{"id":"https://openalex.org/W4221143043","doi":"https://doi.org/10.21437/interspeech.2022-10474","title":"Chain-based Discriminative Autoencoders for Speech Recognition","display_name":"Chain-based Discriminative Autoencoders for Speech Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221143043","doi":"https://doi.org/10.21437/interspeech.2022-10474"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10474","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10474","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","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/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":true,"raw_author_name":"Hung-Shin Lee","raw_affiliation_strings":["Institute of Information Science, Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075928107","display_name":"Pin-Tuan Huang","orcid":null},"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":"Pin-Tuan Huang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002404521","display_name":"Yao-Fei Cheng","orcid":null},"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":"Yao-Fei Cheng","raw_affiliation_strings":["Institute of Information Science, Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5048338308"],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02173871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2078","last_page":"2082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.8288675546646118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7863996028900146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7674332857131958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5681865215301514},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45122379064559937},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44602999091148376}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8288675546646118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863996028900146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7674332857131958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5681865215301514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45122379064559937},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44602999091148376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10474","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10474","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W21300200","https://openalex.org/W1544785557","https://openalex.org/W1598508708","https://openalex.org/W1901129140","https://openalex.org/W2042141988","https://openalex.org/W2057826000","https://openalex.org/W2062164080","https://openalex.org/W2078528584","https://openalex.org/W2096653978","https://openalex.org/W2121973264","https://openalex.org/W2131342762","https://openalex.org/W2150769028","https://openalex.org/W2164502538","https://openalex.org/W2168379380","https://openalex.org/W2173629880","https://openalex.org/W2213952365","https://openalex.org/W2290318471","https://openalex.org/W2291456664","https://openalex.org/W2292733088","https://openalex.org/W2295627154","https://openalex.org/W2402146185","https://openalex.org/W2404126548","https://openalex.org/W2405774341","https://openalex.org/W2408713104","https://openalex.org/W2514741789","https://openalex.org/W2630683241","https://openalex.org/W2729190387","https://openalex.org/W2745772944","https://openalex.org/W2888867175","https://openalex.org/W2889282842","https://openalex.org/W2921824436","https://openalex.org/W2962780374","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2972412503","https://openalex.org/W2972555663","https://openalex.org/W2972664737","https://openalex.org/W3015312544","https://openalex.org/W3097777922","https://openalex.org/W4236328885"],"related_works":["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/W2082783427","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"our":[1,176],"previous":[2],"work,":[3],"we":[4,77,119],"proposed":[5],"a":[6,85,110],"discriminative":[7],"autoencoder":[8],"(DcAE)":[9],"for":[10],"speech":[11,32,36,117,143,148,155,160],"recognition.DcAE":[12],"combines":[13],"two":[14,134],"training":[15],"schemes":[16],"into":[17,163],"one.First,":[18],"since":[19],"DcAE":[20,107,112,177],"aims":[21],"to":[22,115,123],"learn":[23],"encoderdecoder":[24],"mappings,":[25],"the":[26,30,34,40,50,65,137,140,145,150,153,157,164,169],"squared":[27],"error":[28,138,151],"between":[29,53,97,139,152],"reconstructed":[31,141],"and":[33,57,94,100,125,131,144,149,156,171],"input":[35,146],"is":[37,61,104,108],"minimized.Second,":[38],"in":[39,129],"code":[41],"layer,":[42],"frame-based":[43],"phonetic":[44],"embeddings":[45],"are":[46,161],"obtained":[47],"by":[48,68],"minimizing":[49],"categorical":[51,92],"cross-entropy":[52,93],"ground":[54,98],"truth":[55,99],"labels":[56],"predicted":[58,101],"triphone-state":[59,102],"scores.DcAE":[60],"developed":[62],"based":[63],"on":[64,168],"Kaldi":[66],"toolkit":[67],"treating":[69],"various":[70],"TDNN":[71],"models":[72,178],"as":[73],"encoders.In":[74],"this":[75],"paper,":[76],"further":[78,120],"propose":[79],"three":[80],"new":[81,86],"versions":[82],"of":[83],"DcAE.First,":[84],"objective":[87,165],"function":[88],"that":[89,175],"considers":[90],"both":[91,136],"mutual":[95],"information":[96],"sequences":[103],"used.The":[105],"resulting":[106,128],"called":[109],"chain-based":[111],"(c-DcAE).For":[113],"application":[114],"robust":[116],"recognition,":[118],"extend":[121],"c-DcAE":[122],"hierarchical":[124],"parallel":[126],"structures,":[127],"hc-DcAE":[130],"pc-DcAE.In":[132],"these":[133],"models,":[135],"noisy":[142,147],"enhanced":[154],"reference":[158],"clean":[159],"taken":[162],"function.Experimental":[166],"results":[167],"WSJ":[170],"Aurora-4":[172],"corpora":[173],"show":[174],"outperform":[179],"baseline":[180],"systems.":[181]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}