{"id":"https://openalex.org/W2129697784","doi":"https://doi.org/10.1109/icassp.2009.4960653","title":"A speech fragment approach to localising multiple speakers in reverberant environments","display_name":"A speech fragment approach to localising multiple speakers in reverberant environments","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2129697784","doi":"https://doi.org/10.1109/icassp.2009.4960653","mag":"2129697784"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960653","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/A5045619924","display_name":"Heidi Christensen","orcid":"https://orcid.org/0000-0003-3028-5062"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Heidi Christensen","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, UK","Dept. of Computer Science, University of Sheffield, United Kingdom#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Dept. of Computer Science, University of Sheffield, United Kingdom#TAB#","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067036469","display_name":"Ning Ma","orcid":"https://orcid.org/0000-0002-4112-3109"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ning Ma","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, UK","Dept. of Computer Science, University of Sheffield, United Kingdom#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Dept. of Computer Science, University of Sheffield, United Kingdom#TAB#","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028477651","display_name":"Stuart N. Wrigley","orcid":"https://orcid.org/0000-0002-3689-8292"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stuart N. Wrigley","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, UK","Dept. of Computer Science, University of Sheffield, United Kingdom#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Dept. of Computer Science, University of Sheffield, United Kingdom#TAB#","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074458312","display_name":"Jon Barker","orcid":"https://orcid.org/0000-0002-1684-5660"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jon Barker","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, UK","Dept. of Computer Science, University of Sheffield, United Kingdom#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Dept. of Computer Science, University of Sheffield, United Kingdom#TAB#","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045619924"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":5.3519,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.95934744,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"19","issue":null,"first_page":"4593","last_page":"4596"},"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":0.9991999864578247,"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":0.9991000294685364,"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/binaural-recording","display_name":"Binaural recording","score":0.8895372152328491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6955909132957458},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6874115467071533},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6528840065002441},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6248726844787598},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5958490371704102},{"id":"https://openalex.org/keywords/fragment","display_name":"Fragment (logic)","score":0.5230661034584045},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.47678425908088684},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4683510661125183},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.45192620158195496},{"id":"https://openalex.org/keywords/interaural-time-difference","display_name":"Interaural time difference","score":0.44355711340904236},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1724810004234314},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10589787364006042},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10532316565513611},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0760757327079773}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8895372152328491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955909132957458},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6874115467071533},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6528840065002441},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6248726844787598},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5958490371704102},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.5230661034584045},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.47678425908088684},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4683510661125183},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.45192620158195496},{"id":"https://openalex.org/C103364767","wikidata":"https://www.wikidata.org/wiki/Q1807562","display_name":"Interaural time difference","level":3,"score":0.44355711340904236},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1724810004234314},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10589787364006042},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10532316565513611},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0760757327079773},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960653","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W12005700","https://openalex.org/W1987906574","https://openalex.org/W2025127228","https://openalex.org/W2050758723","https://openalex.org/W2096439661","https://openalex.org/W2100335648","https://openalex.org/W2100485456","https://openalex.org/W2103941300","https://openalex.org/W2111890897","https://openalex.org/W2130709419","https://openalex.org/W2138232338","https://openalex.org/W2147214296","https://openalex.org/W2152131029","https://openalex.org/W2155690020","https://openalex.org/W2416573875","https://openalex.org/W2534981247","https://openalex.org/W6674864272","https://openalex.org/W6676895149","https://openalex.org/W6680371619","https://openalex.org/W6681415940"],"related_works":["https://openalex.org/W1982169876","https://openalex.org/W4389240440","https://openalex.org/W2060534021","https://openalex.org/W4383197910","https://openalex.org/W2530097559","https://openalex.org/W2025500868","https://openalex.org/W4221151007","https://openalex.org/W2790330717","https://openalex.org/W2952389570","https://openalex.org/W1571453037"],"abstract_inverted_index":{"Sound":[0],"source":[1],"localisation":[2,55,62,144],"cues":[3,63],"are":[4,11,73],"severely":[5],"degraded":[6],"when":[7],"multiple":[8],"acoustic":[9,127],"sources":[10],"active":[12],"in":[13,32,83,125],"the":[14,29,43,51,61,79,103,114],"presence":[15],"of":[16,50,78,81,102,110],"reverberation.":[17],"We":[18],"present":[19],"a":[20,33,65,68,84,108,121],"binaural":[21,132],"system":[22],"for":[23],"localising":[24],"simultaneous":[25,136],"speakers":[26,137],"which":[27],"exploits":[28],"fact":[30],"that":[31,59],"speech":[34],"mixture":[35],"there":[36],"exist":[37],"spectro-temporal":[38,86],"regions":[39],"or":[40],"dasiafragmentspsila,":[41],"where":[42],"energy":[44],"is":[45,57],"dominated":[46],"by":[47,146],"just":[48],"one":[49],"speakers.":[52],"A":[53],"fragment-level":[54],"model":[56,101],"proposed":[58],"integrates":[60],"within":[64],"fragment":[66],"using":[67],"weighted":[69],"mean.":[70],"The":[71,88],"weights":[72],"based":[74,95],"on":[75],"local":[76],"estimates":[77],"degree":[80],"reverberation":[82],"given":[85],"cell.":[87],"paper":[89],"investigates":[90],"different":[91],"weight":[92],"estimation":[93],"approaches":[94],"variously":[96],"on,":[97],"i)":[98],"an":[99],"established":[100],"perceptual":[104],"precedence":[105],"effect;":[106],"ii)":[107],"measure":[109],"interaural":[111],"coherence":[112],"between":[113],"left":[115],"and":[116],"right":[117],"ear":[118],"signals;":[119],"iii)":[120],"data-driven":[122],"approach":[123],"trained":[124],"matched":[126],"conditions.":[128],"Experiments":[129],"with":[130,134],"reverberant":[131],"data":[133],"two":[135],"show":[138],"appropriate":[139],"weighting":[140],"can":[141],"improve":[142],"frame-based":[143],"performance":[145],"up":[147],"to":[148],"24%.":[149]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
