{"id":"https://openalex.org/W2938260200","doi":"https://doi.org/10.1109/icassp.2019.8682503","title":"Integrating Spectrotemporal Context into Features Based on Auditory Perception for Classification-based Speech Separation","display_name":"Integrating Spectrotemporal Context into Features Based on Auditory Perception for Classification-based Speech Separation","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938260200","doi":"https://doi.org/10.1109/icassp.2019.8682503","mag":"2938260200"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5101585448","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0001-6869-8319"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Department of Machine Intelligence, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Machine Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Department of Machine Intelligence, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Machine Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100394911","display_name":"Jing Chen","orcid":"https://orcid.org/0000-0002-6640-7140"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Chen","raw_affiliation_strings":["Department of Machine Intelligence, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Machine Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101585448"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02491715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"7165","last_page":"7169"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9993000030517578,"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":0.7184923887252808},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7023392915725708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7007742524147034},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6375351548194885},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5636652708053589},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5469591021537781},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5135343074798584},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5127090215682983},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.48365771770477295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4663699269294739},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4413764774799347},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4356027841567993}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7184923887252808},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7023392915725708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7007742524147034},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6375351548194885},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5636652708053589},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5469591021537781},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5135343074798584},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5127090215682983},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.48365771770477295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4663699269294739},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4413764774799347},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4356027841567993},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W278560147","https://openalex.org/W1963970749","https://openalex.org/W1974387177","https://openalex.org/W1979633207","https://openalex.org/W2009348408","https://openalex.org/W2010015629","https://openalex.org/W2017608047","https://openalex.org/W2024946937","https://openalex.org/W2045691673","https://openalex.org/W2057200980","https://openalex.org/W2060237776","https://openalex.org/W2072720341","https://openalex.org/W2085191029","https://openalex.org/W2093878066","https://openalex.org/W2122982914","https://openalex.org/W4231807801","https://openalex.org/W6610195174"],"related_works":["https://openalex.org/W2069592018","https://openalex.org/W2075740387","https://openalex.org/W2358990940","https://openalex.org/W2093931120","https://openalex.org/W2329812990","https://openalex.org/W2349116365","https://openalex.org/W3021708704","https://openalex.org/W2004231473","https://openalex.org/W2060895226","https://openalex.org/W2998542275"],"abstract_inverted_index":{"Speech":[0],"separation,":[1],"which":[2,88,103],"has":[3],"been":[4,52],"a":[5,20,101],"challenging":[6],"task":[7],"for":[8,36],"decades,":[9],"especially":[10],"at":[11],"low":[12],"signal-to-noise":[13],"ratios":[14],"(SNRs),":[15],"can":[16],"be":[17],"cast":[18],"as":[19,48],"classification":[21],"problem.":[22],"In":[23,39,71],"such":[24],"adverse":[25],"acoustic":[26],"environment,":[27],"extracting":[28],"robust":[29],"features":[30,43,57,69],"from":[31],"noisy":[32],"mixtures":[33],"is":[34],"crucial":[35],"successful":[37],"classification.":[38],"the":[40,74,83,109,126,136],"past":[41],"studies,":[42],"representing":[44],"temporal":[45],"dynamics,":[46],"known":[47],"delta":[49,77,112,138],"features,":[50],"have":[51],"widely":[53],"used.":[54],"Combining":[55],"basic":[56,68],"with":[58],"their":[59],"deltas":[60],"yields":[61],"better":[62,131],"speech":[63,132],"separation":[64],"results":[65,123],"than":[66,135],"using":[67],"alone.":[70],"this":[72],"study,":[73],"commonly":[75,110],"used":[76,111],"feature":[78,102,113,117,128],"was":[79],"modified":[80],"according":[81],"to":[82],"characteristics":[84],"of":[85],"auditory":[86,90],"perception,":[87],"included":[89],"processing":[91],"on":[92],"spectral":[93,96,115,119],"change":[94,116],"and":[95,118],"contrast.":[97],"Therefore,":[98],"we":[99],"proposed":[100,127],"integrated":[104],"spectrotemporal":[105],"context":[106],"via":[107],"replacing":[108],"by":[114],"contrast":[120],"feature.":[121,139],"Experimental":[122],"showed":[124],"that":[125],"could":[129],"produce":[130],"segregation":[133],"performance":[134],"common":[137]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}