{"id":"https://openalex.org/W2748009955","doi":"https://doi.org/10.21437/interspeech.2017-339","title":"Comparison of Non-Parametric Bayesian Mixture Models for Syllable Clustering and Zero-Resource Speech Processing","display_name":"Comparison of Non-Parametric Bayesian Mixture Models for Syllable Clustering and Zero-Resource Speech Processing","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2748009955","doi":"https://doi.org/10.21437/interspeech.2017-339","mag":"2748009955"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-339","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://aaltodoc.aalto.fi/handle/123456789/28857","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048838330","display_name":"Shreyas Seshadri","orcid":"https://orcid.org/0000-0003-1731-3129"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Shreyas Seshadri","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037747779","display_name":"Ulpu Remes","orcid":"https://orcid.org/0000-0003-1435-0207"},"institutions":[{"id":"https://openalex.org/I1323065761","display_name":"Statistics Finland","ror":"https://ror.org/01n1rg855","country_code":"FI","type":"other","lineage":["https://openalex.org/I1323065761"]},{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ulpu Remes","raw_affiliation_strings":["Department of Mathematics and Statistics, University of Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, University of Helsinki, Finland","institution_ids":["https://openalex.org/I1323065761","https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016518233","display_name":"Okko R\u00e4s\u00e4nen","orcid":"https://orcid.org/0000-0002-0537-0946"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Okko R\u00e4s\u00e4nen","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048838330"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64285779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2744","last_page":"2748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","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/T11901","display_name":"Bayesian Methods and Mixture Models","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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":0.7609894275665283},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6988998651504517},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6838380098342896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5753722786903381},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5128017067909241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5048545002937317},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4951445162296295},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.45624226331710815},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.44599488377571106},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41706788539886475},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1386481523513794},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08903825283050537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7609894275665283},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6988998651504517},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6838380098342896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5753722786903381},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5128017067909241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5048545002937317},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4951445162296295},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.45624226331710815},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44599488377571106},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41706788539886475},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1386481523513794},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08903825283050537},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-339","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/28857","is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/28857","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"},{"id":"pmh:oai:helda.helsinki.fi:10138/231768","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/231768","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/28857","is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/28857","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"},"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1967687583","https://openalex.org/W1987971958","https://openalex.org/W1997505733","https://openalex.org/W2016155919","https://openalex.org/W2032943813","https://openalex.org/W2038101708","https://openalex.org/W2044138293","https://openalex.org/W2057007397","https://openalex.org/W2069429561","https://openalex.org/W2087309226","https://openalex.org/W2100768664","https://openalex.org/W2115870554","https://openalex.org/W2121464381","https://openalex.org/W2127498532","https://openalex.org/W2135537007","https://openalex.org/W2145001205","https://openalex.org/W2151967501","https://openalex.org/W2154099718","https://openalex.org/W2166637769","https://openalex.org/W2251025892","https://openalex.org/W2295297373","https://openalex.org/W2398490608","https://openalex.org/W2399576818","https://openalex.org/W2403962673","https://openalex.org/W2468716020","https://openalex.org/W2610013054","https://openalex.org/W2786608204"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W2164162849"],"abstract_inverted_index":{"Zero-resource":[0],"speech":[1,11,35,151],"processing":[2],"(ZS)":[3],"systems":[4,22,40,54,88],"aim":[5],"to":[6,14,178],"learn":[7],"structural":[8],"representations":[9],"of":[10,26,33,62,86,98,113,136,171,182,190],"without":[12],"access":[13],"labeled":[15],"data.":[16],"A":[17],"starting":[18],"point":[19],"for":[20],"these":[21,137],"is":[23,139],"the":[24,30,84,101,111,114,126,129,134,143,180,187],"extraction":[25],"syllable":[27,47,163],"tokens":[28,48],"utilizing":[29],"rhythmic":[31],"structure":[32],"a":[34,161,169,172],"signal.":[36],"Several":[37],"recent":[38],"ZS":[39,87,174],"have":[41,55],"therefore":[42],"focused":[43],"on":[44,82,110],"clustering":[45,164],"such":[46],"into":[49],"linguistically":[50],"meaningful":[51],"units.":[52],"These":[53],"so":[56],"far":[57],"used":[58],"heuristically":[59],"set":[60],"number":[61,108],"clusters,":[63],"which":[64],"can,":[65],"however,":[66],"be":[67,73],"highly":[68],"dataset":[69],"dependent":[70],"and":[71,128,166,185],"cannot":[72],"optimized":[74],"in":[75,142,160,176],"actual":[76],"unsupervised":[77],"settings.":[78],"This":[79],"paper":[80],"focuses":[81],"improving":[83],"flexibility":[85],"using":[89,149],"Bayesian":[90],"non-parametric":[91],"(BNP)":[92],"mixture":[93],"models":[94,103,156],"that":[95],"are":[96,147,157],"capable":[97],"simultaneously":[99],"learning":[100],"cluster":[102,130],"as":[104,106,133,168],"well":[105],"their":[107],"based":[109],"properties":[112],"dataset.":[115],"We":[116],"also":[117],"compare":[118],"different":[119,191],"model":[120,192],"design":[121,193],"choices,":[122],"namely":[123],"priors":[124],"over":[125],"weights":[127],"component":[131],"models,":[132],"impact":[135],"choices":[138],"rarely":[140],"reported":[141],"previous":[144],"studies.":[145],"Experiments":[146],"conducted":[148],"conversational":[150],"from":[152],"several":[153],"languages.":[154],"The":[155],"first":[158],"evaluated":[159],"separate":[162],"task":[165],"then":[167],"part":[170],"full":[173],"system":[175],"order":[177],"examine":[179],"potential":[181],"BNP":[183],"methods":[184],"illuminate":[186],"relative":[188],"importance":[189],"choices.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}