech-recognition","display_name":"Speech recognition","score":0.6886557340621948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6552347540855408},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5905170440673828},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5816330909729004},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5337451696395874},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5190499424934387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5187721252441406},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5076133012771606},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.45787283778190613},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45478901267051697},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4537319540977478},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.44392645359039307},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4240371882915497},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4191860556602478},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.34517037868499756}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6886557340621948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6552347540855408},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5905170440673828},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5816330909729004},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5337451696395874},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5190499424934387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5187721252441406},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5076133012771606},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.45787283778190613},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45478901267051697},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4537319540977478},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.44392645359039307},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4240371882915497},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4191860556602478},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.34517037868499756},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854965","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":0.47999998927116394,"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":18,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1493299544","https://openalex.org/W1571821784","https://openalex.org/W1963970749","https://openalex.org/W1974387177","https://openalex.org/W1989364685","https://openalex.org/W1990934990","https://openalex.org/W2020438552","https://openalex.org/W2027804983","https://openalex.org/W2052667477","https://openalex.org/W2057200980","https://openalex.org/W2085191029","https://openalex.org/W2106398669","https://openalex.org/W2114719288","https://openalex.org/W2137075158","https://openalex.org/W2141998673","https://openalex.org/W4231807801","https://openalex.org/W6634082615"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W1975881626","https://openalex.org/W2089240210","https://openalex.org/W4252208810","https://openalex.org/W4375869276","https://openalex.org/W1585241115"],"abstract_inverted_index":{"Speech":[0],"separation":[1,67,114,139],"is":[2,34,53,85],"a":[3,16,42,50,59,77,107,128],"challenging":[4],"problem":[5],"at":[6],"low":[7,43],"signal-to-noise":[8],"ratios":[9],"(SNRs).":[10],"Separation":[11],"can":[12],"be":[13],"formulated":[14],"as":[15],"classification":[17],"problem.":[18],"In":[19,40,73],"this":[20],"study,":[21],"we":[22,64,75],"focus":[23],"on":[24],"the":[25,116,120,143],"SNR":[26,44],"level":[27],"of":[28,69,90,109,146],"-5":[29],"dB":[30],"in":[31],"which":[32,84],"speech":[33,113,135,138],"generally":[35],"dominated":[36],"by":[37,141],"background":[38],"noise.":[39],"such":[41],"condition,":[45],"extracting":[46],"robust":[47,134],"features":[48],"from":[49,87],"noisy":[51],"mixture":[52],"crucial":[54],"for":[55,112,133],"successful":[56],"classification.":[57],"Using":[58],"common":[60],"neural":[61],"network":[62],"classifier,":[63],"systematically":[65],"compare":[66],"performance":[68,140],"many":[70],"monaural":[71],"features.":[72],"addition,":[74],"propose":[76],"new":[78],"feature":[79,110,147],"called":[80],"Multi-Resolution":[81],"Cochleagram":[82],"(MRCG),":[83],"extracted":[86],"four":[88],"cochlea-grams":[89],"different":[91],"resolutions":[92],"to":[93],"capture":[94],"both":[95],"local":[96],"information":[97],"and":[98],"spectrotemporal":[99],"context.":[100],"Comparisons":[101],"using":[102],"two":[103],"non-stationary":[104],"noises":[105],"show":[106],"range":[108],"robustness":[111],"with":[115],"proposed":[117],"MRCG":[118],"performing":[119],"best.":[121],"We":[122],"also":[123],"find":[124],"that":[125],"ARMA":[126],"filtering,":[127],"post-processing":[129],"technique":[130],"previously":[131],"used":[132],"recognition,":[136],"improves":[137],"smoothing":[142],"temporal":[144],"trajectories":[145],"dimensions.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}