{"id":"https://openalex.org/W2402058645","doi":"https://doi.org/10.1109/icassp.2016.7471711","title":"Binaural speaker localization and separation based on a joint ITD/ILD model and head movement tracking","display_name":"Binaural speaker localization and separation based on a joint ITD/ILD model and head movement tracking","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2402058645","doi":"https://doi.org/10.1109/icassp.2016.7471711","mag":"2402058645"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5053479846","display_name":"Mehdi Zohourian","orcid":"https://orcid.org/0000-0003-0644-7527"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mehdi Zohourian","raw_affiliation_strings":["Institute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064880163","display_name":"Rainer Martin","orcid":"https://orcid.org/0000-0002-9587-4215"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rainer Martin","raw_affiliation_strings":["Institute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053479846"],"corresponding_institution_ids":["https://openalex.org/I904495901"],"apc_list":null,"apc_paid":null,"fwci":3.5709,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93676609,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"430","last_page":"434"},"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":0.9991999864578247,"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":0.9983000159263611,"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/binaural-recording","display_name":"Binaural recording","score":0.785822331905365},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6828978061676025},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.6680635809898376},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6080085039138794},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5685741901397705},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5152773857116699},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.49237215518951416},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.49112674593925476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4142225384712219},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34405767917633057},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21414044499397278},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11961624026298523},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07293552160263062}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.785822331905365},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6828978061676025},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.6680635809898376},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6080085039138794},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5685741901397705},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5152773857116699},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.49237215518951416},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.49112674593925476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4142225384712219},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34405767917633057},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21414044499397278},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11961624026298523},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07293552160263062},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7471711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W189850294","https://openalex.org/W1505940748","https://openalex.org/W1517393545","https://openalex.org/W1520758678","https://openalex.org/W1549884461","https://openalex.org/W1552314771","https://openalex.org/W1555217905","https://openalex.org/W1581848821","https://openalex.org/W1931312565","https://openalex.org/W1986423218","https://openalex.org/W2009649672","https://openalex.org/W2032047731","https://openalex.org/W2034593061","https://openalex.org/W2049633694","https://openalex.org/W2071387240","https://openalex.org/W2075098731","https://openalex.org/W2101609516","https://openalex.org/W2113250153","https://openalex.org/W2125697172","https://openalex.org/W2125768106","https://openalex.org/W2140889287","https://openalex.org/W2141998673","https://openalex.org/W2153248083","https://openalex.org/W2155323221","https://openalex.org/W2166682639","https://openalex.org/W4214498238"],"related_works":["https://openalex.org/W2766995619","https://openalex.org/W4224270619","https://openalex.org/W2168148781","https://openalex.org/W1991848873","https://openalex.org/W2026165661","https://openalex.org/W2099651033","https://openalex.org/W2783525307","https://openalex.org/W2593008828","https://openalex.org/W2155323221","https://openalex.org/W2076135780"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"a":[5,51],"novel":[6],"algorithm":[7,84,99],"to":[8,22,35,72,116],"localize":[9,102],"and":[10,48,89,135],"separate":[11],"simultaneous":[12],"speakers":[13,104],"using":[14,85],"hearing":[15,31],"aids":[16,32],"when":[17],"the":[18,27,42,46,106,118,123,129,132,137],"head":[19,68],"is":[20,90],"subject":[21],"rotational":[23],"movement.":[24],"Most":[25],"of":[26,45,108,131,139],"algorithms":[28],"used":[29,115],"in":[30,41,54,105],"are":[33,40,114],"able":[34],"extract":[36],"target":[37],"signals":[38],"that":[39],"look":[43],"direction":[44],"user":[47],"suffer":[49],"from":[50,58],"reduced":[52],"performance":[53,130],"localizing":[55],"sounds":[56],"received":[57],"other":[59],"directions.":[60],"Moreover,":[61],"head-shadowing":[62],"as":[63,65],"well":[64],"variations":[66],"like":[67],"movements":[69],"may":[70],"lead":[71],"significant":[73],"distortions.":[74],"The":[75,97,110],"proposed":[76],"binaural":[77],"GSC":[78,119],"beamformer":[79,120],"includes":[80],"an":[81,86,93],"MMSE-based":[82],"localization":[83,98],"ITD/ILD":[87],"model":[88],"controlled":[91],"by":[92],"inertial":[94],"measurement":[95],"unit.":[96],"can":[100],"effectively":[101],"multiple":[103],"presence":[107],"reverberation.":[109],"estimated":[111],"source":[112],"locations":[113],"adapt":[117],"which":[121],"extracts":[122],"desired":[124],"speaker.":[125],"Experimental":[126],"results":[127],"demonstrate":[128],"new":[133],"system":[134],"especially":[136],"benefits":[138],"ILD":[140],"information.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":4}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}
