{"id":"https://openalex.org/W62294813","doi":"https://doi.org/10.21437/interspeech.2011-385","title":"Information bottleneck features for HMM/GMM speaker diarization of meetings recordings","display_name":"Information bottleneck features for HMM/GMM speaker diarization of meetings recordings","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W62294813","doi":"https://doi.org/10.21437/interspeech.2011-385","mag":"62294813"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-385","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/192712","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065571234","display_name":"Sree Harsha Yella","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":true,"raw_author_name":"Sree Harsha Yella","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061495800","display_name":"Fabio Valente","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":"Fabio Valente","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065571234"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":1.761,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86103683,"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":"953","last_page":"956"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9965000152587891,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8570510149002075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8169077634811401},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7938222289085388},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7276722192764282},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7106888890266418},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6209359169006348},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.611103892326355},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.597282886505127},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5804944038391113},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4967666268348694},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.4867856204509735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4718330502510071},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.433318167924881},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.418995201587677},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4067959189414978},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40616047382354736},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.29597917199134827}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8570510149002075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169077634811401},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7938222289085388},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7276722192764282},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7106888890266418},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6209359169006348},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.611103892326355},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.597282886505127},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5804944038391113},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4967666268348694},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.4867856204509735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4718330502510071},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.433318167924881},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.418995201587677},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4067959189414978},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40616047382354736},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29597917199134827},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2011-385","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.646.3217","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.646.3217","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/2011/Yella_INTERSPEECH_2011.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:192712","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192712","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"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:192712","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192712","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1556474518","https://openalex.org/W2071489795","https://openalex.org/W2098726438","https://openalex.org/W2103723258","https://openalex.org/W2113386290","https://openalex.org/W2132990350","https://openalex.org/W2149402184","https://openalex.org/W2159591770","https://openalex.org/W2165712214","https://openalex.org/W2170695863","https://openalex.org/W2171700247","https://openalex.org/W2497516627","https://openalex.org/W2979454998","https://openalex.org/W4300666183"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W4229940372"],"abstract_inverted_index":{"Improved":[0],"diarization":[1,36,45,80],"results":[2],"can":[3],"be":[4],"obtained":[5],"through":[6,38],"combination":[7,12],"of":[8,41,58,104],"multiple":[9],"systems.":[10],"Several":[11],"techniques":[13],"have":[14],"been":[15],"proposed":[16],"based":[17,47],"on":[18,48,115],"output":[19],"voting,":[20],"initialization":[21],"and":[22,29],"also":[23],"integrated":[24],"approaches.":[25],"This":[26,82],"paper":[27],"proposes":[28],"investigates":[30],"a":[31,56,78],"novel":[32],"approach":[33,97],"to":[34,54,64,102,110,147],"combine":[35],"systems":[37,107],"the":[39,49,65,87,96,105,112,119,131,139],"use":[40],"features.":[42],"A":[43],"first":[44],"system,":[46],"Information":[50],"Bottleneck,":[51],"is":[52,84,143],"used":[53,71,135],"generate":[55],"set":[57],"features":[59,68,133],"that":[60,129],"contain":[61],"information":[62],"relevant":[63],"clustering.":[66],"Those":[67],"are":[69,134],"later":[70],"in":[72,77,90,108,124],"conjunction":[73],"with":[74,137],"conventional":[75],"MFCC":[76],"second":[79],"system.":[81],"method":[83],"inspired":[85],"from":[86,118,145],"TANDEM":[88],"framework":[89],"ASR.":[91],"While":[92],"being":[93],"fully":[94],"integrated,":[95],"does":[98],"not":[99],"need":[100],"modifications":[101],"any":[103],"two":[106],"order":[109],"integrate":[111],"information.":[113],"Experiments":[114],"24":[116],"recordings":[117],"NIST":[120],"RT06/RT07/RT09":[121],"evaluations":[122],"collected":[123],"five":[125],"meeting":[126],"rooms":[127],"reveal":[128],"when":[130],"IB":[132],"together":[136],"MFCC,":[138],"total":[140],"speaker":[141],"error":[142],"reduced":[144],"12%":[146],"9.7%,":[148],"i.e.,":[149],"by":[150],"approximatively":[151],"19%":[152],"relative.":[153]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}