{"id":"https://openalex.org/W2891609809","doi":"https://doi.org/10.1109/icassp.2018.8461533","title":"Optimization of Speaker-Aware Multichannel Speech Extraction with ASR Criterion","display_name":"Optimization of Speaker-Aware Multichannel Speech Extraction with ASR Criterion","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891609809","doi":"https://doi.org/10.1109/icassp.2018.8461533","mag":"2891609809"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461533","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/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/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 Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"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 Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101768343","display_name":"Takuya Higuchi","orcid":"https://orcid.org/0000-0002-0361-7132"},"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":"Takuya Higuchi","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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 Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"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":"Jan Cernocky","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"]}]}],"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":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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":0.9991999864578247,"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":0.996999979019165,"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":0.7852267026901245},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7763673663139343},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.54189133644104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36651137471199036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852267026901245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7763673663139343},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.54189133644104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36651137471199036}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461533","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320315323","display_name":"Technology Agency of the Czech Republic","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1548802052","https://openalex.org/W1987906574","https://openalex.org/W2031583051","https://openalex.org/W2043216213","https://openalex.org/W2129171989","https://openalex.org/W2130361043","https://openalex.org/W2144763279","https://openalex.org/W2158143227","https://openalex.org/W2221409856","https://openalex.org/W2289394825","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/W2568678469","https://openalex.org/W2589857635","https://openalex.org/W2591810467","https://openalex.org/W2640112133","https://openalex.org/W2699350432","https://openalex.org/W2714487941","https://openalex.org/W2749337587","https://openalex.org/W2749510669","https://openalex.org/W2750380122","https://openalex.org/W2750446090","https://openalex.org/W2787692317","https://openalex.org/W2963773971","https://openalex.org/W2963843276","https://openalex.org/W4205778870","https://openalex.org/W6741874079","https://openalex.org/W6743406453","https://openalex.org/W6748206876"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,22,51,55,66,70,75,85,115,121,125,129,137,141,149,155],"problem":[4],"of":[5,134,148],"recognizing":[6],"speech":[7,92,95,108],"corrupted":[8],"by":[9,35,145],"overlapping":[10],"speakers":[11],"in":[12,74],"a":[13,18,26,36,94,106],"multichannel":[14],"setting.":[15],"To":[16],"extract":[17,84],"target":[19,56,71],"speaker":[20,57,86,142],"from":[21,61],"mixture,":[23],"we":[24,49,99],"use":[25,147],"neural":[27,37,52],"network":[28,38,53,67],"based":[29],"beamformer":[30],"which":[31],"uses":[32],"masks":[33,156],"estimated":[34],"to":[39,68,82,93,153],"compute":[40],"statistically":[41],"optimal":[42],"spatial":[43],"filters.":[44],"Following":[45],"our":[46],"previous":[47,76],"work,":[48,77],"inform":[50],"about":[54],"using":[58],"information":[59,135],"extracted":[60],"an":[62],"adaptation":[63],"utterance\u2019":[64],"enabling":[65],"track":[69],"speaker.":[72],"While":[73],"this":[78],"method":[79],"was":[80],"used":[81,157],"separately":[83],"and":[87,118,140],"then":[88],"pass":[89],"such":[90],"preprocessed":[91],"recognition":[96,109],"system,":[97,144],"here":[98],"explore":[100],"training":[101,119],"both":[102],"systems":[103,117],"jointly":[104],"with":[105],"common":[107],"criterion.":[110],"We":[111],"show":[112],"that":[113],"integrating":[114],"two":[116],"for":[120,158],"final":[122],"objective":[123],"improves":[124],"performance.":[126],"In":[127],"addition,":[128],"integration":[130],"enables":[131],"further":[132],"sharing":[133],"between":[136],"acoustic":[138],"model":[139],"extraction":[143],"making":[146],"predicted":[150],"HMM-state":[151],"posteriors":[152],"refine":[154],"beamforming.":[159]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}