{"id":"https://openalex.org/W2891833136","doi":"https://doi.org/10.1109/icassp.2018.8462661","title":"Single Channel Target Speaker Extraction and Recognition with Speaker Beam","display_name":"Single Channel Target Speaker Extraction and Recognition with Speaker Beam","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891833136","doi":"https://doi.org/10.1109/icassp.2018.8462661","mag":"2891833136"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067790073","display_name":"Kate\u0159ina \u017dmol\u00edkov\u00e1","orcid":"https://orcid.org/0000-0003-4438-8580"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Katerina Zmolikova","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":202,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5554","last_page":"5558"},"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":0.9997000098228455,"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":0.9988999962806702,"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/speaker-recognition","display_name":"Speaker recognition","score":0.7493350505828857},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6832923889160156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6798252463340759},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5406858325004578},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5174468159675598},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.41677623987197876},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13623762130737305}],"concepts":[{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7493350505828857},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6832923889160156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6798252463340759},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5406858325004578},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5174468159675598},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.41677623987197876},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13623762130737305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1571447047","https://openalex.org/W1992475611","https://openalex.org/W2057826000","https://openalex.org/W2079362249","https://openalex.org/W2079623482","https://openalex.org/W2144763279","https://openalex.org/W2221409856","https://openalex.org/W2397725648","https://openalex.org/W2398042854","https://openalex.org/W2398776621","https://openalex.org/W2398972335","https://openalex.org/W2460742184","https://openalex.org/W2517616541","https://openalex.org/W2558649592","https://openalex.org/W2589857635","https://openalex.org/W2640112133","https://openalex.org/W2749510669","https://openalex.org/W2749659773","https://openalex.org/W2766901645","https://openalex.org/W2787692317","https://openalex.org/W2962728945","https://openalex.org/W2962866211","https://openalex.org/W2963843276","https://openalex.org/W3099832538","https://openalex.org/W6648656139","https://openalex.org/W6664675605","https://openalex.org/W6688843265","https://openalex.org/W6712306154","https://openalex.org/W6712524419","https://openalex.org/W6712626118","https://openalex.org/W6730148858","https://openalex.org/W6740059222","https://openalex.org/W6748206876","https://openalex.org/W6765948438","https://openalex.org/W6798498067"],"related_works":["https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2144470400","https://openalex.org/W1516392727","https://openalex.org/W2140022733","https://openalex.org/W2911612049"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,33,60,65,130,178,189,193,204],"problem":[4],"of":[5,10,17,59,62,87],"single":[6,156],"channel":[7,157],"speech":[8,18,85,111,191,194],"recognition":[9,86],"a":[11,15,50,100,113,117,142,170,182],"target":[12,34,114,131,179,190],"speaker":[13,25,35,51,94,115,118,132,139,158,161,171,180,184,206],"in":[14,64],"mixture":[16,195],"signals.":[19],"We":[20,89,200],"propose":[21],"to":[22,36,168,198,217],"exploit":[23],"auxiliary":[24,45,127],"information":[26],"provided":[27],"by":[28],"an":[29,92,214],"adaptation":[30,119,162],"utterance":[31],"from":[32,112,192],"extract":[37],"and":[38,67],"recognize":[39],"only":[40,177],"that":[41,56,68,108,150,175,187,203],"speaker.":[42],"Using":[43],"such":[44,91],"information,":[46],"we":[47,148],"can":[48,69,164,209],"build":[49,169],"extraction":[52,95,140,185,207],"neural":[53],"network":[54,186,208],"(NN)":[55],"is":[57,152],"independent":[58],"number":[61],"sources":[63],"mixture,":[66],"track":[70],"speakers":[71],"across":[72],"different":[73],"utterances,":[74],"which":[75],"are":[76,123],"two":[77],"challenging":[78],"issues":[79],"occurring":[80],"with":[81,213],"conventional":[82],"approaches":[83],"for":[84,138,155],"mixtures.":[88],"call":[90],"informed":[93],"scheme":[96],"\u201cSpeakerBeam\u201d.":[97],"SpeakerBeam":[98,134],"exploits":[99],"recently":[101],"developed":[102],"context":[103],"adaptive":[104,172],"deep":[105],"NN":[106],"(CADNN)":[107],"allows":[109],"tracking":[110],"using":[116,141],"layer,":[120],"whose":[121],"parameters":[122],"adjusted":[124],"depending":[125],"on":[126],"features":[128],"representing":[129],"characteristics.":[133],"was":[135],"previously":[136],"investigated":[137],"microphone":[143],"array.":[144],"In":[145],"this":[146],"paper,":[147],"demonstrate":[149],"it":[151],"also":[153,201],"efficient":[154],"extraction.":[159],"The":[160],"layer":[163],"be":[165,210],"employed":[166],"either":[167],"acoustic":[173,215],"model":[174,216],"recognizes":[176],"or":[181],"mask-based":[183],"extracts":[188],"signal":[196],"prior":[197],"recognition.":[199],"show":[202],"latter":[205],"optimized":[211],"jointly":[212],"further":[218],"improve":[219],"ASR":[220],"performance.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":44},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":30},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}