{"id":"https://openalex.org/W3016215840","doi":"https://doi.org/10.1109/icassp40776.2020.9054239","title":"DNN-based Mask Estimation Integrating Spectral and Spatial Features for Robust Beamforming","display_name":"DNN-based Mask Estimation Integrating Spectral and Spatial Features for Robust Beamforming","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016215840","doi":"https://doi.org/10.1109/icassp40776.2020.9054239","mag":"3016215840"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054239","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":"article","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/A5086408501","display_name":"Chengyun Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengyun Deng","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061863093","display_name":"Hui Song","orcid":"https://orcid.org/0000-0002-0458-5136"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Song","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388333","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0003-4299-1511"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086086079","display_name":"Yongtao Sha","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongtao Sha","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangang Li","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086408501"],"corresponding_institution_ids":["https://openalex.org/I4401726870"],"apc_list":null,"apc_paid":null,"fwci":1.0607,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76168532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4647","last_page":"4651"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10931","display_name":"Direction-of-Arrival Estimation Techniques","score":0.9901000261306763,"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/beamforming","display_name":"Beamforming","score":0.7886810898780823},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.7097507119178772},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7032687664031982},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47550803422927856},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41844046115875244},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4113050699234009},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.401431143283844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3087586462497711},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.20899063348770142},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20826271176338196},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13725093007087708},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06503254175186157}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7886810898780823},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.7097507119178772},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7032687664031982},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47550803422927856},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41844046115875244},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4113050699234009},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.401431143283844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3087586462497711},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.20899063348770142},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20826271176338196},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13725093007087708},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06503254175186157}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054239","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W123936940","https://openalex.org/W2016100027","https://openalex.org/W2058079016","https://openalex.org/W2158143227","https://openalex.org/W2166458192","https://openalex.org/W2289394825","https://openalex.org/W2290075840","https://openalex.org/W2398042854","https://openalex.org/W2412956798","https://openalex.org/W2702006285","https://openalex.org/W2718052359","https://openalex.org/W2747798993","https://openalex.org/W2890489755","https://openalex.org/W2937581095","https://openalex.org/W2962892438"],"related_works":["https://openalex.org/W2963170046","https://openalex.org/W2376244802","https://openalex.org/W1971477554","https://openalex.org/W818226659","https://openalex.org/W2923631784","https://openalex.org/W4311414679","https://openalex.org/W2567141277","https://openalex.org/W2130785056","https://openalex.org/W2132841313","https://openalex.org/W2727286692"],"abstract_inverted_index":{"Spectral":[0],"mask":[1,19,40,56,75,115],"based":[2,57],"beamforming":[3,58],"has":[4,42],"showed":[5],"competitive":[6],"performance":[7,107],"on":[8,21,101],"multi-channel":[9],"speech":[10,34],"enhancement":[11],"in":[12,82,118],"recent":[13],"years.":[14],"However,":[15],"such":[16],"methods":[17],"apply":[18],"estimation":[20,41,116],"each":[22],"channel":[23,86],"and":[24,35,67],"ensemble":[25],"the":[26,105,109],"masks":[27,78],"from":[28],"multiple":[29],"channels":[30],"into":[31],"one":[32],"for":[33,60,88],"noise":[36],"covariance":[37],"estimation.":[38,76],"Spectral-spatial":[39],"not":[43,80],"been":[44],"well":[45],"extended":[46,96],"yet.":[47],"In":[48],"this":[49,92],"paper,":[50],"we":[51],"propose":[52],"a":[53],"novel":[54],"spectral-spatial":[55],"method":[59,94,111],"two-channel":[61,93],"noisy":[62],"signals,":[63],"where":[64],"spectral":[65,114],"amplitude":[66],"cross-channel":[68],"spatial":[69],"features":[70],"are":[71,79],"integrated":[72],"to":[73,84,97],"improve":[74],"Multi-channel":[77],"merged":[81],"order":[83],"preserve":[85],"characteristics":[87],"robust":[89],"beamforming.":[90],"Furthermore,":[91],"is":[95],"six-channel":[98],"scenario.":[99],"Experiments":[100],"CHiME-3":[102],"evaluation":[103],"confirm":[104],"superior":[106],"of":[108,120],"proposed":[110],"over":[112],"two":[113],"approaches":[117],"terms":[119],"word":[121],"error":[122],"rates":[123],"(WER)":[124],"improvement.":[125]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}