{"id":"https://openalex.org/W3015623828","doi":"https://doi.org/10.1109/icassp40776.2020.9054222","title":"Speakerfilter: Deep Learning-Based Target Speaker Extraction Using Anchor Speech","display_name":"Speakerfilter: Deep Learning-Based Target Speaker Extraction Using Anchor Speech","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015623828","doi":"https://doi.org/10.1109/icassp40776.2020.9054222","mag":"3015623828"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103195569","display_name":"Shulin He","orcid":"https://orcid.org/0009-0002-0382-3515"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulin He","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348614","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-5963-4505"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":2.1361,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.88979346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"376","last_page":"380"},"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":0.9998000264167786,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8230847120285034},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6285412311553955},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5929412245750427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5057551860809326},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.484079509973526},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.45088326930999756},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3478288948535919}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230847120285034},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6285412311553955},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5929412245750427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5057551860809326},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.484079509973526},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.45088326930999756},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3478288948535919}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1523691755","https://openalex.org/W1552314771","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2304609584","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2567070169","https://openalex.org/W2568308529","https://openalex.org/W2749659773","https://openalex.org/W2889442120","https://openalex.org/W2891833136","https://openalex.org/W2935865280","https://openalex.org/W2946244506","https://openalex.org/W2951130829","https://openalex.org/W2962866211","https://openalex.org/W2963970792","https://openalex.org/W2973062255","https://openalex.org/W2973165826","https://openalex.org/W6731370813","https://openalex.org/W6755462816","https://openalex.org/W6761015776"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2160753975","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2161543916"],"abstract_inverted_index":{"Speaker":[0],"extraction":[1,74],"aims":[2],"to":[3,26],"separate":[4],"a":[5,28,58,71,81,115],"target":[6,33,52],"speaker":[7,34,42,53,98],"from":[8,54],"multiple":[9],"voices":[10],"which":[11,37,93],"is":[12,94],"useful":[13,39],"for":[14,41,97],"applications,":[15],"e.g.":[16],"teleconference.":[17],"In":[18],"many":[19],"practical":[20],"cases,":[21],"it":[22],"has":[23],"an":[24],"opportunity":[25],"get":[27],"piece":[29,60],"voice":[30],"of":[31,49,61,120],"the":[32,47,51,55,78,89,105,110,124],"in":[35],"advance,":[36],"provides":[38],"information":[40],"extraction.":[43,99],"This":[44],"paper":[45],"addresses":[46],"problem":[48],"extracting":[50],"mixture":[56],"using":[57],"short":[59],"anchor":[62,67],"speech.":[63],"To":[64],"effectively":[65],"utilize":[66],"speech,":[68],"we":[69],"propose":[70],"multi-level":[72],"feature":[73],"and":[75,113],"seamlessly":[76],"integrate":[77],"features":[79],"into":[80],"speech":[82],"separation":[83],"model.":[84],"Experiments":[85],"are":[86],"conducted":[87],"on":[88,123],"two-speaker":[90],"dataset":[91],"(WSJ0-mix2)":[92],"widely":[95],"used":[96],"The":[100],"systematic":[101],"evaluation":[102],"shows":[103],"that":[104],"proposed":[106],"method":[107],"significantly":[108],"outperforms":[109],"previous":[111],"methods":[112],"achieves":[114],"signal-to-distortion":[116],"ratio":[117],"(SDR)":[118],"improvement":[119],"11.3":[121],"dB":[122],"unprocessed":[125],"mixture.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}