{"id":"https://openalex.org/W3158075127","doi":"https://doi.org/10.21437/interspeech.2021-1378","title":"AvaTr: One-Shot Speaker Extraction with Transformers","display_name":"AvaTr: One-Shot Speaker Extraction with Transformers","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3158075127","doi":"https://doi.org/10.21437/interspeech.2021-1378","mag":"3158075127"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1378","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.00609","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032445207","display_name":"Shell Xu Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shell Xu Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052255635","display_name":"Rifat Arefin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md. Rifat Arefin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085659980","display_name":"Viet-Nhat Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viet-Nhat Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061302160","display_name":"Alish Dipani","orcid":"https://orcid.org/0000-0002-9201-1369"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alish Dipani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057055829","display_name":"Xaq Pitkow","orcid":"https://orcid.org/0000-0001-6376-329X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xaq Pitkow","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054637446","display_name":"Andreas S. Tolias","orcid":"https://orcid.org/0000-0002-4305-6376"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Savas Tolias","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04224186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3510","last_page":"3514"},"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":0.9998999834060669,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7945345640182495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6990973949432373},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6342263221740723},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6024768948554993},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4623827338218689},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45020121335983276},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4232284724712372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38093841075897217},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3734312653541565},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26780688762664795},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1364007592201233},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10512953996658325}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7945345640182495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6990973949432373},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6342263221740723},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6024768948554993},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4623827338218689},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45020121335983276},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4232284724712372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38093841075897217},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3734312653541565},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26780688762664795},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1364007592201233},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10512953996658325},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1378","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.00609","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.00609","pdf_url":"https://arxiv.org/pdf/2105.00609","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:3158075127","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2105.00609","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2105.00609","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.00609","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.00609","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.00609","pdf_url":"https://arxiv.org/pdf/2105.00609","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3158075127.pdf","grobid_xml":"https://content.openalex.org/works/W3158075127.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1621710783","https://openalex.org/W1773016195","https://openalex.org/W1902237438","https://openalex.org/W1964797398","https://openalex.org/W1987292658","https://openalex.org/W2013068849","https://openalex.org/W2052666245","https://openalex.org/W2078528584","https://openalex.org/W2082183045","https://openalex.org/W2149985837","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2593116425","https://openalex.org/W2899771611","https://openalex.org/W2906042495","https://openalex.org/W2952218014","https://openalex.org/W2963341924","https://openalex.org/W2963403868","https://openalex.org/W2963828919","https://openalex.org/W2963921132","https://openalex.org/W2964121744","https://openalex.org/W2972541922","https://openalex.org/W2973062255","https://openalex.org/W3030163527","https://openalex.org/W3045904949","https://openalex.org/W3094502228","https://openalex.org/W3095339269","https://openalex.org/W3099782249","https://openalex.org/W3103434036","https://openalex.org/W3120907516","https://openalex.org/W3163464523"],"related_works":["https://openalex.org/W86526702","https://openalex.org/W2897485352","https://openalex.org/W2104779640","https://openalex.org/W131597382","https://openalex.org/W3038110917","https://openalex.org/W2467310271","https://openalex.org/W2114499274","https://openalex.org/W1531976713","https://openalex.org/W3208262919","https://openalex.org/W299254312","https://openalex.org/W3171805418","https://openalex.org/W1597082751","https://openalex.org/W2087349971","https://openalex.org/W1621367523","https://openalex.org/W1560044228","https://openalex.org/W329768343","https://openalex.org/W2427348892","https://openalex.org/W1991995173","https://openalex.org/W3123318516","https://openalex.org/W1591454599"],"abstract_inverted_index":{"To":[0],"extract":[1],"the":[2,23,30,35,42,46,68,79,90,110],"voice":[3,80],"of":[4,13,25,48,56,67,88,117],"a":[5,11,54,62],"target":[6,43],"speaker":[7,44,111],"when":[8],"mixed":[9],"with":[10,39],"variety":[12],"other":[14],"sounds,":[15],"such":[16],"as":[17,53],"white":[18],"and":[19],"ambient":[20],"noises":[21],"or":[22,50,103],"voices":[24,52],"interfering":[26],"speakers,":[27],"we":[28,73],"extend":[29],"Transformer":[31,83],"network":[32],"to":[33,41,77],"attend":[34],"most":[36],"relevant":[37],"information":[38],"respect":[40],"given":[45],"characteristics":[47,81],"his":[49],"her":[51],"form":[55],"contextual":[57],"information.":[58],"The":[59],"idea":[60],"has":[61],"natural":[63],"interpretation":[64],"in":[65,82],"terms":[66],"selective":[69],"attention":[70],"theory.":[71],"Specifically,":[72],"propose":[74],"two":[75],"models":[76,97,108],"incorporate":[78],"based":[84],"on":[85,101,109],"different":[86],"insights":[87],"where":[89],"feature":[91],"selection":[92],"should":[93],"take":[94],"place.":[95],"Both":[96],"yield":[98],"excellent":[99],"performance,":[100],"par":[102],"better":[104],"than":[105],"published":[106],"state-of-the-art":[107],"extraction":[112],"task,":[113],"including":[114],"separating":[115],"speech":[116],"novel":[118],"speakers":[119],"not":[120],"seen":[121],"during":[122],"training.":[123]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}