{"id":"https://openalex.org/W4205606719","doi":"https://doi.org/10.1109/ic-nidc54101.2021.9660488","title":"Speech Separation Based on DPTNet with Sparse Attention","display_name":"Speech Separation Based on DPTNet with Sparse Attention","publication_year":2021,"publication_date":"2021-11-17","ids":{"openalex":"https://openalex.org/W4205606719","doi":"https://doi.org/10.1109/ic-nidc54101.2021.9660488"},"language":"en","primary_location":{"id":"doi:10.1109/ic-nidc54101.2021.9660488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic-nidc54101.2021.9660488","pdf_url":null,"source":{"id":"https://openalex.org/S4363608589","display_name":"2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC)","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/A5003903797","display_name":"Beom Jun Woo","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Beom Jun Woo","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048876025","display_name":"Hyung Yong Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung Yong Kim","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020418641","display_name":"Jeunghun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeunghun Kim","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003903797"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.3441,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56883815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"83","issue":null,"first_page":"339","last_page":"343"},"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":0.9991999864578247,"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":0.9991000294685364,"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":0.7680794596672058},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7089197635650635},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6601663827896118},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5469635725021362},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4879888892173767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46244245767593384},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4262339174747467},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1252937912940979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7680794596672058},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7089197635650635},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6601663827896118},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5469635725021362},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4879888892173767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46244245767593384},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4262339174747467},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1252937912940979},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ic-nidc54101.2021.9660488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic-nidc54101.2021.9660488","pdf_url":null,"source":{"id":"https://openalex.org/S4363608589","display_name":"2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2519091744","https://openalex.org/W2558649592","https://openalex.org/W2952218014","https://openalex.org/W3015199127","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3163652268","https://openalex.org/W4323654151","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6761628794","https://openalex.org/W6784764134"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2611989081","https://openalex.org/W4230611425","https://openalex.org/W2731899572","https://openalex.org/W4304166257","https://openalex.org/W4294635752","https://openalex.org/W4383066092","https://openalex.org/W3215138031","https://openalex.org/W2804383999","https://openalex.org/W2802049774"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,65],"sparse":[4,77,93],"attention-based":[5],"speech":[6,13,18,30,36,39,84],"separation":[7,31,40,85],"algorithm":[8],"separating":[9],"and":[10],"generating":[11],"clean":[12,35],"from":[14,19],"mixed":[15],"audio":[16],"containing":[17],"multiple":[20],"speakers.":[21],"Recent":[22],"development":[23],"of":[24,71],"deep":[25],"learning":[26],"has":[27],"enabled":[28],"several":[29],"models":[32,41],"to":[33,49,52,80],"generate":[34],"audios.":[37],"Especially":[38],"based":[42],"on":[43],"transformer":[44,66],"show":[45,88],"high":[46],"performance":[47],"due":[48],"their":[50],"ability":[51],"learn":[53],"long":[54],"term":[55],"dependencies":[56],"compared":[57],"with":[58,67,92],"other":[59],"neural":[60],"network":[61],"structures.":[62],"However,":[63],"as":[64],"self-attention":[68],"falls":[69],"short":[70],"catching":[72],"short-term":[73],"dependencies,":[74],"we":[75],"adopt":[76],"attention":[78,94,99],"structure":[79],"the":[81,90,96],"original":[82,97],"transformer-based":[83],"model.":[86],"We":[87],"that":[89],"model":[91],"outperforms":[95],"full":[98],"method.":[100]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}