{"id":"https://openalex.org/W1562651896","doi":"https://doi.org/10.21437/interspeech.2010-704","title":"Audio-visual synchronisation for speaker diarisation","display_name":"Audio-visual synchronisation for speaker diarisation","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W1562651896","doi":"https://doi.org/10.21437/interspeech.2010-704","mag":"1562651896"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-704","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/150588","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089965540","display_name":"Giulia Garau","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giulia Garau","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075750735","display_name":"Alfred Dielmann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alfred Dielmann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bourlard","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3386,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.52998729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2654","last_page":"2657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7657928466796875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.654878556728363},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.605968713760376},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5623757839202881},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5405145883560181},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4933125078678131},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.4876798391342163},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.4870362877845764},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4779674708843231},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4484519958496094},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.445176899433136},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2530677318572998},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.135142982006073},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.05916866660118103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657928466796875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.654878556728363},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.605968713760376},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5623757839202881},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5405145883560181},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4933125078678131},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.4876798391342163},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.4870362877845764},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4779674708843231},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4484519958496094},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.445176899433136},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2530677318572998},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.135142982006073},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.05916866660118103},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2010-704","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.375.5837","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.375.5837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2010/Garau_INTERSPEECH_2010.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:150588","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/150588","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:150588","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/52445","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:150588","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/150588","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W94101771","https://openalex.org/W2025341678","https://openalex.org/W2042608483","https://openalex.org/W2081841744","https://openalex.org/W2100561338","https://openalex.org/W2106015547","https://openalex.org/W2115175902","https://openalex.org/W2118847468","https://openalex.org/W2124022904","https://openalex.org/W2125336414","https://openalex.org/W2127211243","https://openalex.org/W2130103520","https://openalex.org/W2157667843","https://openalex.org/W2159591770","https://openalex.org/W2164899449","https://openalex.org/W2338994564"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2271369634","https://openalex.org/W2914532148","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W2466816617","https://openalex.org/W578794879","https://openalex.org/W2372625757","https://openalex.org/W2625296515"],"abstract_inverted_index":{"The":[0,74,87],"role":[1],"of":[2,27,97],"audio\u00e2\u0080\u0093visual":[3],"speech":[4,84],"synchrony":[5,85],"for":[6,83],"speaker":[7],"diarisation":[8,112],"is":[9],"investigated":[10],"on":[11,24,51],"the":[12,52,66],"multiparty":[13],"meeting":[14],"domain.":[15],"We":[16],"measured":[17],"both":[18,45],"mutual":[19,88],"information":[20,89],"and":[21,29,38,55,71,93,123],"canonical":[22],"correlation":[23],"different":[25],"sets":[26],"audio":[28],"video":[30],"features.":[31],"As":[32,40],"acoustic":[33,91],"features":[34,42,118],"we":[35,43,64],"considered":[36],"energy":[37,92],"MFCCs.":[39],"visual":[41,117],"experimented":[44],"with":[46],"motion":[47,59,67,96,121],"intensity":[48],"features,":[49],"computed":[50],"whole":[53],"image,":[54],"Kanade":[56],"Lucas":[57],"Tomasi":[58],"estimation.":[60,86],"Thanks":[61],"to":[62,79],"KLT":[63,94],"decomposed":[65],"in":[68,103],"its":[69],"horizontal":[70],"vertical":[72,75,95],"components.":[73],"component":[76],"was":[77],"found":[78],"be":[80],"more":[81],"reliable":[82],"between":[90],"skin":[98],"pixels,":[99],"not":[100],"only":[101,111],"resulted":[102],"a":[104,109],"20%":[105],"relative":[106],"improvement":[107],"over":[108],"MFCC":[110],"system,":[113],"but":[114],"also":[115],"outperformed":[116],"such":[119],"as":[120],"intensities":[122],"head":[124],"poses.":[125]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
