{"id":"https://openalex.org/W2143038775","doi":"https://doi.org/10.21437/interspeech.2010-113","title":"Multimodal speaker diarization using oriented optical flow histograms","display_name":"Multimodal speaker diarization using oriented optical flow histograms","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W2143038775","doi":"https://doi.org/10.21437/interspeech.2010-113","mag":"2143038775"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-113","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-113","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059962618","display_name":"Mary Tai Knox","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mary Tai Knox","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062323483","display_name":"Gerald Friedland","orcid":"https://orcid.org/0000-0002-9400-6539"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["University of California, Berkeley, Berkeley, United States"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059962618"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.3371,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60686033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"290","last_page":"293"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9984999895095825,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8874337077140808},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8423745632171631},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.6728798151016235},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6633821129798889},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5791317224502563},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.516423761844635},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4771696627140045},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.42866405844688416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3962395191192627},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12140753865242004}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8874337077140808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8423745632171631},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.6728798151016235},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6633821129798889},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5791317224502563},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.516423761844635},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4771696627140045},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.42866405844688416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3962395191192627},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12140753865242004},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2010-113","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-113","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W341184420","https://openalex.org/W1971791733","https://openalex.org/W2048447221","https://openalex.org/W2099403067","https://openalex.org/W2114032116","https://openalex.org/W2115175902","https://openalex.org/W2118847468","https://openalex.org/W2118877769","https://openalex.org/W2124673517","https://openalex.org/W2138467558","https://openalex.org/W2156255174","https://openalex.org/W2338994564","https://openalex.org/W3003662786"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1979041948","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,44,79,94],"is":[2],"the":[3,33,36,48,62,75,93],"task":[4],"of":[5,38,50,64],"partitioning":[6],"an":[7,101],"input":[8],"stream":[9],"into":[10],"speaker":[11],"homogeneous":[12],"regions,":[13],"or":[14],"in":[15,42],"other":[16],"words,":[17],"to":[18,25],"determine":[19],"\u201dwho":[20],"spoke":[21],"when.\u201d":[22],"While":[23],"approaches":[24],"this":[26,58],"problem":[27],"have":[28],"traditionally":[29],"relied":[30],"entirely":[31],"on":[32,53,69],"audio":[34,88],"stream,":[35],"availability":[37],"accompanying":[39],"video":[40,66],"streams":[41],"recent":[43],"corpora":[45],"has":[46],"prompted":[47],"study":[49],"methods":[51],"based":[52,68],"multimodal":[54],"audio-visual":[55],"features.":[56],"In":[57],"work,":[59],"we":[60,81],"propose":[61],"use":[63],"robust":[65],"features":[67,91],"oriented":[70],"optical":[71],"flow":[72],"histograms.":[73],"Using":[74],"state-of-the":[76],"art":[77],"ICSI":[78],"system,":[80],"show":[82],"that,":[83],"when":[84],"combined":[85],"with":[86],"standard":[87],"features,":[89],"these":[90],"improve":[92],"error":[95],"rate":[96],"by":[97],"14%":[98],"percent":[99],"over":[100],"audio-only":[102],"baseline.":[103]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}