{"id":"https://openalex.org/W2396291807","doi":"https://doi.org/10.1109/icassp.2016.7472697","title":"Audio word similarity for clustering with zero resources based on iterative HMM classification","display_name":"Audio word similarity for clustering with zero resources based on iterative HMM classification","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2396291807","doi":"https://doi.org/10.1109/icassp.2016.7472697","mag":"2396291807"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01394757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034545872","display_name":"Am\u00e9lie Royer","orcid":"https://orcid.org/0000-0002-8407-0705"},"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/I4210146044","display_name":"\u00c9cole Normale Sup\u00e9rieure de Rennes","ror":"https://ror.org/03rxtdc22","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210146044","https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Amelie Royer","raw_affiliation_strings":["ENS Rennes, IRISA & Inria Rennes, France","LinkMedia - Creating and exploiting explicit links between multimedia fragments (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ENS Rennes, IRISA & Inria Rennes, France","institution_ids":["https://openalex.org/I2802519937","https://openalex.org/I4210146044"]},{"raw_affiliation_string":"LinkMedia - Creating and exploiting explicit links between multimedia fragments (France)","institution_ids":[]}]},{"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/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/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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Gravier","raw_affiliation_strings":["CNRS, IRISA & Inria Rennes, France","LinkMedia - Creating and exploiting explicit links between multimedia fragments (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS, IRISA & Inria Rennes, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2802519937"]},{"raw_affiliation_string":"LinkMedia - Creating and exploiting explicit links between multimedia fragments (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036636249","display_name":"Vincent Claveau","orcid":null},"institutions":[{"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/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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Claveau","raw_affiliation_strings":["CNRS, IRISA & Inria Rennes, France","LinkMedia - Creating and exploiting explicit links between multimedia fragments (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS, IRISA & Inria Rennes, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2802519937"]},{"raw_affiliation_string":"LinkMedia - Creating and exploiting explicit links between multimedia fragments (France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01982781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5340","last_page":"5344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9958000183105469,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8482325077056885},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.8425654172897339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7795422077178955},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7270193696022034},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6055047512054443},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.588051438331604},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.586617648601532},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5256853103637695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4731004238128662},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4359782040119171},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4286663830280304},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13543343544006348}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8482325077056885},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.8425654172897339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7795422077178955},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7270193696022034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6055047512054443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.588051438331604},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.586617648601532},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5256853103637695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4731004238128662},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4359782040119171},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4286663830280304},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13543343544006348},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7472697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01394757v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01394757","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Acoustics, Speech and Signal Processing, ICASSP, Mar 2016, Shanghai, China. pp.5340 - 5344, &#x27E8;10.1109/ICASSP.2016.7472697&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01394757v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01394757","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Acoustics, Speech and Signal Processing, ICASSP, Mar 2016, Shanghai, China. pp.5340 - 5344, &#x27E8;10.1109/ICASSP.2016.7472697&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W64472890","https://openalex.org/W943204654","https://openalex.org/W1539935047","https://openalex.org/W1969241115","https://openalex.org/W2021833436","https://openalex.org/W2072343647","https://openalex.org/W2112107221","https://openalex.org/W2113054345","https://openalex.org/W2116555262","https://openalex.org/W2140277151","https://openalex.org/W2154093685","https://openalex.org/W2166557397","https://openalex.org/W2786608204","https://openalex.org/W6601311673","https://openalex.org/W6602594759","https://openalex.org/W6632428362","https://openalex.org/W6973666849"],"related_works":["https://openalex.org/W2030799363","https://openalex.org/W2950183183","https://openalex.org/W2341338763","https://openalex.org/W2419138286","https://openalex.org/W2507549656","https://openalex.org/W2050318184","https://openalex.org/W2182848507","https://openalex.org/W101156158","https://openalex.org/W2506414444","https://openalex.org/W2387825067"],"abstract_inverted_index":{"Recent":[0],"work":[1],"on":[2,30,78,84,120],"zero":[3],"resource":[4],"word":[5,142],"discovery":[6],"makes":[7],"intensive":[8],"use":[9,80],"of":[10,22,46,66,81,106,134,147,150],"audio":[11,141],"fragment":[12],"clustering":[13,26],"to":[14,35,98,118,140],"find":[15],"repeating":[16],"speech":[17],"patterns.":[18],"In":[19],"the":[20,25,43,63,79,90,131,148],"absence":[21],"acoustic":[23],"models,":[24],"step":[27],"traditionally":[28],"relies":[29,77],"dynamic":[31],"time":[32],"warping":[33],"(DTW)":[34],"compare":[36],"two":[37,121],"samples":[38,94],"and":[39,88,127,144],"thus":[40],"suffers":[41],"from":[42],"known":[44],"limitations":[45,149],"this":[47],"technique.":[48],"We":[49],"propose":[50],"a":[51,103],"new":[52],"sample":[53],"comparison":[54,143],"method,":[55],"called":[56],"similarity":[57,114],"by":[58,102],"iterative":[59],"classification,":[60],"that":[61,92,130],"exploits":[62,89],"modeling":[64],"capacities":[65],"hidden":[67],"Markov":[68],"models":[69],"(HMM)":[70],"with":[71],"no":[72],"supervision.":[73],"The":[74,112],"core":[75],"idea":[76],"HMMs":[82],"trained":[83],"randomly":[85],"labeled":[86],"data":[87],"fact":[91],"similar":[93],"are":[95],"more":[96],"likely":[97],"be":[99],"classified":[100],"together":[101],"large":[104],"number":[105],"random":[107],"classifiers":[108],"than":[109],"dissimilar":[110],"ones.":[111],"resulting":[113],"measure":[115],"is":[116],"compared":[117],"DTW":[119],"tasks,":[122],"namely":[123],"nearest":[124],"neighbor":[125],"retrieval":[126],"clustering,":[128],"showing":[129],"generalization":[132],"capabilities":[133],"probabilistic":[135],"machine":[136],"learning":[137],"significantly":[138],"benefit":[139],"overcome":[145],"many":[146],"DTW-based":[151],"comparison.":[152]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
