{"id":"https://openalex.org/W2900182167","doi":"https://doi.org/10.1109/iwaenc.2018.8521319","title":"Automatic Detection of Speech Under Cold Using Discriminative Autoencoders and Strength Modeling with Multiple Sub-Dictionary Generation","display_name":"Automatic Detection of Speech Under Cold Using Discriminative Autoencoders and Strength Modeling with Multiple Sub-Dictionary Generation","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2900182167","doi":"https://doi.org/10.1109/iwaenc.2018.8521319","mag":"2900182167"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc.2018.8521319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5010897750","display_name":"Yi-Ying Kao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Ying Kao","raw_affiliation_strings":["Ministry of Justice, Investigation Bureau, R.O.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Justice, Investigation Bureau, R.O.C","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013560320","display_name":"Hsiang-Ping Hsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsiang-Ping Hsu","raw_affiliation_strings":["Ministry of Justice, Investigation Bureau, R.O.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Justice, Investigation Bureau, R.O.C","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034891715","display_name":"Chien-Feng Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-Feng Liao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062621013","display_name":"Hao-Chun Yang","orcid":"https://orcid.org/0000-0003-3724-5055"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hao-Chun Yang","raw_affiliation_strings":["Department of Electrical Engineering, National Tsing Hua University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001894880","display_name":"Jeng-Lin Li","orcid":"https://orcid.org/0000-0002-9261-1524"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeng-Lin Li","raw_affiliation_strings":["Department of Electrical Engineering, National Tsing Hua University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086107623","display_name":"Chi-Chun Lee","orcid":"https://orcid.org/0000-0003-0186-4321"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Chun Lee","raw_affiliation_strings":["Department of Electrical Engineering, National Tsing Hua University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048338308","display_name":"Hung-Shin Lee","orcid":"https://orcid.org/0000-0001-7044-9434"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Shin Lee","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.13011212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"416","last_page":"420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9672999978065491,"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/discriminative-model","display_name":"Discriminative model","score":0.8962811231613159},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7206259965896606},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6725146770477295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6072834134101868},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4747614860534668},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4164612591266632}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8962811231613159},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7206259965896606},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6725146770477295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6072834134101868},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4747614860534668},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4164612591266632}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc.2018.8521319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W147964346","https://openalex.org/W1521781547","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1973681148","https://openalex.org/W2090777335","https://openalex.org/W2101234009","https://openalex.org/W2101285851","https://openalex.org/W2147296978","https://openalex.org/W2150769028","https://openalex.org/W2296527405","https://openalex.org/W2296581541","https://openalex.org/W2405774341","https://openalex.org/W2472925679","https://openalex.org/W2513507089","https://openalex.org/W2517415851","https://openalex.org/W2560025328","https://openalex.org/W2612919868","https://openalex.org/W2717402182","https://openalex.org/W2783111252","https://openalex.org/W2793675140","https://openalex.org/W2964121744","https://openalex.org/W3210141620","https://openalex.org/W6605980550","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6675354045","https://openalex.org/W6697251715","https://openalex.org/W6730583231","https://openalex.org/W7001268321"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0,29],"this":[1,30],"paper":[2,31],"we":[3,32,128],"aim":[4],"to":[5,20,77,160,166],"tackle":[6],"the":[7,12,56,65,74,82,98,105,108,124,167,180],"Cold":[8],"sub-challenge":[9],"proposed":[10],"in":[11,61],"INTERSPEECH":[13],"2017":[14,143,206],"ComParE":[15],"Challenge.":[16],"The":[17,52,90,171],"goal":[18],"is":[19,25,39,55,71,92,148],"determine":[21],"whether":[22],"given":[23],"speech":[24],"under":[26],"cold":[27,111],"condition.":[28],"present":[33],"two":[34,48],"frameworks.":[35],"One":[36],"of":[37,101,110,182],"them":[38],"based":[40,149],"on":[41,135,150,199],"an":[42],"alternative":[43],"neural":[44],"network-based":[45],"autoencoder":[46],"using":[47],"different":[49],"loss":[50,67,69],"functions.":[51],"first":[53],"one":[54],"standard":[57],"reconstruction":[58],"error":[59],"used":[60],"unsupervised":[62],"autoencoder,":[63],"and":[64,107,112,123,132,138,186,197,201],"hinge":[66],"(second":[68],"function)":[70],"incorporated":[72],"into":[73,85],"middle":[75],"layer":[76],"attract":[78],"utterances":[79],"spoken":[80],"by":[81,96,142,205],"same":[83],"condition":[84],"similar":[86],"identity":[87,102],"code":[88],"spaces.":[89],"classification":[91],"then":[93],"carried":[94],"out":[95],"comparing":[97],"cosine":[99],"similarity":[100],"codes":[103],"between":[104],"target":[106],"mean":[109],"non-cold":[113],"utterances.":[114],"With":[115],"a":[116],"simple":[117],"logistic":[118],"regression":[119],"combining":[120],"our":[121],"method":[122],"baseline":[125],"systems":[126],"predictions,":[127],"achieve":[129,195],"65.81":[130],"%":[131],"66%":[133],"UAR":[134],"development":[136,200],"set":[137,140,203],"test":[139,202],"provided":[141,204],"ComParE,":[144],"respectively.":[145,208],"Another":[146],"approach":[147],"strength":[151],"modeling,":[152],"where":[153],"diverse":[154,192],"classifiers'":[155],"confidence":[156],"outputs":[157],"are":[158,174],"concatenated":[159],"original":[161],"feature":[162,172],"space":[163],"as":[164],"input":[165],"support":[168],"vector":[169],"machine.":[170],"representations":[173],"derived":[175],"from":[176],"multiple":[177],"sub-dictionary":[178],"within":[179],"framework":[181],"GMM":[183],"Fisher-vector":[184],"encoding":[185],"eGeMAPS":[187],"functional":[188],"features":[189],"concatenating":[190],"with":[191],"classifiers.":[193],"We":[194],"70.2%":[196],"65.5%":[198],"ComPareE,":[207]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}