{"id":"https://openalex.org/W2031232012","doi":"https://doi.org/10.1109/iscslp.2014.6936698","title":"A robust high resolution speaker DOA estimation under reverberant environment","display_name":"A robust high resolution speaker DOA estimation under reverberant environment","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2031232012","doi":"https://doi.org/10.1109/iscslp.2014.6936698","mag":"2031232012"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5026759570","display_name":"Yifan Guo","orcid":"https://orcid.org/0000-0002-9700-5005"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Guo","raw_affiliation_strings":["ADSPLAB/ELIP, School of Electronic and Computer Engineering, Peking University, Shenzhen 518055, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADSPLAB/ELIP, School of Electronic and Computer Engineering, Peking University, Shenzhen 518055, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102747882","display_name":"Y. X. Zou","orcid":"https://orcid.org/0009-0006-7335-7272"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Y.X. Zou","raw_affiliation_strings":["ADSPLAB/ELIP, School of Electronic and Computer Engineering, Peking University, Shenzhen 518055, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADSPLAB/ELIP, School of Electronic and Computer Engineering, Peking University, Shenzhen 518055, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100673739","display_name":"Yongqing Wang","orcid":"https://orcid.org/0000-0003-1164-0137"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqing Wang","raw_affiliation_strings":["ADSPLAB/ELIP, School of Electronic and Computer Engineering, Peking University, Shenzhen 518055, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADSPLAB/ELIP, School of Electronic and Computer Engineering, Peking University, Shenzhen 518055, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"400","last_page":"400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.9986000061035156,"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/T13717","display_name":"Advanced Algorithms and Applications","score":0.96670001745224,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9513999819755554,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.8315681219100952},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7049113512039185},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.6643725633621216},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5711878538131714},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.544603168964386},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.437860369682312},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4330875277519226},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3470993638038635},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3425571322441101},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.33947619795799255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29225096106529236},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11410015821456909},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0734717845916748},{"id":"https://openalex.org/keywords/antenna","display_name":"Antenna (radio)","score":0.07208061218261719}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8315681219100952},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7049113512039185},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.6643725633621216},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5711878538131714},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.544603168964386},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.437860369682312},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4330875277519226},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3470993638038635},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3425571322441101},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.33947619795799255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29225096106529236},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11410015821456909},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0734717845916748},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.07208061218261719},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","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":0,"referenced_works":[],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2331622705","https://openalex.org/W2009811519","https://openalex.org/W3166640618","https://openalex.org/W4308823735","https://openalex.org/W2787240389"],"abstract_inverted_index":{"Summary":[0],"form":[1],"given.":[2],"Direction":[3],"of":[4,8,21,47,52,58,105,116,151,167,199],"arrival":[5],"(DOA)":[6],"estimation":[7,34,118,125,144,187,198],"the":[9,18,22,53,61,73,76,81,90,103,110,113,122,141,155,163,168,194,203],"spatial":[10,42],"speech":[11,106],"source":[12,169,196],"is":[13,65,119,127,146,157,165],"a":[14,28,85,179],"key":[15],"technique":[16],"in":[17,60,202],"audition":[19],"system":[20],"service":[23,200],"robot.":[24],"This":[25],"paper":[26,91],"investigates":[27],"robust":[29,86],"high":[30,94,123],"resolution":[31],"speaker":[32,87,195],"DOA":[33,88,117,124,143,186,197],"based":[35],"on":[36],"acoustic":[37],"vector":[38,79],"sensor":[39],"(AVS)":[40],"and":[41,69,80,108,121,135,171,182],"sparsity":[43],"representation":[44],"(SSR)":[45],"theory":[46],"source.":[48],"The":[49,129],"approximate":[50],"model":[51,115],"inter-sensor":[54],"data":[55],"ratio":[56,97],"(ISDR)":[57],"AVS":[59,77,177],"time-frequency":[62],"(TF)":[63],"domain":[64],"derived":[66],"with":[67],"reverberation":[68,134],"noise,":[70],"which":[71],"determines":[72],"relationship":[74],"between":[75],"manifold":[78],"ISDR.":[82],"To":[83],"obtain":[84],"estimation,":[89],"gets":[92],"reliable":[93],"local":[95],"signal-to-noise":[96],"(HLSNR)":[98],"TF":[99],"points":[100],"by":[101],"extracting":[102],"pitch":[104],"signal":[107],"fitting":[109],"curve.":[111],"Then":[112],"SSR":[114],"formulated":[120],"accuracy":[126],"achieved.":[128],"experimental":[130],"results":[131],"under":[132],"different":[133],"additive":[136],"noise":[137],"conditions":[138],"show":[139],"that":[140],"proposed":[142],"method":[145,164],"able":[147],"to":[148,160,174],"achieve":[149],"RMSE":[150],"below":[152],"0.5\u00b0":[153],"when":[154],"SNR":[156],"from":[158],"5dB":[159],"30dB.":[161],"Moreover,":[162],"independent":[166],"frequencies":[170],"not":[172],"sensitive":[173],"reverberation.":[175],"Since":[176],"has":[178],"small":[180],"size":[181],"few":[183],"sensors,":[184],"this":[185],"approach":[188],"will":[189],"probably":[190],"provide":[191],"solutions":[192],"for":[193],"robots":[201],"natural":[204],"home":[205],"environment.":[206]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}