{"id":"https://openalex.org/W2049142189","doi":"https://doi.org/10.1109/tasl.2012.2194283","title":"Unsupervised Motif Acquisition in Speech via Seeded Discovery and Template Matching Combination","display_name":"Unsupervised Motif Acquisition in Speech via Seeded Discovery and Template Matching Combination","publication_year":2012,"publication_date":"2012-04-09","ids":{"openalex":"https://openalex.org/W2049142189","doi":"https://doi.org/10.1109/tasl.2012.2194283","mag":"2049142189"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2194283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2194283","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5016152101","display_name":"Armando Muscariello","orcid":null},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I4210133778","display_name":"Centre Inria de l'Universit\u00e9 de Rennes","ror":"https://ror.org/04040yw90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Armando Muscariello","raw_affiliation_strings":["METISS, IRISA, UMR 6074, INRIA Rennes Bretagne Atlantique, CNRS, Rennes, France","IRISA / INRIA Rennes - Bretagne Atlantique, Rennes, France#TAB#"],"affiliations":[{"raw_affiliation_string":"METISS, IRISA, UMR 6074, INRIA Rennes Bretagne Atlantique, CNRS, Rennes, France","institution_ids":["https://openalex.org/I4210133778","https://openalex.org/I2802519937","https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"IRISA / INRIA Rennes - Bretagne Atlantique, Rennes, France#TAB#","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008190208","display_name":"Guillaume Gravier","orcid":"https://orcid.org/0000-0002-2266-5682"},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210133778","display_name":"Centre Inria de l'Universit\u00e9 de Rennes","ror":"https://ror.org/04040yw90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Gravier","raw_affiliation_strings":["TEXMEX, IRISA, UMR 6074, INRIA Rennes Bretagne Atlantique, CNRS, Rennes, France","TEXMEX, INRIA Rennes Bretagne Atlantique, Rennes, France"],"affiliations":[{"raw_affiliation_string":"TEXMEX, IRISA, UMR 6074, INRIA Rennes Bretagne Atlantique, CNRS, Rennes, France","institution_ids":["https://openalex.org/I4210133778","https://openalex.org/I2802519937","https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"TEXMEX, INRIA Rennes Bretagne Atlantique, Rennes, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111908492","display_name":"Fr\u00e9d\u00e9ric Bimbot","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I4210133778","display_name":"Centre Inria de l'Universit\u00e9 de Rennes","ror":"https://ror.org/04040yw90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fr\u00e9d\u00e9ric Bimbot","raw_affiliation_strings":["METISS, IRISA, UMR 6074, INRIA Rennes Bretagne Atlantique, CNRS, Rennes, France","IRISA / INRIA Rennes - Bretagne Atlantique, Rennes, France#TAB#"],"affiliations":[{"raw_affiliation_string":"METISS, IRISA, UMR 6074, INRIA Rennes Bretagne Atlantique, CNRS, Rennes, France","institution_ids":["https://openalex.org/I4210133778","https://openalex.org/I2802519937","https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"IRISA / INRIA Rennes - Bretagne Atlantique, Rennes, France#TAB#","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016152101"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2802519937","https://openalex.org/I4210133778"],"apc_list":null,"apc_paid":null,"fwci":3.183,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.94002314,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"20","issue":"7","first_page":"2031","last_page":"2044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9973999857902527,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9889000058174133,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8413699865341187},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.6791787147521973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6564664244651794},{"id":"https://openalex.org/keywords/template-matching","display_name":"Template matching","score":0.5236891508102417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5044184923171997},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5032936930656433},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.49683716893196106},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.474161297082901},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47003453969955444},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4613191783428192},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4425329864025116},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.43682006001472473},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.42417484521865845},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33128559589385986},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.27932658791542053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413699865341187},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.6791787147521973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6564664244651794},{"id":"https://openalex.org/C158096908","wikidata":"https://www.wikidata.org/wiki/Q3983303","display_name":"Template