{"id":"https://openalex.org/W2641832364","doi":"https://doi.org/10.1109/icassp.2017.7953258","title":"Bayesian phonotactic Language Model for Acoustic Unit Discovery","display_name":"Bayesian phonotactic Language Model for Acoustic Unit Discovery","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2641832364","doi":"https://doi.org/10.1109/icassp.2017.7953258","mag":"2641832364"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5104831405","display_name":"Lucas Ondel","orcid":"https://orcid.org/0000-0003-4512-0471"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lucas Ondel","raw_affiliation_strings":["Brno University of technology, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of technology, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Cernocky","raw_affiliation_strings":["Brno University of technology, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008468618","display_name":"Santosh Kesiraju","orcid":"https://orcid.org/0000-0002-3725-742X"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Santosh Kesiraju","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.494,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83663164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2016","issue":null,"first_page":"5750","last_page":"5754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9951000213623047,"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/bigram","display_name":"Bigram","score":0.8933690190315247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7726998329162598},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6955836415290833},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6926031708717346},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6640883684158325},{"id":"https://openalex.org/keywords/phonotactics","display_name":"Phonotactics","score":0.568110466003418},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5675532221794128},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5665349960327148},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4863746464252472},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.45518797636032104},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.42065420746803284},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.42025241255760193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4059203267097473},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.14000990986824036},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09558859467506409}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.8933690190315247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726998329162598},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6955836415290833},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6926031708717346},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6640883684158325},{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.568110466003418},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5675532221794128},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5665349960327148},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4863746464252472},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.45518797636032104},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.42065420746803284},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.42025241255760193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4059203267097473},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.14000990986824036},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09558859467506409},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W165878654","https://openalex.org/W166614460","https://openalex.org/W943204654","https://openalex.org/W1524333225","https://openalex.org/W1796128977","https://openalex.org/W1967687583","https://openalex.org/W2100768664","https://openalex.org/W2117126688","https://openalex.org/W2120636621","https://openalex.org/W2127498532","https://openalex.org/W2154099718","https://openalex.org/W2347098582","https://openalex.org/W2564058731","https://openalex.org/W3127686677","https://openalex.org/W6606723699","https://openalex.org/W6631362777","https://openalex.org/W6638159135","https://openalex.org/W6675022971","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W1518493474","https://openalex.org/W2102951823","https://openalex.org/W2151852520","https://openalex.org/W1589286968","https://openalex.org/W2105076537","https://openalex.org/W1700330385","https://openalex.org/W2002221802","https://openalex.org/W2041167939","https://openalex.org/W2250909759","https://openalex.org/W2562995433"],"abstract_inverted_index":{"Recent":[0],"work":[1],"on":[2,56,150],"Acoustic":[3],"Unit":[4],"Discovery":[5],"(AUD)":[6],"has":[7],"led":[8],"to":[9,30,43,90],"the":[10,19,22,25,59,68,92,97,103,120,136],"development":[11],"of":[12,24,58,67,77,94,110,118],"a":[13,34,49,74,86,139],"non-parametric":[14],"Bayesian":[15],"phone-loop":[16,88,99,105],"model":[17,46,64,89,137],"where":[18],"prior":[20],"over":[21],"probability":[23],"phone-like":[26],"units":[27],"is":[28,100],"assumed":[29],"be":[31],"sampled":[32],"from":[33,102],"Dirichlet":[35],"Process":[36],"(DP).":[37],"In":[38],"this":[39,45,81],"work,":[40],"we":[41,83,127],"propose":[42],"improve":[44],"by":[47],"incorporating":[48],"Hierarchical":[50],"Pitman-Yor":[51],"based":[52],"bigram":[53,98],"Language":[54],"Model":[55],"top":[57],"units'":[60],"transitions.":[61],"This":[62],"new":[63],"makes":[65],"use":[66],"phonotactic":[69],"context":[70],"information":[71],"but":[72],"assumes":[73],"fixed":[75],"number":[76,93],"units.":[78],"To":[79],"remedy":[80],"limitation":[82],"first":[84],"train":[85],"DP":[87,104],"infer":[91],"units,":[95],"then,":[96],"initialized":[101],"and":[106],"trained":[107,149],"until":[108],"convergence":[109],"its":[111],"parameters.":[112],"Results":[113],"show":[114,128],"an":[115,145],"absolute":[116],"improvement":[117],"1\u20132%on":[119],"Normalized":[121],"Mutual":[122],"Information":[123],"(NMI)":[124],"metric.":[125],"Furthermore,":[126],"that,":[129],"combined":[130],"with":[131],"Multilingual":[132],"Bottleneck":[133],"(MBN)":[134],"features":[135],"yields":[138],"same":[140],"or":[141],"higher":[142],"NMI":[143],"as":[144],"English":[146],"phone":[147],"recogniser":[148],"TIMIT.":[151]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}