{"id":"https://openalex.org/W2949510815","doi":"https://doi.org/10.21437/interspeech.2019-1338","title":"Improving Unsupervised Subword Modeling via Disentangled Speech Representation Learning and Transformation","display_name":"Improving Unsupervised Subword Modeling via Disentangled Speech Representation Learning and Transformation","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2949510815","doi":"https://doi.org/10.21437/interspeech.2019-1338","mag":"2949510815"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1338","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.07245","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053373302","display_name":"Siyuan Feng","orcid":"https://orcid.org/0000-0003-2531-8480"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Siyuan Feng","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.1277,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83524574,"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":"281","last_page":"285"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.8066359758377075},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6016550064086914},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5984762907028198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5417746305465698},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5211620330810547},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4622134566307068},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45733126997947693},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4210345149040222}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8066359758377075},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6016550064086914},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5984762907028198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5417746305465698},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5211620330810547},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4622134566307068},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45733126997947693},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4210345149040222},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-1338","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.07245","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.07245","pdf_url":"https://arxiv.org/pdf/1906.07245","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:1906.07245","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.07245","pdf_url":"https://arxiv.org/pdf/1906.07245","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":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1975728937","https://openalex.org/W2025482506","https://openalex.org/W2106284094","https://openalex.org/W2128032727","https://openalex.org/W2345811097","https://openalex.org/W2483390977","https://openalex.org/W2513125788","https://openalex.org/W2758785877","https://openalex.org/W2767122664","https://openalex.org/W2786608204","https://openalex.org/W2786902352","https://openalex.org/W2787447541","https://openalex.org/W2889228998","https://openalex.org/W2914746235","https://openalex.org/W2962689740","https://openalex.org/W2963134917","https://openalex.org/W2963618559","https://openalex.org/W2963620343","https://openalex.org/W2964121744","https://openalex.org/W2964245029","https://openalex.org/W4298028408","https://openalex.org/W4300047444"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W3174759195","https://openalex.org/W3167013339","https://openalex.org/W4287121366","https://openalex.org/W60493759","https://openalex.org/W4308619659","https://openalex.org/W3213069564","https://openalex.org/W4378421684","https://openalex.org/W4294203825","https://openalex.org/W1505616161"],"abstract_inverted_index":{"This":[0],"study":[1],"tackles":[2],"unsupervised":[3],"subword":[4,161],"modeling":[5],"in":[6,34,44,62,91,133,156],"the":[7,74,140],"zero-resource":[8],"scenario,":[9],"learning":[10],"frame-level":[11],"speech":[12,23],"representation":[13],"that":[14,120],"is":[15,30],"phonetically":[16],"discriminative":[17],"and":[18,50,86,103,111,126,135,160],"speaker-invariant,":[19],"using":[20],"only":[21],"untranscribed":[22],"for":[24],"target":[25],"languages.":[26],"Frame":[27],"label":[28,60],"acquisition":[29,61],"an":[31],"essential":[32],"step":[33],"solving":[35],"this":[36],"problem.":[37],"High":[38],"quality":[39],"frame":[40,59,109,158],"labels":[41],"should":[42],"be":[43],"good":[45],"consistency":[46],"with":[47],"golden":[48],"transcriptions":[49],"robust":[51],"to":[52,57,82,107,139],"speaker":[53,87,97],"variation.":[54],"We":[55],"propose":[56],"improve":[58],"our":[63,121],"previously":[64],"adopted":[65],"deep":[66],"neural":[67],"network-bottleneck":[68],"feature":[69],"(DNN-BNF)":[70],"architecture":[71],"by":[72],"applying":[73,145],"factorized":[75],"hierarchical":[76],"variational":[77],"autoencoder":[78],"(FHVAE).":[79],"FHVAEs":[80],"learn":[81],"disentangle":[83],"linguistic":[84],"content":[85],"identity":[88],"information":[89],"encoded":[90],"speech.":[92],"By":[93],"discarding":[94],"or":[95],"unifying":[96],"information,":[98],"speaker-invariant":[99],"features":[100],"are":[101],"learned":[102],"fed":[104],"as":[105],"inputs":[106],"DPGMM":[108],"clustering":[110],"DNN-BNF":[112,142],"training.":[113],"Experiments":[114],"conducted":[115],"on":[116],"ZeroSpeech":[117],"2017":[118],"show":[119],"proposed":[122,148],"approaches":[123,149],"achieve":[124],"$2.4\\%$":[125],"$0.6\\%$":[127],"absolute":[128],"ABX":[129],"error":[130],"rate":[131],"reductions":[132],"across-":[134],"within-speaker":[136],"conditions,":[137],"comparing":[138],"baseline":[141],"system":[143],"without":[144],"FHVAEs.":[146],"Our":[147],"significantly":[150],"outperform":[151],"vocal":[152],"tract":[153],"length":[154],"normalization":[155],"improving":[157],"labeling":[159],"modeling.":[162]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2019-06-27T00:00:00"}