{"id":"https://openalex.org/W2737331776","doi":"https://doi.org/10.1109/taslp.2017.2729024","title":"Unsupervised Iterative Deep Learning of Speech Features and Acoustic Tokens with Applications to Spoken Term Detection","display_name":"Unsupervised Iterative Deep Learning of Speech Features and Acoustic Tokens with Applications to Spoken Term Detection","publication_year":2017,"publication_date":"2017-07-19","ids":{"openalex":"https://openalex.org/W2737331776","doi":"https://doi.org/10.1109/taslp.2017.2729024","mag":"2737331776"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2729024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2729024","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1707.05315","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102330488","display_name":"Cheng-Tao Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Tao Chung","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028459162","display_name":"Cheng\u2010Yu Tsai","orcid":"https://orcid.org/0000-0001-6150-4577"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Yu Tsai","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","[Graduate Inst. of Commun. Eng., Nat. Taiwan Univ., Taipei, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[Graduate Inst. of Commun. Eng., Nat. Taiwan Univ., Taipei, Taiwan]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024856346","display_name":"Chia-Hsiang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Hsiang Liu","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044010123","display_name":"Lin-shan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lin-Shan Lee","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan","Department of electrical engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Department of electrical engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.2273,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67828063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"25","issue":"10","first_page":"1914","last_page":"1928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"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":0.9882000088691711,"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":0.8536115288734436},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.804984450340271},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5872511863708496},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5847066044807434},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5715524554252625},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5483452081680298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5150842070579529},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5006580352783203},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.48782017827033997},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.42476779222488403},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42030495405197144},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34943366050720215},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34605857729911804},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3347797095775604},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3309212327003479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8536115288734436},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.804984450340271},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5872511863708496},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5847066044807434},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5715524554252625},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5483452081680298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5150842070579529},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5006580352783203},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.48782017827033997},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.42476779222488403},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42030495405197144},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34943366050720215},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34605857729911804},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3347797095775604},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3309212327003479},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2017.2729024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2729024","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1707.05315","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.05315","pdf_url":"https://arxiv.org/pdf/1707.05315","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.1707.05315","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1707.05315","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2737331776","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1707.05315","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.05315","pdf_url":"https://arxiv.org/pdf/1707.05315","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2737331776.pdf"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1545920196","https://openalex.org/W1577418252","https://openalex.org/W1970890968","https://openalex.org/W1975126845","https://openalex.org/W1975728937","https://openalex.org/W2014012135","https://openalex.org/W2033178790","https://openalex.org/W2053306448","https://openalex.org/W2057007397","https://openalex.org/W2064675550","https://openalex.org/W2078769636","https://openalex.org/W2105016867","https://openalex.org/W2116422968","https://openalex.org/W2127176025","https://openalex.org/W2141362318","https://openalex.org/W2154093685","https://openalex.org/W2155893237","https://openalex.org/W2159329531","https://openalex.org/W2160815625","https://openalex.org/W2398490608","https://openalex.org/W2513125788","https://openalex.org/W2518166530","https://openalex.org/W2963684067","https://openalex.org/W4240592325","https://openalex.org/W6601311673","https://openalex.org/W6602092770","https://openalex.org/W6602762607","https://openalex.org/W6606306245","https://openalex.org/W6607775107","https://openalex.org/W6610841746","https://openalex.org/W6631362777","https://openalex.org/W6638159135","https://openalex.org/W6639619044","https://openalex.org/W6640828828","https://openalex.org/W6675022971","https://openalex.org/W6676246739","https://openalex.org/W6677461952","https://openalex.org/W6687014475","https://openalex.org/W6691362072","https://openalex.org/W6712202099","https://openalex.org/W6712444837","https://openalex.org/W6712553779","https://openalex.org/W6712960331","https://openalex.org/W6712968304","https://openalex.org/W6713016582","https://openalex.org/W6713256719","https://openalex.org/W6713378787","https://openalex.org/W6713463742","https://openalex.org/W6713678193","https://openalex.org/W6713745070","https://openalex.org/W6713823255","https://openalex.org/W6973666849"],"related_works":["https://openalex.org/W2259232214","https://openalex.org/W3095049654","https://openalex.org/W3169122250","https://openalex.org/W2116422968","https://openalex.org/W2795493431","https://openalex.org/W1499245496","https://openalex.org/W3029023844","https://openalex.org/W2567070270","https://openalex.org/W3015797571","https://openalex.org/W3129009457","https://openalex.org/W1583772995","https://openalex.org/W2961016059","https://openalex.org/W3091088345","https://openalex.org/W2009388533","https://openalex.org/W2182155920","https://openalex.org/W3044386551","https://openalex.org/W2188924248","https://openalex.org/W2567545547","https://openalex.org/W1983300351","https://openalex.org/W1549275533"],"abstract_inverted_index":{"In":[0],"this":[1,148],"paper,":[2],"we":[3],"aim":[4],"to":[5,115],"automatically":[6],"discover":[7],"high-quality":[8],"frame-level":[9,99,133],"speech":[10,18,134],"features":[11,103,135],"and":[12,68,118,131,162,175],"acoustic":[13,22,34,41,59,100,128],"tokens":[14,35,60,198],"directly":[15],"from":[16,36,105],"unlabeled":[17],"data.":[19],"A":[20],"multigranular":[21,127],"tokenizer":[23],"(MAT)":[24],"was":[25,178,203],"proposed":[26],"for":[27,64,195],"automatic":[28],"discovery":[29],"of":[30,33,49,58,81,90,183,185],"multiple":[31,79],"sets":[32,57,80,130],"the":[37,52,65,69,88,106,112,116,119,123,132,141,150,160,166,191,196,200],"given":[38,66],"corpus.":[39],"Each":[40],"token":[42,82,129],"set":[43,48,182],"is":[44],"specified":[45],"by":[46],"a":[47,91,181],"hyperparameters":[50],"describing":[51],"model":[53],"configuration.":[54],"These":[55],"different":[56,62],"carry":[61],"characteristics":[63],"corpus":[67],"language":[70],"behind":[71],"and,":[72],"thus,":[73],"can":[74,136],"be":[75,137],"mutually":[76],"reinforced.":[77],"The":[78,126,155],"labels":[83],"are":[84,108],"then":[85,109],"used":[86,110],"as":[87,111],"targets":[89],"multitarget":[92],"deep":[93,143,152],"neural":[94,153],"network":[95],"(MDNN)":[96],"trained":[97],"on":[98,190],"features.":[101],"Bottleneck":[102],"extracted":[104],"MDNN":[107,120],"feedback":[113],"input":[114],"MAT":[117,151],"itself":[121],"in":[122,140,165],"next":[124],"iteration.":[125],"iteratively":[138],"optimized":[139],"iterative":[142],"learning":[144],"framework.":[145],"We":[146],"call":[147],"framework":[149],"network.":[154],"results":[156],"were":[157],"evaluated":[158],"using":[159],"metrics":[161],"corpora":[163],"defined":[164],"Zero":[167],"Resource":[168],"Speech":[169],"Challenge":[170],"organized":[171],"at":[172],"Interspeech":[173],"2015,":[174],"improved":[176],"performance":[177],"obtained":[179],"with":[180],"experiments":[184],"query-by-example":[186],"spoken":[187],"term":[188],"detection":[189],"same":[192],"corpora.":[193],"Visualization":[194],"discovered":[197],"against":[199],"English":[201],"phonemes":[202],"also":[204],"shown.":[205]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}