{"id":"https://openalex.org/W2921843068","doi":"https://doi.org/10.23919/apsipa.2018.8659619","title":"Unsupervised Pattern Discovery from Thematic Speech Archives Based on Multilingual Bottleneck Features","display_name":"Unsupervised Pattern Discovery from Thematic Speech Archives Based on Multilingual Bottleneck Features","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921843068","doi":"https://doi.org/10.23919/apsipa.2018.8659619","mag":"2921843068"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659619","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.01986","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Man-Ling Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Man-Ling Sung","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siyuan Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Feng","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.1692,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63607728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1448","last_page":"1455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9957000017166138,"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/bottleneck","display_name":"Bottleneck","score":0.6033999919891357},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5181000232696533},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4645000100135803},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.46239998936653137},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.43959999084472656},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4343000054359436},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42260000109672546},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.42260000109672546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8377000093460083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7110000252723694},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6033999919891357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5214999914169312},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5181000232696533},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4645000100135803},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.46239998936653137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45730000734329224},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.42260000109672546},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.30630001425743103},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/apsipa.2018.8659619","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.01986","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01986","pdf_url":"https://arxiv.org/pdf/2011.01986","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.01986","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01986","pdf_url":"https://arxiv.org/pdf/2011.01986","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1545920196","https://openalex.org/W1778492285","https://openalex.org/W1967924372","https://openalex.org/W1970890968","https://openalex.org/W1975728937","https://openalex.org/W2016381774","https://openalex.org/W2020607164","https://openalex.org/W2024490156","https://openalex.org/W2025198378","https://openalex.org/W2057007397","https://openalex.org/W2072563337","https://openalex.org/W2079460648","https://openalex.org/W2087064593","https://openalex.org/W2110589736","https://openalex.org/W2114347655","https://openalex.org/W2126203737","https://openalex.org/W2147768505","https://openalex.org/W2167845555","https://openalex.org/W2401464865","https://openalex.org/W2406504561","https://openalex.org/W2468716020","https://openalex.org/W2594951208","https://openalex.org/W2627092829","https://openalex.org/W2747917286","https://openalex.org/W2962826786","https://openalex.org/W2963266252","https://openalex.org/W2963499843","https://openalex.org/W6631362777","https://openalex.org/W6638159135","https://openalex.org/W6640828828","https://openalex.org/W6677803786","https://openalex.org/W6696934422","https://openalex.org/W6697293080","https://openalex.org/W6712553779","https://openalex.org/W6713678193","https://openalex.org/W6748489002","https://openalex.org/W6973666849"],"related_works":[],"abstract_inverted_index":{"The":[0,26,71],"present":[1],"study":[2],"tackles":[3],"the":[4,89,145,158],"problem":[5,27],"of":[6,29,35,46,81],"automatically":[7],"discovering":[8],"spoken":[9,106],"keywords":[10,107],"from":[11,104,157],"untranscribed":[12,86],"audio":[13,96],"archives":[14],"without":[15],"requiring":[16],"word-by-word":[17],"speech":[18,22,36,83,126,132],"transcription":[19],"by":[20,64,75,100,111,124],"automatic":[21],"recognition":[23],"(ASR)":[24],"technology.":[25],"is":[28,98,128,148],"practical":[30],"significance":[31],"in":[32,67],"many":[33],"applications":[34],"analytics,":[37],"including":[38],"those":[39],"concerning":[40],"low-resource":[41],"languages,":[42],"and":[43,48,61,77,134,155],"large":[44],"amount":[45],"multilingual":[47,125],"multi-genre":[49],"data.":[50,87],"We":[51],"propose":[52],"a":[53,79,94,101,119],"two-stage":[54],"approach,":[55],"which":[56,105],"comprises":[57],"unsupervised":[58,116],"acoustic":[59,68,92,117],"modeling":[60,78],"decoding,":[62],"followed":[63],"pattern":[65],"mining":[66,113],"unit":[69],"sequences.":[70],"whole":[72],"process":[73],"starts":[74],"deriving":[76],"set":[80],"subword-level":[82],"units":[84],"with":[85],"With":[88],"unsupervisedly":[90],"trained":[91,123],"models,":[93],"given":[95],"archive":[97],"represented":[99],"pseudo":[102],"transcription,":[103],"can":[108],"be":[109],"discovered":[110],"string":[112],"algorithms.":[114],"For":[115],"modeling,":[118],"deep":[120],"neural":[121],"network":[122],"corpora":[127],"used":[129],"to":[130,150],"generate":[131],"segmentation":[133],"compute":[135],"bottleneck":[136],"features":[137],"for":[138],"segment":[139],"clustering.":[140],"Experimental":[141],"results":[142],"show":[143],"that":[144],"proposed":[146],"system":[147],"able":[149],"effectively":[151],"extract":[152],"topic-related":[153],"words":[154],"phrases":[156],"lecture":[159],"recordings":[160],"on":[161],"MIT":[162],"OpenCourse":[163],"Ware.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-03-22T00:00:00"}