{"id":"https://openalex.org/W2093844087","doi":"https://doi.org/10.1109/slt.2012.6424204","title":"On the generalization of Shannon entropy for speech recognition","display_name":"On the generalization of Shannon entropy for speech recognition","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2093844087","doi":"https://doi.org/10.1109/slt.2012.6424204","mag":"2093844087"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2012.6424204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","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/A5042745853","display_name":"Nicolas Obin","orcid":"https://orcid.org/0000-0002-5236-5306"},"institutions":[{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Nicolas Obin","raw_affiliation_strings":["IRCAM, CNRS, Paris, France","IRCAM-CNRS UMR 9912-STMS Paris, France"],"affiliations":[{"raw_affiliation_string":"IRCAM, CNRS, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"IRCAM-CNRS UMR 9912-STMS Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062200666","display_name":"Marco Liuni","orcid":"https://orcid.org/0000-0001-6831-8259"},"institutions":[{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marco Liuni","raw_affiliation_strings":["IRCAM, CNRS, Paris, France","IRCAM-CNRS UMR 9912-STMS Paris, France"],"affiliations":[{"raw_affiliation_string":"IRCAM, CNRS, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"IRCAM-CNRS UMR 9912-STMS Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042745853"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I4389425508"],"apc_list":null,"apc_paid":null,"fwci":0.97698156,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.79599692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7088516354560852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6102087497711182},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5529414415359497},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4726490080356598},{"id":"https://openalex.org/keywords/breathy-voice","display_name":"Breathy voice","score":0.4389876425266266},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.43797701597213745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4084007143974304},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3237226605415344},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.10459703207015991}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7088516354560852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6102087497711182},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5529414415359497},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4726490080356598},{"id":"https://openalex.org/C72453395","wikidata":"https://www.wikidata.org/wiki/Q3328163","display_name":"Breathy voice","level":3,"score":0.4389876425266266},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.43797701597213745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4084007143974304},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3237226605415344},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.10459703207015991},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2012.6424204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1483501585","https://openalex.org/W1498609987","https://openalex.org/W1553236419","https://openalex.org/W1592472301","https://openalex.org/W1991851767","https://openalex.org/W1995875735","https://openalex.org/W2041823554","https://openalex.org/W2096588881","https://openalex.org/W2100620757","https://openalex.org/W2122882636","https://openalex.org/W2131284901","https://openalex.org/W2144205901","https://openalex.org/W2147147599","https://openalex.org/W2153144850","https://openalex.org/W2169559282","https://openalex.org/W2401969501","https://openalex.org/W2949606031","https://openalex.org/W4310854362","https://openalex.org/W6846947293"],"related_works":["https://openalex.org/W2010723308","https://openalex.org/W2066514841","https://openalex.org/W2071762554","https://openalex.org/W2390163410","https://openalex.org/W1981431100","https://openalex.org/W2144536094","https://openalex.org/W2163103544","https://openalex.org/W2551182807","https://openalex.org/W3033899355","https://openalex.org/W4383822431"],"abstract_inverted_index":{"This":[0,131],"paper":[1],"introduces":[2],"an":[3,155],"entropy-based":[4],"spectral":[5],"representation":[6,30,77],"as":[7],"a":[8,39,64,91],"measure":[9],"of":[10,13,41,54,73,94,102,124,135,148,154],"the":[11,20,34,42,52,58,68,99,122,133,146,152],"degree":[12],"noisiness":[14,81,136],"in":[15,90,98,113,160],"audio":[16,24,46],"signals,":[17],"complementary":[18],"to":[19,145],"standard":[21],"MFCCs":[22],"for":[23,121,137,151],"and":[25,86,117,140],"speech":[26,126,138],"recognition.":[27],"The":[28,75,108],"proposed":[29,76],"is":[31,38,110,118],"based":[32],"on":[33,57,67],"R\u00e9nyi":[35,49],"entropy,":[36],"which":[37],"generalization":[40],"Shannon":[43,85],"entropy.":[44],"In":[45],"signal":[47],"representation,":[48],"entropy":[50],"presents":[51],"advantage":[53],"focusing":[55],"either":[56],"harmonic":[59],"content":[60,70],"(prominent":[61],"amplitude":[62],"within":[63],"distribution)":[65],"or":[66],"noise":[69],"(equal":[71],"distribution":[72],"amplitudes).":[74],"outperforms":[78],"all":[79],"other":[80],"measures":[82],"-":[83,89,127],"including":[84],"Wiener":[87],"entropies":[88],"large-scale":[92],"classification":[93,147],"vocal":[95],"effort":[96],"(whispered-soft/normal/loud-shouted)":[97],"real":[100],"scenario":[101],"multi-language":[103],"massive":[104],"role-playing":[105],"video":[106,161],"games.":[107,162],"improvement":[109],"around":[111],"10%":[112],"relative":[114],"error":[115],"reduction,":[116],"particularly":[119],"significant":[120],"recognition":[123],"noisy":[125],"i.e.,":[128],"whispery/breathy":[129],"speech.":[130],"confirms":[132],"role":[134],"recognition,":[139],"will":[141],"further":[142],"be":[143],"extended":[144],"voice":[149,157],"quality":[150],"design":[153],"automatic":[156],"casting":[158],"system":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}