{"id":"https://openalex.org/W2586846985","doi":"https://doi.org/10.1109/slt.2016.7846308","title":"Deep learning with maximal figure-of-merit cost to advance multi-label speech attribute detection","display_name":"Deep learning with maximal figure-of-merit cost to advance multi-label speech attribute detection","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2586846985","doi":"https://doi.org/10.1109/slt.2016.7846308","mag":"2586846985"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2016.7846308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","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/A5083404931","display_name":"Ivan Kukanov","orcid":"https://orcid.org/0000-0003-4052-2754"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Ivan Kukanov","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Finland"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037259225","display_name":"Ville Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-5885-0003"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Hautamaki","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Finland"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I246010334","display_name":"Universit\u00e0 degli Studi di Enna Kore","ror":"https://ror.org/04vd28p53","country_code":"IT","type":"education","lineage":["https://openalex.org/I246010334"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["Faculty of Architecture and Engineering, University of Enna \u201cKore\u201d, Italy","School of ECE, Georgia Institute of Technology, USA","Faculty of Architecture and Engineering, University of Enna \"Kore\", Italy"],"affiliations":[{"raw_affiliation_string":"Faculty of Architecture and Engineering, University of Enna \u201cKore\u201d, Italy","institution_ids":["https://openalex.org/I246010334"]},{"raw_affiliation_string":"School of ECE, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Faculty of Architecture and Engineering, University of Enna \"Kore\", Italy","institution_ids":["https://openalex.org/I246010334"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012954193","display_name":"Kehuang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kehuang Li","raw_affiliation_strings":["School of ECE, Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"School of ECE, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083404931"],"corresponding_institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"],"apc_list":null,"apc_paid":null,"fwci":0.8569,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85192659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"489","last_page":"495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.7461751103401184},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7368696331977844},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.6646040678024292},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6428643465042114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5671808123588562},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5322347283363342},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5202630758285522},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5041333436965942},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4968278706073761},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49168139696121216},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4899131655693054},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.4854636788368225},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.4525146782398224},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42232733964920044},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.42157161235809326},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4177970290184021},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4156644344329834},{"id":"https://openalex.org/keywords/figure-of-merit","display_name":"Figure of merit","score":0.4143086373806},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41168704628944397},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16410917043685913},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08084920048713684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461751103401184},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7368696331977844},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.6646040678024292},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6428643465042114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5671808123588562},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5322347283363342},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5202630758285522},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5041333436965942},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4968278706073761},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49168139696121216},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4899131655693054},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.4854636788368225},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.4525146782398224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42232733964920044},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42157161235809326},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4177970290184021},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4156644344329834},{"id":"https://openalex.org/C130277099","wikidata":"https://www.wikidata.org/wiki/Q3676605","display_name":"Figure of merit","level":2,"score":0.4143086373806},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41168704628944397},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16410917043685913},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08084920048713684},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2016.7846308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unipa.it:10447/649501","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/649501","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W14023614","https://openalex.org/W35737003","https://openalex.org/W45736138","https://openalex.org/W185189022","https://openalex.org/W1559678887","https://openalex.org/W2003890417","https://openalex.org/W2013477326","https://openalex.org/W2020057315","https://openalex.org/W2038050265","https://openalex.org/W2053280194","https://openalex.org/W2055667362","https://openalex.org/W2062652351","https://openalex.org/W2080758042","https://openalex.org/W2096234460","https://openalex.org/W2112739286","https://openalex.org/W2114315281","https://openalex.org/W2119466907","https://openalex.org/W2160017196","https://openalex.org/W2160815625","https://openalex.org/W2163314930","https://openalex.org/W2295176673","https://openalex.org/W2951829787","https://openalex.org/W4212863985","https://openalex.org/W4232093537","https://openalex.org/W6600577253","https://openalex.org/W6601392253","https://openalex.org/W6607538539","https://openalex.org/W6633418959","https://openalex.org/W6659848019","https://openalex.org/W6677222910","https://openalex.org/W6683795702","https://openalex.org/W6764454516"],"related_works":["https://openalex.org/W4385957115","https://openalex.org/W2061372042","https://openalex.org/W3047779762","https://openalex.org/W1520030019","https://openalex.org/W2071654592","https://openalex.org/W2088157920","https://openalex.org/W2055545425","https://openalex.org/W2163401555","https://openalex.org/W3104477175","https://openalex.org/W2019022049"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,105],"are":[4,24],"interested":[5],"in":[6,59,81],"boosting":[7],"speech":[8,28,37],"attribute":[9,29,38],"detection":[10,39],"by":[11,110],"formulating":[12],"it":[13],"as":[14],"a":[15,56,77,108],"multi-label":[16,83],"classification":[17],"task,":[18],"and":[19,54],"deep":[20],"neural":[21],"networks":[22],"(DNNs)":[23],"used":[25,79],"to":[26,34,42,70,90],"design":[27],"detectors.":[30],"A":[31,64],"straightforward":[32],"way":[33,67],"tackle":[35],"the":[36,47,60,72,82,86,93,115,130],"task":[40,113],"is":[41,68,76,101],"estimate":[43],"DNN":[44,61,87],"parameters":[45],"using":[46],"mean":[48],"squared":[49],"error":[50],"(MSE)":[51],"loss":[52,88],"function":[53,58,89],"employ":[55],"sigmoid":[57],"output":[62],"nodes.":[63],"more":[65],"principled":[66],"nonetheless":[69],"incorporate":[71],"micro-F1":[73],"measure,":[74],"which":[75],"widely":[78],"metric":[80,94],"classification,":[84],"into":[85],"directly":[91],"improve":[92],"of":[95],"interest":[96],"at":[97],"training":[98],"time.":[99],"Micro-F1":[100],"not":[102],"differentiable,":[103],"yet":[104],"overcome":[106],"such":[107],"problem":[109],"casting":[111],"our":[112,125],"under":[114],"maximal":[116],"figure-of-merit":[117],"(MFoM)":[118],"learning":[119],"framework.":[120],"The":[121],"results":[122],"demonstrate":[123],"that":[124],"MFoM":[126],"approach":[127],"consistently":[128],"outperforms":[129],"baseline":[131],"systems.":[132]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}