matching","level":3,"score":0.5236891508102417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5044184923171997},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5032936930656433},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.49683716893196106},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.474161297082901},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47003453969955444},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4613191783428192},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4425329864025116},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.43682006001472473},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.42417484521865845},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33128559589385986},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27932658791542053},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2012.2194283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2194283","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-00740978v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-00740978","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing, 2012, 20 (7), pp.2031 - 2044. ⟨10.1109/TASL.2012.2194283⟩","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W20983465","https://openalex.org/W30845872","https://openalex.org/W62023843","https://openalex.org/W66167291","https://openalex.org/W1499245496","https://openalex.org/W1507177964","https://openalex.org/W1539935047","https://openalex.org/W1556583247","https://openalex.org/W1988596541","https://openalex.org/W2025344845","https://openalex.org/W2028903194","https://openalex.org/W2045346852","https://openalex.org/W2079460648","https://openalex.org/W2083087666","https://openalex.org/W2089458547","https://openalex.org/W2097128017","https://openalex.org/W2097207027","https://openalex.org/W2112107221","https://openalex.org/W2118474530","https://openalex.org/W2125247927","https://openalex.org/W2141882396","https://openalex.org/W2144788278","https://openalex.org/W2149179203","https://openalex.org/W2161969291","https://openalex.org/W2403207842","https://openalex.org/W2407151108","https://openalex.org/W4211153864","https://openalex.org/W4245668478","https://openalex.org/W6601311673","https://openalex.org/W6602705600","https://openalex.org/W6632428362","https://openalex.org/W6633342350","https://openalex.org/W6680991293"],"related_works":["https://openalex.org/W2335896301","https://openalex.org/W2012393389","https://openalex.org/W2333240621","https://openalex.org/W3006618853","https://openalex.org/W2253066076","https://openalex.org/W2295636786","https://openalex.org/W2399492946","https://openalex.org/W2578092491","https://openalex.org/W3184620678","https://openalex.org/W2048014685"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"and":[3,10,34,72,140,176,184,193,199,216,218],"evaluates":[4],"a":[5,19,64,79,108],"computational":[6],"architecture":[7,159],"to":[8,67,82,90,129,150,172,226],"discover":[9],"collect":[11],"occurrences":[12],"of":[13,28,54,107,117,125,145,154,166,187,209,223],"speech":[14,51,83,146],"repetitions,":[15],"or":[16,31],"motifs,":[17],"in":[18,25,59,148,196],"totally":[20],"unsupervised":[21],"fashion,":[22],"that":[23,77,85,111,212],"is":[24,160],"the":[26,38,50,87,99,105,123,151,206,210,220],"absence":[27],"acoustic,":[29],"lexical":[30],"pronunciation":[32],"modeling":[33],"training":[35],"material.":[36],"In":[37],"last":[39],"few":[40],"years,":[41],"this":[42],"task":[43],"has":[44],"known":[45],"an":[46],"increasing":[47],"interest":[48],"from":[49],"community":[52],"because":[53],"a)":[55,205],"its":[56,74],"potential":[57],"applicability":[58],"spoken":[60],"document":[61],"processing":[62,84],"(as":[63],"preliminary":[65],"step":[66],"summarization,":[68],"topic":[69],"clustering,":[70],"etc.)":[71],"b)":[73,219],"novel":[75],"methodology,":[76],"defines":[78],"new":[80],"paradigm":[81],"circumvents":[86],"issues":[88],"common":[89],"all":[91],"supervised,":[92],"trained":[93],"technologies.":[94],"The":[95,158,202],"contributions":[96],"implied":[97],"by":[98,114],"proposed":[100],"system":[101,211],"are":[102],"two-fold:":[103],"1)":[104],"design":[106],"discovery":[109],"strategy":[110],"detects":[112],"repetitions":[113],"extending":[115],"matches":[116],"motif":[118],"fragments,":[119],"called":[120],"seeds;":[121],"2)":[122],"implementation":[124],"template":[126,232],"matching":[127],"techniques":[128],"detect":[130],"acoustically":[131],"close":[132],"segments,":[133],"based":[134,230],"on":[135,163,231],"dynamic":[136],"time":[137],"warping":[138],"(DTW)":[139],"self-similarity":[141],"matrix":[142],"(SSM)":[143],"comparison":[144],"templates,":[147],"contrast":[149],"decoding":[152],"procedures":[153],"model-based":[155],"recognition":[156],"systems.":[157],"thoroughly":[161],"evaluated":[162],"several":[164],"hours":[165],"French":[167],"broadcast":[168],"news":[169],"shows":[170],"according":[171],"various":[173],"parameter":[174],"settings":[175],"acoustic":[177,227],"features,":[178],"namely":[179],"mel-frequency":[180],"cepstral":[181],"coefficients":[182],"(MFCCs)":[183],"different":[185],"types":[186],"posteriorgrams:":[188],"Gaussian":[189],"mixture":[190],"model":[191],"(GMM)-based,":[192],"phone-based":[194],"posteriors,":[195],"both":[197],"language-matched":[198],"mismatched":[200],"conditions.":[201],"evaluation":[203],"highlights":[204],"improved":[207],"robustness":[208],"jointly":[213],"employs":[214],"DTW":[215],"SSM":[217],"relevant":[221],"impact":[222],"language-specific":[224],"features":[225],"similarity":[228],"detection":[229],"matching.":[233]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}