{"id":"https://openalex.org/W2891984996","doi":"https://doi.org/10.1109/icassp.2018.8461816","title":"On Spatial Features for Supervised Speech Separation and its Application to Beamforming and Robust ASR","display_name":"On Spatial Features for Supervised Speech Separation and its Application to Beamforming and Robust ASR","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891984996","doi":"https://doi.org/10.1109/icassp.2018.8461816","mag":"2891984996"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461816","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":"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/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101607498"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":4.9543,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.96220911,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5709","last_page":"5713"},"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":0.9983999729156494,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7955183386802673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7524293661117554},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6127035021781921},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5920888185501099},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5766958594322205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5759369730949402},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5009713172912598},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4773152768611908},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4465496242046356},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44481417536735535},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.43470877408981323},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4324151575565338},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13598236441612244},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10348939895629883}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7955183386802673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7524293661117554},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6127035021781921},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5920888185501099},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5766958594322205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5759369730949402},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5009713172912598},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4773152768611908},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4465496242046356},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44481417536735535},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.43470877408981323},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4324151575565338},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13598236441612244},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10348939895629883},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461816","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":42,"referenced_works":["https://openalex.org/W1525788760","https://openalex.org/W1544785557","https://openalex.org/W1992879732","https://openalex.org/W2057200980","https://openalex.org/W2069681747","https://openalex.org/W2148613904","https://openalex.org/W2168379380","https://openalex.org/W2219253687","https://openalex.org/W2288645994","https://openalex.org/W2289480995","https://openalex.org/W2289731793","https://openalex.org/W2296167893","https://openalex.org/W2337992322","https://openalex.org/W2397728357","https://openalex.org/W2401485387","https://openalex.org/W2510074933","https://openalex.org/W2517616541","https://openalex.org/W2559809918","https://openalex.org/W2568308529","https://openalex.org/W2599685671","https://openalex.org/W2635471793","https://openalex.org/W2641129314","https://openalex.org/W2701869962","https://openalex.org/W2714487941","https://openalex.org/W2718052359","https://openalex.org/W2749337587","https://openalex.org/W2891219041","https://openalex.org/W2962866211","https://openalex.org/W2966212213","https://openalex.org/W3103256658","https://openalex.org/W4249052411","https://openalex.org/W6631382614","https://openalex.org/W6632646963","https://openalex.org/W6696273679","https://openalex.org/W6712476441","https://openalex.org/W6739427221","https://openalex.org/W6739504299","https://openalex.org/W6739973813","https://openalex.org/W6740199906","https://openalex.org/W6740340063","https://openalex.org/W6754279408","https://openalex.org/W6766475400"],"related_works":["https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2885833775","https://openalex.org/W2205176333","https://openalex.org/W2126149694","https://openalex.org/W1963911409"],"abstract_inverted_index":{"This":[0],"study":[1],"integrates":[2],"complementary":[3],"spectral":[4],"and":[5,15,19,37,47,64,77,83],"spatial":[6,78],"information":[7],"to":[8,33,52,56,73],"elevate":[9],"deep":[10,29],"learning":[11],"based":[12],"time-frequency":[13],"masking":[14],"acoustic":[16],"beamforming.":[17],"Coherence":[18],"directional":[20,39,48],"features":[21,27,49],"are":[22,50,70],"designed":[23,51],"as":[24],"additional":[25],"input":[26],"for":[28,81],"neural":[30],"network":[31],"training":[32],"remove":[34],"diffuse":[35,46],"noise":[36],"other":[38],"interferences":[40],"pervasive":[41],"in":[42],"real-world":[43],"recordings.":[44],"The":[45,67],"be":[53],"relatively":[54],"invariant":[55],"the":[57,88,92,95],"underlying":[58],"target":[59],"direction,":[60],"number":[61],"of":[62,94],"microphones":[63],"microphone":[65],"geometry.":[66],"estimated":[68],"masks":[69],"then":[71],"utilized":[72],"compute":[74],"steering":[75],"vectors":[76],"covariance":[79],"matrices":[80],"beamforming":[82],"robust":[84],"ASR.":[85],"Experiments":[86],"on":[87],"CHiME-4":[89],"dataset":[90],"demonstrate":[91],"effectiveness":[93],"proposed":[96],"approach.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}