{"id":"https://openalex.org/W3145811386","doi":"https://doi.org/10.21437/interspeech.2021-1664","title":"Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation","display_name":"Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3145811386","doi":"https://doi.org/10.21437/interspeech.2021-1664","mag":"3145811386"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1664","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.00994","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/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Siyuan Feng","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr \u017belasko","raw_affiliation_strings":["Johns Hopkins University, Baltimore, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069488212","display_name":"Laureano Moro-Vel\u00e1zquez","orcid":"https://orcid.org/0000-0002-3033-7005"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laureano Moro-Vel\u00e1zquez","raw_affiliation_strings":["Johns Hopkins University, Baltimore, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1362,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50931998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1534","last_page":"1538"},"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/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":0.9988999962806702,"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/discriminative-model","display_name":"Discriminative model","score":0.8802458047866821},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8010275363922119},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6204013228416443},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6103169322013855},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5854793787002563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5495253801345825},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5470933318138123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5279974937438965},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49508967995643616},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.46966683864593506},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45675453543663025},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4555252492427826},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.44484737515449524},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43916991353034973},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.42992621660232544},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11019450426101685}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8802458047866821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010275363922119},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6204013228416443},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6103169322013855},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5854793787002563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5495253801345825},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5470933318138123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5279974937438965},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49508967995643616},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.46966683864593506},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45675453543663025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4555252492427826},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.44484737515449524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43916991353034973},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.42992621660232544},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11019450426101685},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2021-1664","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.00994","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.00994","pdf_url":"https://arxiv.org/pdf/2104.00994","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"},{"id":"mag:3145811386","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.00994.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:tudelft.nl:uuid:f9cdc9ff-b495-46af-b48e-a99fc28333c7","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:f9cdc9ff-b495-46af-b48e-a99fc28333c7","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"},{"id":"doi:10.48550/arxiv.2104.00994","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.00994","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.00994","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.00994","pdf_url":"https://arxiv.org/pdf/2104.00994","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W66627554","https://openalex.org/W1524333225","https://openalex.org/W1557247526","https://openalex.org/W1631260214","https://openalex.org/W1957665339","https://openalex.org/W1975728937","https://openalex.org/W2059652594","https://openalex.org/W2100768664","https://openalex.org/W2101234009","https://openalex.org/W2147768505","https://openalex.org/W2327501763","https://openalex.org/W2347098582","https://openalex.org/W2347145335","https://openalex.org/W2399576818","https://openalex.org/W2514741789","https://openalex.org/W2594951208","https://openalex.org/W2750248772","https://openalex.org/W2762715843","https://openalex.org/W2787447541","https://openalex.org/W2895297209","https://openalex.org/W2950414763","https://openalex.org/W2962693497","https://openalex.org/W2963620343","https://openalex.org/W2963678298","https://openalex.org/W2963799213","https://openalex.org/W2964169922","https://openalex.org/W2972574141","https://openalex.org/W2972794572","https://openalex.org/W2972943112","https://openalex.org/W2973026522","https://openalex.org/W2995181338","https://openalex.org/W2996383576","https://openalex.org/W3016181583","https://openalex.org/W3025286576","https://openalex.org/W3044483536","https://openalex.org/W3045485643","https://openalex.org/W3093096176","https://openalex.org/W3094197178","https://openalex.org/W3095361818","https://openalex.org/W3095732712","https://openalex.org/W3100202343","https://openalex.org/W3104842308"],"related_works":["https://openalex.org/W3196459653","https://openalex.org/W2787447541","https://openalex.org/W1963627370","https://openalex.org/W2949510815","https://openalex.org/W2486205537","https://openalex.org/W134006180","https://openalex.org/W2747943889","https://openalex.org/W2100768664","https://openalex.org/W2594951208","https://openalex.org/W1967924372","https://openalex.org/W2296452459","https://openalex.org/W2786902352","https://openalex.org/W2626212216","https://openalex.org/W1942713348","https://openalex.org/W3003168082","https://openalex.org/W2785860501","https://openalex.org/W2906122999","https://openalex.org/W2963720603","https://openalex.org/W2950523597","https://openalex.org/W2801798988"],"abstract_inverted_index":{"This":[0],"paper":[1],"tackles":[2],"automatically":[3],"discovering":[4],"phone-like":[5,44],"acoustic":[6,49],"units":[7],"(AUD)":[8],"from":[9,181],"unlabeled":[10],"speech":[11,104],"data.":[12],"Past":[13],"studies":[14],"usually":[15],"proposed":[16,57],"single-step":[17],"approaches.":[18],"We":[19],"propose":[20],"a":[21,28,55,70,77,82,114,168],"two-stage":[22],"approach:":[23],"the":[24,33,39,47,52,60,90,102,140,151,163,175],"first":[25,53],"stage":[26,35],"learns":[27],"subword-discriminative":[29,83],"feature":[30,108],"representation":[31,41,84],"and":[32,42,97,133,148,160],"second":[34,91],"applies":[36],"clustering":[37],"to":[38,80,100],"learned":[40],"obtains":[43],"clusters":[45],"as":[46,106],"discovered":[48],"units.":[50],"In":[51,89],"stage,":[54,92],"recently":[56],"method":[58],"in":[59,127,143,149],"task":[61],"of":[62,156],"unsupervised":[63],"subword":[64],"modeling":[65],"is":[66,86,95],"improved":[67,138,182],"by":[68],"replacing":[69],"monolingual":[71,141],"out-of-domain":[72],"(OOD)":[73],"ASR":[74,137,142],"system":[75],"with":[76,159],"multilingual":[78,136],"one":[79],"create":[81],"that":[85,121,174],"more":[87],"language-independent.":[88],"segment-level":[93],"k-means":[94],"adopted,":[96],"two":[98],"methods":[99],"represent":[101],"variable-length":[103],"segments":[105],"fixed-dimension":[107],"vectors":[109],"are":[110],"compared.":[111],"Experiments":[112],"on":[113],"very":[115],"low-resource":[116],"Mboshi":[117],"language":[118],"corpus":[119],"show":[120],"our":[122,157],"approach":[123,177],"outperforms":[124],"state-of-the-art":[125],"AUD":[126],"both":[128],"normalized":[129],"mutual":[130],"information":[131],"(NMI)":[132],"F-score.":[134],"The":[135],"upon":[139],"providing":[144],"OOD":[145],"phone":[146,152,165,183],"labels":[147],"estimating":[150],"boundaries.":[153],"A":[154],"comparison":[155],"systems":[158],"without":[161],"knowing":[162],"ground-truth":[164],"boundaries":[166],"showed":[167],"16%":[169],"NMI":[170],"performance":[171],"gap,":[172],"suggesting":[173],"current":[176],"can":[178],"significantly":[179],"benefit":[180],"boundary":[184],"estimation.":[185]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2022-07-25T00:00:00"}