{"id":"https://openalex.org/W2515930231","doi":"https://doi.org/10.21437/interspeech.2016-551","title":"Long Short-Term Memory for Speaker Generalization in Supervised Speech Separation","display_name":"Long Short-Term Memory for Speaker Generalization in Supervised Speech Separation","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2515930231","doi":"https://doi.org/10.21437/interspeech.2016-551","mag":"2515930231"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-551","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","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/A5046063537","display_name":"Jitong Chen","orcid":"https://orcid.org/0000-0001-6084-043X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jitong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3314","last_page":"3318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.991100013256073,"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":0.9846000075340271,"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/computer-science","display_name":"Computer science","score":0.779071569442749},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7597650289535522},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6308144330978394},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.602430522441864},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48481956124305725},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.48371317982673645},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48317280411720276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4685303568840027},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4621617794036865},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4476993978023529},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42341169714927673},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1453721821308136},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08790796995162964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779071569442749},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7597650289535522},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6308144330978394},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.602430522441864},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48481956124305725},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.48371317982673645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48317280411720276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4685303568840027},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4621617794036865},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4476993978023529},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42341169714927673},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1453721821308136},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08790796995162964},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2016-551","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"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":0,"referenced_works":[],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Speech":[0],"separation":[1,61,128],"can":[2],"be":[3],"formulated":[4],"as":[5],"learning":[6],"to":[7,24],"estimate":[8],"a":[9,31,51,60,88],"time-frequency":[10],"mask":[11],"from":[12,16],"acoustic":[13],"features":[14],"extracted":[15],"noisy":[17],"speech.":[18,78],"For":[19],"supervised":[20],"speech":[21,44,101,112,127,154],"separation,":[22,45],"generalization":[23],"unseen":[25,28,92,95],"noises":[26,96],"and":[27,94,129,152],"speakers":[29,93],"is":[30,69,115,122],"critical":[32],"issue.":[33],"Although":[34],"deep":[35],"neural":[36],"networks":[37],"(DNNs)":[38],"have":[39],"been":[40],"successful":[41],"in":[42,49,97],"noise-independent":[43,153],"DNNs":[46],"are":[47],"limited":[48],"modeling":[50],"large":[52],"number":[53],"of":[54,77,99],"speakers.":[55],"To":[56],"improve":[57],"speaker":[58],"generalization,":[59],"model":[62,85,90,121,139,145],"based":[63],"on":[64,91],"long":[65],"short-term":[66],"memory":[67],"(LSTM)":[68],"proposed,":[70],"which":[71],"naturally":[72],"accounts":[73],"for":[74,125,150],"temporal":[75],"dynamics":[76],"Systematic":[79],"evaluation":[80],"shows":[81],"that":[82,108,118],"the":[83,119,137],"proposed":[84,144],"substantially":[86],"outperforms":[87],"DNN-based":[89],"terms":[98],"objective":[100],"intelligibility.":[102],"Analyzing":[103],"LSTM":[104,109,120],"internal":[105],"representations":[106],"reveals":[107],"captures":[110],"long-term":[111],"contexts.":[113],"It":[114],"also":[116],"found":[117],"more":[123],"advantageous":[124],"low-latency":[126],"it,":[130],"without":[131],"future":[132,141],"frames,":[133],"performs":[134],"better":[135],"than":[136],"DNN":[138],"with":[140],"frames.":[142],"The":[143],"represents":[146],"an":[147],"effective":[148],"approach":[149],"speaker-":[151],"separation.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}