{"id":"https://openalex.org/W2112107221","doi":"https://doi.org/10.1109/cbmi.2011.5972534","title":"Spoken WordCloud: Clustering recurrent patterns in speech","display_name":"Spoken WordCloud: Clustering recurrent patterns in speech","publication_year":2011,"publication_date":"2011-06-01","ids":{"openalex":"https://openalex.org/W2112107221","doi":"https://doi.org/10.1109/cbmi.2011.5972534","mag":"2112107221"},"language":"en","primary_location":{"id":"doi:10.1109/cbmi.2011.5972534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi.2011.5972534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 9th International Workshop on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"},"type":"preprint","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/A5051249358","display_name":"R\u00e9mi Flamary","orcid":"https://orcid.org/0000-0002-4212-6627"},"institutions":[{"id":"https://openalex.org/I4210108118","display_name":"Laboratoire d'Informatique, du Traitement de l'Information et des Syst\u00e8mes","ror":"https://ror.org/01f1vfy95","country_code":"FR","type":"facility","lineage":["https://openalex.org/I141576021","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210108118","https://openalex.org/I62396329","https://openalex.org/I88814501"]},{"id":"https://openalex.org/I62396329","display_name":"Universit\u00e9 de Rouen Normandie","ror":"https://ror.org/03nhjew95","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I62396329"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Remi Flamary","raw_affiliation_strings":["LITIS EA 4108, Universit\u00e9 de Rouen, France","LITIS, EA 4108, Universit\u00e9 de Rouen, 76801 Saint Etienne du Rouvray, France"],"affiliations":[{"raw_affiliation_string":"LITIS EA 4108, Universit\u00e9 de Rouen, France","institution_ids":["https://openalex.org/I4210108118","https://openalex.org/I62396329"]},{"raw_affiliation_string":"LITIS, EA 4108, Universit\u00e9 de Rouen, 76801 Saint Etienne du Rouvray, France","institution_ids":["https://openalex.org/I62396329","https://openalex.org/I4210108118"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051383020","display_name":"Xavier Anguera","orcid":"https://orcid.org/0000-0001-8659-3991"},"institutions":[{"id":"https://openalex.org/I4210134591","display_name":"Telefonica Research and Development","ror":"https://ror.org/03qgzzb04","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210097190","https://openalex.org/I4210134591"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Anguera","raw_affiliation_strings":["Telefonica Research and Development, Barcelona, Spain","Telefonica Research, Via Augusta 177, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Telefonica Research and Development, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]},{"raw_affiliation_string":"Telefonica Research, Via Augusta 177, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013727792","display_name":"Nuria Oliver","orcid":"https://orcid.org/0000-0001-5985-691X"},"institutions":[{"id":"https://openalex.org/I4210134591","display_name":"Telefonica Research and Development","ror":"https://ror.org/03qgzzb04","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210097190","https://openalex.org/I4210134591"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nuria Oliver","raw_affiliation_strings":["Telefonica Research and Development, Barcelona, Spain","Telefonica Research, Via Augusta 177, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Telefonica Research and Development, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]},{"raw_affiliation_string":"Telefonica Research, Via Augusta 177, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051249358"],"corresponding_institution_ids":["https://openalex.org/I4210108118","https://openalex.org/I62396329"],"apc_list":null,"apc_paid":null,"fwci":2.79589348,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91132742,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"133","last_page":"138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9947999715805054,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8591146469116211},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8468669652938843},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7033724188804626},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6215236186981201},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5818588733673096},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5656516551971436},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5591748356819153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5208609700202942},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5099776983261108},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4939025044441223},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4694012701511383},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.450936883687973},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44541293382644653},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44456738233566284},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.29578226804733276},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07398468255996704}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8591146469116211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8468669652938843},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7033724188804626},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6215236186981201},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5818588733673096},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5656516551971436},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5591748356819153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5208609700202942},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5099776983261108},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4939025044441223},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4694012701511383},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.450936883687973},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44541293382644653},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44456738233566284},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.29578226804733276},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07398468255996704},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi.2011.5972534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi.2011.5972534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 9th International Workshop on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W1539935047","https://openalex.org/W1606268232","https://openalex.org/W1986007546","https://openalex.org/W2072240081","https://openalex.org/W2089458547","https://openalex.org/W2114347655","https://openalex.org/W2116810533","https://openalex.org/W2118841860","https://openalex.org/W2149802835","https://openalex.org/W2162545477","https://openalex.org/W2165874743","https://openalex.org/W2166343746","https://openalex.org/W6601311673","https://openalex.org/W6636285342","https://openalex.org/W6684578312"],"related_works":["https://openalex.org/W1987021544","https://openalex.org/W3151376046","https://openalex.org/W2964829415","https://openalex.org/W3089379469","https://openalex.org/W2131711534","https://openalex.org/W2105439218","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W2009814707","https://openalex.org/W2903652364"],"abstract_inverted_index":{"The":[0],"automatic":[1,22,69,78],"summarization":[2,71],"of":[3,80,105,112,143,151,160],"speech":[4,16,23,70],"recordings":[5],"is":[6,17,74],"typically":[7],"carried":[8],"out":[9],"as":[10],"a":[11,35,125,140,157],"two":[12],"step":[13],"process:":[14],"the":[15,27,77,84,93,103],"first":[18,90],"decoded":[19],"using":[20,156],"an":[21,68,108,136,148],"recognition":[24],"system":[25],"and":[26,95,99,147],"resulting":[28],"text":[29],"transcripts":[30],"are":[31,89,97],"processed":[32],"to":[33,51,59,102,120,145],"create":[34],"summary.":[36],"However,":[37],"this":[38,64],"approach":[39,117],"might":[40],"not":[41],"be":[42],"suitable":[43],"in":[44,63,83,153],"adverse":[45],"acoustic":[46,87,110],"conditions":[47],"or":[48],"when":[49],"applied":[50],"languages":[52],"with":[53,131],"limited":[54],"training":[55],"resources.":[56],"In":[57],"order":[58],"address":[60],"these":[61],"limitations,":[62],"paper":[65],"we":[66,123],"propose":[67],"method":[72],"that":[73,138],"based":[75],"on":[76],"discovery":[79],"recurrent":[81,86],"patterns":[82,88],"speech:":[85],"extracted":[91],"from":[92],"audio":[94],"then":[96],"clustered":[98],"ranked":[100],"according":[101],"number":[104],"repetitions,":[106],"creating":[107],"approximate":[109],"summary":[111],"what":[113,122],"was":[114],"spoken.":[115],"This":[116],"allows":[118],"us":[119],"build":[121],"call":[124],"\"Spoken":[126],"WordCloud\"":[127],"termed":[128],"after":[129],"similarity":[130],"text-based":[132],"word-clouds.":[133],"We":[134],"present":[135],"algorithm":[137],"achieves":[139],"cluster":[141],"purity":[142,150],"up":[144],"90%":[146],"inverse":[149],"71%":[152],"preliminary":[154],"experiments":[155],"small":[158],"dataset":[159],"connected":[161],"spoken":[162],"words.":[163]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}