{"id":"https://openalex.org/W2147214296","doi":"https://doi.org/10.1109/icassp.2005.1416211","title":"Improving Audio Source Localization by Learning the Precedence Effect","display_name":"Improving Audio Source Localization by Learning the Precedence Effect","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2147214296","doi":"https://doi.org/10.1109/icassp.2005.1416211","mag":"2147214296"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1416211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1416211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/A5087313939","display_name":"Kevin Wilson","orcid":"https://orcid.org/0000-0001-9141-2219"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kevin Wilson","raw_affiliation_strings":["Vision Interface Group, CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA","CSAIL - MIT, Cambridge, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Vision Interface Group, CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"CSAIL - MIT, Cambridge, MA, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["Vision Interface Group, CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA","CSAIL - MIT, Cambridge, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Vision Interface Group, CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"CSAIL - MIT, Cambridge, MA, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087313939"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":1.9345,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86206144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"4","issue":null,"first_page":"1125","last_page":"1128"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983999729156494,"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":0.74431312084198},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7398978471755981},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.7082709074020386},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.6957518458366394},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5605061650276184},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.539910078048706},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5336687564849854},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.49029186367988586},{"id":"https://openalex.org/keywords/precedence-effect","display_name":"Precedence effect","score":0.48634225130081177},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4612303078174591},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4533126652240753},{"id":"https://openalex.org/keywords/audio-signal-flow","display_name":"Audio signal flow","score":0.4272606670856476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4018368124961853},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.2829229235649109},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.21217864751815796},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.1046018898487091},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0690058171749115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74431312084198},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7398978471755981},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.7082709074020386},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.6957518458366394},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5605061650276184},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.539910078048706},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5336687564849854},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.49029186367988586},{"id":"https://openalex.org/C82600853","wikidata":"https://www.wikidata.org/wiki/Q2115271","display_name":"Precedence effect","level":3,"score":0.48634225130081177},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4612303078174591},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4533126652240753},{"id":"https://openalex.org/C167940747","wikidata":"https://www.wikidata.org/wiki/Q63727227","display_name":"Audio signal flow","level":5,"score":0.4272606670856476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4018368124961853},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2829229235649109},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.21217864751815796},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.1046018898487091},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0690058171749115},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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":2,"locations":[{"id":"doi:10.1109/icassp.2005.1416211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1416211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.205.1705","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.205.1705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://groups.csail.mit.edu/vision/vip/papers/icassp2005-wilson.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8700000047683716,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1596560216","https://openalex.org/W1786963892","https://openalex.org/W2025127228","https://openalex.org/W2117678320","https://openalex.org/W2128334000","https://openalex.org/W2158852496","https://openalex.org/W2798909945"],"related_works":["https://openalex.org/W2074698273","https://openalex.org/W2091939257","https://openalex.org/W4387698063","https://openalex.org/W4212794605","https://openalex.org/W1975359510","https://openalex.org/W2375101025","https://openalex.org/W2898469868","https://openalex.org/W2171737355","https://openalex.org/W2289868279","https://openalex.org/W2069094726"],"abstract_inverted_index":{"Audio":[0],"source":[1],"localization":[2,58,84],"in":[3,16,24],"reverberant":[4],"environments":[5],"is":[6],"difficult":[7],"for":[8,37],"automated":[9],"microphone":[10],"array":[11],"systems.":[12],"Certain":[13],"features":[14],"observable":[15],"the":[17,70,78],"audio":[18,25,38],"signal,":[19],"such":[20],"as":[21],"sudden":[22],"increases":[23],"energy,":[26],"provide":[27],"cues":[28],"to":[29,57],"indicate":[30],"time-frequency":[31],"regions":[32],"that":[33],"are":[34],"particularly":[35],"useful":[36],"localization,":[39],"but":[40],"previous":[41],"approaches":[42],"have":[43],"not":[44],"systematically":[45],"exploited":[46],"these":[47],"cues.":[48],"We":[49],"learn":[50],"a":[51],"mapping":[52],"from":[53,74],"reverberated":[54],"signal":[55],"spectrograms":[56],"precision":[59],"using":[60],"ridge":[61],"regression.":[62],"The":[63],"resulting":[64],"mappings":[65],"exhibit":[66],"behavior":[67],"consistent":[68],"with":[69],"well-known":[71],"precedence":[72],"effect":[73],"psychoacoustic":[75],"studies.":[76],"Using":[77],"learned":[79],"mappings,":[80],"we":[81],"demonstrate":[82],"improved":[83],"performance.":[85]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}