{"id":"https://openalex.org/W17421212","doi":"https://doi.org/10.21437/interspeech.2004-427","title":"Audio-visual SPeaker localization for car navigation systems","display_name":"Audio-visual SPeaker localization for car navigation systems","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W17421212","doi":"https://doi.org/10.21437/interspeech.2004-427","mag":"17421212"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-427","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"conference-paper","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/A5082681724","display_name":"Xianxian Zhang","orcid":"https://orcid.org/0000-0003-1238-1341"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xianxian Zhang","raw_affiliation_strings":["University of Colorado \u2010 Boulder"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado \u2010 Boulder","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":["#N##TAB##TAB##TAB##TAB# Nagoya University#N##TAB##TAB##TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# Nagoya University#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["University of Colorado \u2010 Boulder"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado \u2010 Boulder","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081599222","display_name":"Toshiki Maeno","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshiki Maeno","raw_affiliation_strings":["#N##TAB##TAB##TAB##TAB# Nagoya University#N##TAB##TAB##TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# Nagoya University#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5188,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.5232118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2501","last_page":"2504"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.8160427808761597},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6007148027420044},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5966112613677979},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.569532573223114},{"id":"https://openalex.org/keywords/navigation-system","display_name":"Navigation system","score":0.4641927480697632},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4533289670944214},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4362798035144806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3606669306755066},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35439229011535645},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14599338173866272},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12096509337425232}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8160427808761597},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6007148027420044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5966112613677979},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.569532573223114},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.4641927480697632},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4533289670944214},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4362798035144806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3606669306755066},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35439229011535645},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14599338173866272},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12096509337425232},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-427","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W196476531","https://openalex.org/W204466630","https://openalex.org/W1538482441","https://openalex.org/W2074074031","https://openalex.org/W2103203016","https://openalex.org/W2104425135","https://openalex.org/W2117071049","https://openalex.org/W2139813639","https://openalex.org/W2141823335"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W1596203174","https://openalex.org/W2117933979","https://openalex.org/W2283130723","https://openalex.org/W103938586","https://openalex.org/W2104718772","https://openalex.org/W4233992201","https://openalex.org/W2292950558","https://openalex.org/W2368721880"],"abstract_inverted_index":{"Human-computer":[0],"interaction":[1],"for":[2,57,63],"in-vehicle":[3,65],"information":[4,30,77],"and":[5,16,28,60,75],"navigation":[6],"systems":[7],"is":[8,21,41],"a":[9,52],"challenging":[10],"problem":[11],"because":[12],"of":[13,26],"the":[14,24,38,80,91],"diverse":[15],"changing":[17],"acoustic":[18,45],"environments.":[19],"It":[20],"proposed":[22,70,92],"that":[23],"integration":[25,55],"video":[27],"audio":[29,74,104],"can":[31,94],"significantly":[32],"improve":[33,95],"dialog":[34,67],"system":[35,56,71,93],"performance,":[36],"since":[37],"visual":[39,76],"modality":[40],"not":[42],"impacted":[43],"by":[44,98],"noise.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"propose":[51],"robust":[53],"audio-visual":[54],"source":[58],"tracking":[59],"speech":[61,66,96],"enhancement":[62],"an":[64],"system.":[68],"The":[69],"integrates":[72],"both":[73],"to":[78,100],"locate":[79],"desired":[81],"speaker":[82],"source.":[83],"Using":[84],"real":[85],"data":[86,105],"collected":[87],"in":[88],"car":[89],"environments,":[90],"accuracy":[97],"up":[99],"40.75%":[101],"compared":[102],"with":[103],"alone.":[106]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
