{"id":"https://openalex.org/W2998072428","doi":"https://doi.org/10.1109/icct46805.2019.8947242","title":"Multi-layer Attention Mechanism Based Speech Separation Model","display_name":"Multi-layer Attention Mechanism Based Speech Separation Model","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2998072428","doi":"https://doi.org/10.1109/icct46805.2019.8947242","mag":"2998072428"},"language":"en","primary_location":{"id":"doi:10.1109/icct46805.2019.8947242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icct46805.2019.8947242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","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/A5064287377","display_name":"Meng Li","orcid":"https://orcid.org/0000-0001-7680-1451"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meng Li","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101523731","display_name":"Tian Lan","orcid":"https://orcid.org/0000-0001-6381-7657"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Lan","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046508827","display_name":"Chuan Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Peng","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007734028","display_name":"Yuxin Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Qian","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077109703","display_name":"Qiao Liu","orcid":"https://orcid.org/0000-0002-2573-9544"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao Liu","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064287377"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.4976,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65128268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"506","last_page":"509"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.8371756076812744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.793459415435791},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7326338291168213},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7181752920150757},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5693356990814209},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5412700772285461},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5252782106399536},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48623791337013245},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.46929532289505005},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4565448760986328},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44766733050346375},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43565109372138977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3797779679298401},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.11247625946998596}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8371756076812744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.793459415435791},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7326338291168213},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7181752920150757},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5693356990814209},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5412700772285461},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5252782106399536},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48623791337013245},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.46929532289505005},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4565448760986328},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44766733050346375},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43565109372138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3797779679298401},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.11247625946998596},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icct46805.2019.8947242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icct46805.2019.8947242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W1514535095","https://openalex.org/W1991139021","https://openalex.org/W2044222806","https://openalex.org/W2069681747","https://openalex.org/W2127877627","https://openalex.org/W2133564696","https://openalex.org/W2168379380","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2735663686","https://openalex.org/W2782360754","https://openalex.org/W2794289187","https://openalex.org/W2935934262","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2964308564","https://openalex.org/W3124972797","https://openalex.org/W4214591285","https://openalex.org/W6607486085","https://openalex.org/W6630875275","https://openalex.org/W6679434410"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W1973895194","https://openalex.org/W2546593254","https://openalex.org/W3135613579","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W3209446892"],"abstract_inverted_index":{"Speech":[0,121],"separation":[1,92],"is":[2,11,107],"the":[3,14,33,40,44,69,74,84,98,110],"front-end":[4],"of":[5,32,46,120],"speech":[6,15,28],"processing":[7],"applications.":[8],"Its":[9],"purpose":[10],"to":[12,37,72,109],"separate":[13,38],"in":[16,27,61,113],"a":[17,79,89],"multi-speaker":[18,62],"environment.":[19],"The":[20,94],"neural":[21],"network":[22],"methods":[23,35],"show":[24,103],"good":[25],"performance":[26],"separation,":[29],"but":[30],"most":[31],"existing":[34],"try":[36],"all":[39],"speaker":[41,58,75],"speech.":[42,93],"From":[43],"theory":[45],"auditory":[47],"selection,":[48],"we":[49,67],"know":[50],"that":[51,83,104],"people":[52],"can":[53,87],"only":[54],"focus":[55],"on":[56,97],"one":[57],"each":[59],"time":[60],"conditions.":[63],"Inspired":[64],"by":[65],"this,":[66],"use":[68],"attention":[70],"mechanism":[71],"introduce":[73],"information":[76],"and":[77,100,117],"propose":[78],"multi-layer":[80],"structure":[81],"so":[82],"proposed":[85],"model":[86,106],"extract":[88],"more":[90],"complete":[91],"experiments":[95],"tested":[96],"TSP":[99],"THCHS-30":[101],"datasets":[102],"our":[105],"superior":[108],"baseline":[111],"models":[112],"Short-Time":[114],"Objective":[115],"Intelligibility(STOI)":[116],"Perceptual":[118],"Evaluation":[119],"Quality(PESQ).":[122]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}