{"id":"https://openalex.org/W2991648769","doi":"https://doi.org/10.1109/icassp40776.2020.9054550","title":"Unsupervised Neural Mask Estimator for Generalized Eigen-Value Beamforming Based Asr","display_name":"Unsupervised Neural Mask Estimator for Generalized Eigen-Value Beamforming Based Asr","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2991648769","doi":"https://doi.org/10.1109/icassp40776.2020.9054550","mag":"2991648769"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054550","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.12617","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100786052","display_name":"Rohit Kumar","orcid":"https://orcid.org/0000-0001-5594-0129"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rohit Kumar","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns (LEAP) lab, Indian Institute of Science, Bangalore","Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) lab,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) lab, Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) lab,Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050183512","display_name":"Anirudh Sreeram","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anirudh Sreeram","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns (LEAP) lab, Indian Institute of Science, Bangalore","Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) lab,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) lab, Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) lab,Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022033905","display_name":"Anurenjan Purushothaman","orcid":"https://orcid.org/0000-0001-6779-4122"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anurenjan Purushothaman","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns (LEAP) lab, Indian Institute of Science, Bangalore","Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) lab,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) lab, Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) lab,Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns (LEAP) lab, Indian Institute of Science, Bangalore","Indian Institute of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) lab, Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Indian Institute of Science","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7494","last_page":"7498"},"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":0.9991000294685364,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7963716983795166},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7775812149047852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743159294128418},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.6542614102363586},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.572085976600647},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5593946576118469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47957247495651245},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4778023362159729},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45825353264808655},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4153686761856079},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4107632040977478},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17572569847106934},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13746094703674316},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.071198970079422},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.062484532594680786}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7963716983795166},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7775812149047852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743159294128418},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6542614102363586},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.572085976600647},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5593946576118469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47957247495651245},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4778023362159729},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45825353264808655},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4153686761856079},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4107632040977478},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17572569847106934},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13746094703674316},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.071198970079422},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.062484532594680786},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054550","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"},{"id":"pmh:oai:eprints.iisc.ac.in:66773","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:arXiv.org:1911.12617","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.12617","pdf_url":"https://arxiv.org/pdf/1911.12617","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"raw_type":"text"},{"id":"mag:2991648769","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.12617","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.1911.12617","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.12617","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},{"id":"doi:10.17023/ydcv-f504","is_oa":true,"landing_page_url":"https://doi.org/10.17023/ydcv-f504","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.12617","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.12617","pdf_url":"https://arxiv.org/pdf/1911.12617","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2991648769.pdf","grobid_xml":"https://content.openalex.org/works/W2991648769.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1524333225","https://openalex.org/W1989314204","https://openalex.org/W2060108923","https://openalex.org/W2148613904","https://openalex.org/W2158143227","https://openalex.org/W2162654459","https://openalex.org/W2164502538","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2702006285","https://openalex.org/W2796868621","https://openalex.org/W2899515918","https://openalex.org/W2930641205","https://openalex.org/W2933708090","https://openalex.org/W2981555996","https://openalex.org/W6607333740","https://openalex.org/W6631362777","https://openalex.org/W6769136941"],"related_works":["https://openalex.org/W3015870855","https://openalex.org/W2787069756","https://openalex.org/W2995085615","https://openalex.org/W2963504687","https://openalex.org/W3000191574","https://openalex.org/W2891759647","https://openalex.org/W2923728956","https://openalex.org/W3109458322","https://openalex.org/W2107426051","https://openalex.org/W2900091068","https://openalex.org/W2057826000","https://openalex.org/W3111246190","https://openalex.org/W2035576074","https://openalex.org/W2766672686","https://openalex.org/W2750380122","https://openalex.org/W2939497224","https://openalex.org/W2922439870","https://openalex.org/W3131332223","https://openalex.org/W161118803","https://openalex.org/W2915844545"],"abstract_inverted_index":{"The":[0,60,132],"state-of-art":[1],"methods":[2],"for":[3,55,135],"acoustic":[4],"beamforming":[5,67],"in":[6,101,114],"multi-channel":[7,69],"ASR":[8,133],"are":[9,26,142],"based":[10,62],"on":[11,63,89,109,150,155,163],"a":[12,29,102,146],"neural":[13],"mask":[14,58,76,160],"estimator":[15],"that":[16,141],"predicts":[17],"the":[18,48,57,74,81,115,121,126,129,136,158,164],"presence":[19],"of":[20,32,50,92,128],"speech":[21,94],"and":[22,34,66,111,154],"noise.":[23],"These":[24],"models":[25,61],"trained":[27,149,162],"using":[28,68],"paired":[30],"corpus":[31,117,124],"clean":[33,53],"noisy":[35,93,110],"recordings":[36,54,91],"(teacher":[37],"model).":[38],"In":[39,78],"this":[40,79],"paper,":[41],"we":[42],"attempt":[43],"to":[44],"move":[45],"away":[46],"from":[47],"requirements":[49],"having":[51],"supervised":[52],"training":[56,83],"estimator.":[59],"signal":[64],"enhancement":[65],"linear":[70],"prediction":[71],"serve":[72],"as":[73,118,120],"required":[75],"estimate.":[77],"way,":[80],"model":[82,148],"can":[84],"also":[85],"be":[86],"carried":[87],"out":[88],"real":[90],"rather":[95],"than":[96,145],"simulated":[97],"ones":[98],"alone":[99],"done":[100],"typical":[103],"teacher":[104,147],"model.":[105],"Several":[106],"experiments":[107],"performed":[108],"reverberant":[112],"environments":[113],"CHiME-3":[116],"well":[119],"REVERB":[122],"challenge":[123],"highlight":[125],"effectiveness":[127],"proposed":[130,137],"approach.":[131],"results":[134],"approach":[138],"provide":[139],"performances":[140],"significantly":[143],"better":[144],"an":[151],"out-of-domain":[152],"dataset":[153],"par":[156],"with":[157],"oracle":[159],"estimators":[161],"in-domain":[165],"dataset.":[166]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}