{"id":"https://openalex.org/W2166377810","doi":"https://doi.org/10.1109/icassp.2009.4960394","title":"Role of head pose estimation in speech acquisition from distant microphones","display_name":"Role of head pose estimation in speech acquisition from distant microphones","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2166377810","doi":"https://doi.org/10.1109/icassp.2009.4960394","mag":"2166377810"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5006058785","display_name":"Shankar T. Shivappa","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shankar T. Shivappa","raw_affiliation_strings":["Department of Electrical and Computer Engineering, UNiversity of California, San Diego, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, UNiversity of California, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108088237","display_name":"Bhaskar D. Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhaskar D. Rao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, UNiversity of California, San Diego, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, UNiversity of California, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068831718","display_name":"Mohan M. Trivedi","orcid":"https://orcid.org/0000-0002-0937-6771"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohan M. Trivedi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, UNiversity of California, San Diego, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, UNiversity of California, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006058785"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":2.4976,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89714172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3557","last_page":"3560"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.79610276222229},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7887513637542725},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7583950757980347},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6941574811935425},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.587531328201294},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5828256607055664},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5408928394317627},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.49748900532722473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.481479287147522},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4649331271648407},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4055561125278473},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.062073975801467896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79610276222229},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7887513637542725},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7583950757980347},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6941574811935425},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.587531328201294},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5828256607055664},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5408928394317627},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.49748900532722473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.481479287147522},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4649331271648407},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4055561125278473},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.062073975801467896},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.160.3158","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.160.3158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cvrr.ucsd.edu/publications/2009/shivappa_ICASSP09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2017262259","https://openalex.org/W2054077254","https://openalex.org/W2061390283","https://openalex.org/W2094570750","https://openalex.org/W2146053319","https://openalex.org/W2149382413","https://openalex.org/W2161947961","https://openalex.org/W2172220459","https://openalex.org/W4249052411"],"related_works":["https://openalex.org/W2896203542","https://openalex.org/W201299990","https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W4214946933","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W3004719695","https://openalex.org/W2120442551","https://openalex.org/W2769861442"],"abstract_inverted_index":{"Reverberant":[0],"environments":[1],"pose":[2,70,107],"a":[3,92],"challenge":[4],"to":[5,53,89],"speech":[6,77,85],"acquisition":[7,78],"from":[8,79],"distant":[9,80],"microphones.":[10,81],"Approaches":[11],"using":[12,22,67],"microphone":[13,95],"arrays":[14],"have":[15],"met":[16],"with":[17],"limited":[18],"success.":[19],"Recent":[20],"research":[21],"audio-visual":[23],"sensors":[24],"for":[25,72,104],"tasks":[26],"such":[27],"as":[28],"speaker":[29],"localization":[30],"has":[31],"shown":[32],"improvement":[33],"over":[34],"traditional":[35],"audio-only":[36],"approaches.":[37],"Using":[38],"computer":[39],"vision":[40],"techniques":[41],"we":[42,62],"can":[43],"estimate":[44],"the":[45,48,54,57,64,68,99],"orientation":[46],"of":[47,56,66,91],"speaker's":[49],"head":[50,69,106],"in":[51,84,109],"addition":[52],"location":[55],"speaker.":[58],"In":[59],"this":[60],"paper":[61],"study":[63],"utility":[65],"information":[71,108],"effective":[73],"beamforming":[74,110],"and":[75,98],"clean":[76],"The":[82],"improvements":[83],"recognition":[86],"accuracy":[87],"relative":[88],"that":[90],"close":[93],"talking":[94],"are":[96],"presented":[97],"results":[100],"provide":[101],"sufficient":[102],"motivation":[103],"incorporating":[105],"techniques.":[111]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}