{"id":"https://openalex.org/W1578424336","doi":"https://doi.org/10.1109/mmsp.2004.1436567","title":"Audio indexing using feature warping and fusion techniques","display_name":"Audio indexing using feature warping and fusion techniques","publication_year":2005,"publication_date":"2005-06-07","ids":{"openalex":"https://openalex.org/W1578424336","doi":"https://doi.org/10.1109/mmsp.2004.1436567","mag":"1578424336"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2004.1436567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2004.1436567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE 6th Workshop on Multimedia Signal Processing, 2004.","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/A5016443995","display_name":"Christine S\u00e9nac","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/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"C. Senac","raw_affiliation_strings":["Institut de Recherche en Informatique de Toulouse, UMR 5505 CNRS INP UPS, Toulouse, France"],"affiliations":[{"raw_affiliation_string":"Institut de Recherche en Informatique de Toulouse, UMR 5505 CNRS INP UPS, Toulouse, France","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I134560555","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028116210","display_name":"Eliathamby Ambikairajah","orcid":"https://orcid.org/0000-0003-4673-6534"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"E. Ambikairajah","raw_affiliation_strings":["School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016443995"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I134560555","https://openalex.org/I4210119061"],"apc_list":null,"apc_paid":null,"fwci":0.6359,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66032483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"359","last_page":"362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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/T10860","display_name":"Speech 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":0.9991000294685364,"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":0.7424315810203552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.710178792476654},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6895351409912109},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5399487018585205},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49577102065086365},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.470455527305603},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4371834993362427},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.4337575435638428},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.4110243022441864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40579754114151},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3998104929924011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7424315810203552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.710178792476654},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6895351409912109},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5399487018585205},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49577102065086365},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.470455527305603},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4371834993362427},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.4337575435638428},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.4110243022441864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40579754114151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3998104929924011},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/mmsp.2004.1436567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2004.1436567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE 6th Workshop on Multimedia Signal Processing, 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1534264473","https://openalex.org/W1805888261","https://openalex.org/W2016243284","https://openalex.org/W2063415950","https://openalex.org/W2121127941","https://openalex.org/W2136461127","https://openalex.org/W2143562645","https://openalex.org/W2162170885","https://openalex.org/W2397634864","https://openalex.org/W6678487648","https://openalex.org/W6683924503","https://openalex.org/W6712325649"],"related_works":["https://openalex.org/W1670332068","https://openalex.org/W2095618524","https://openalex.org/W2735770592","https://openalex.org/W2347413598","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2154472250","https://openalex.org/W2350336482","https://openalex.org/W2133184712","https://openalex.org/W2229352698"],"abstract_inverted_index":{"This":[0],"paper":[1],"reports":[2],"on":[3,74],"the":[4,27,108,111,129,133],"improvement":[5],"of":[6,35,77,127],"speech":[7,45,90,104,143],"and":[8,46,91,101],"music":[9,47,92],"indexation":[10],"performance":[11],"under":[12,107,145],"various":[13],"noisy":[14,147],"conditions":[15,100],"for":[16,142],"radio":[17,80],"broadcast":[18,81],"using":[19],"warped":[20,112,130],"features":[21,25,113,117,131,135],"fused":[22,114],"with":[23,94,115],"traditional":[24,116,134],"at":[26],"output":[28],"stage.":[29],"The":[30],"system":[31],"employs":[32,56],"a":[33,42,57],"bank":[34],"four":[36],"parallel":[37],"front":[38,54],"ends":[39],"followed":[40],"by":[41,48],"classification":[43,106,144],"in":[44,66],"Gaussian":[49],"mixture":[50],"models,":[51],"where":[52],"each":[53],"end":[55],"different":[58,95],"feature":[59],"extraction":[60],"technique.":[61],"Then":[62],"an":[63,119],"automatic":[64],"gathering":[65],"macro":[67],"classes":[68],"is":[69],"made.":[70],"Indexing":[71],"was":[72],"performed":[73],"8":[75],"hours":[76],"manually":[78],"labelled":[79],"from":[82],"multilingual":[83],"Radio":[84],"France":[85],"International":[86],"recordings":[87],"containing":[88],"diverse":[89],"content":[93],"speaking":[96],"styles,":[97],"speakers,":[98],"noise":[99],"channels.":[102],"For":[103],"signal":[105],"noisiest":[109],"conditions,":[110],"produced":[118],"error":[120],"rate":[121],"three":[122],"times":[123],"smaller":[124],"than":[125],"that":[126],"either":[128],"or":[132],"alone.":[136],"Significant":[137],"improvements":[138],"were":[139],"also":[140],"found":[141],"less":[146],"conditions.":[148]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
