{"id":"https://openalex.org/W2785860501","doi":"https://doi.org/10.1109/asru.2017.8269014","title":"Unsupervised HMM posteriograms for language independent acoustic modeling in zero resource conditions","display_name":"Unsupervised HMM posteriograms for language independent acoustic modeling in zero resource conditions","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2785860501","doi":"https://doi.org/10.1109/asru.2017.8269014","mag":"2785860501"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8269014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8269014","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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/A5110544676","display_name":"Tabish Ansari","orcid":"https://orcid.org/0009-0003-8412-1247"},"institutions":[{"id":"https://openalex.org/I4210110448","display_name":"Learning Through an Expanded Arts Program","ror":"https://ror.org/01yq8nk56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210110448"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"T K Ansari","raw_affiliation_strings":["Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab","institution_ids":["https://openalex.org/I4210110448"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082530526","display_name":"Rajath Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110448","display_name":"Learning Through an Expanded Arts Program","ror":"https://ror.org/01yq8nk56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210110448"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajath Kumar","raw_affiliation_strings":["Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab","institution_ids":["https://openalex.org/I4210110448"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058385222","display_name":"Sonali Singh","orcid":"https://orcid.org/0000-0002-5498-5744"},"institutions":[{"id":"https://openalex.org/I4210110448","display_name":"Learning Through an Expanded Arts Program","ror":"https://ror.org/01yq8nk56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210110448"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sonali Singh","raw_affiliation_strings":["Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab","institution_ids":["https://openalex.org/I4210110448"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[{"id":"https://openalex.org/I4210110448","display_name":"Learning Through an Expanded Arts Program","ror":"https://ror.org/01yq8nk56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210110448"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab","institution_ids":["https://openalex.org/I4210110448"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103371372","display_name":"Susheela Devi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110448","display_name":"Learning Through an Expanded Arts Program","ror":"https://ror.org/01yq8nk56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210110448"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susheela Devi","raw_affiliation_strings":["Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Learning and Extraction of Acoustic Patterns (LEAP) Lab","institution_ids":["https://openalex.org/I4210110448"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5110544676"],"corresponding_institution_ids":["https://openalex.org/I4210110448"],"apc_list":null,"apc_paid":null,"fwci":2.0764,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.90525755,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"762","last_page":"768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9986000061035156,"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/T11309","display_name":"Music and Audio Processing","score":0.9958999752998352,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9075942039489746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7907732725143433},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6630052924156189},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6226677298545837},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.591077983379364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5390893816947937},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5328256487846375},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5232597589492798},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5003018379211426},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46833300590515137},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4384418725967407},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38238242268562317},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.27650466561317444},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22193163633346558}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9075942039489746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907732725143433},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6630052924156189},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6226677298545837},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.591077983379364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5390893816947937},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5328256487846375},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5232597589492798},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5003018379211426},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46833300590515137},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4384418725967407},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38238242268562317},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27650466561317444},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22193163633346558},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2017.8269014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8269014","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai::74513","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W330298975","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1560013842","https://openalex.org/W1796128977","https://openalex.org/W1970890968","https://openalex.org/W2041823554","https://openalex.org/W2078769636","https://openalex.org/W2086115904","https://openalex.org/W2095458199","https://openalex.org/W2115008841","https://openalex.org/W2117041980","https://openalex.org/W2126203737","https://openalex.org/W2127982613","https://openalex.org/W2152175008","https://openalex.org/W2286443923","https://openalex.org/W2335112305","https://openalex.org/W2396043527","https://openalex.org/W2404799143","https://openalex.org/W2406349064","https://openalex.org/W2786608204","https://openalex.org/W2787223168","https://openalex.org/W2963620343","https://openalex.org/W6631362777","https://openalex.org/W6633431331","https://openalex.org/W6638159135","https://openalex.org/W6682825348","https://openalex.org/W6695606915","https://openalex.org/W6712202099","https://openalex.org/W6713256719","https://openalex.org/W6713745070","https://openalex.org/W6973666849"],"related_works":["https://openalex.org/W2048014685","https://openalex.org/W2370972896","https://openalex.org/W1494724239","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2129812225","https://openalex.org/W2032826752","https://openalex.org/W4290708361"],"abstract_inverted_index":{"The":[0,22,76,101,150],"task":[1],"of":[2,29,64,78,129,198,228],"language":[3,54,84,216,231],"independent":[4,55,85,232],"acoustic":[5,30,73,86],"unit":[6,74],"modeling":[7,224],"in":[8,52,118,172],"unlabeled":[9],"raw":[10],"speech":[11],"(zero-resource":[12],"setting)":[13],"has":[14],"gained":[15],"significant":[16,186],"interest":[17],"over":[18,188],"the":[19,27,37,62,79,83,127,133,141,146,160,173,179,189,211,214,222],"recent":[20],"years.":[21],"main":[23],"challenge":[24,148],"here":[25],"is":[26,104,156,217,226],"extraction":[28],"representations":[31,51],"that":[32,178],"elicit":[33],"good":[34],"similarity":[35],"between":[36],"same":[38],"words":[39],"or":[40],"linguistic":[41],"tokens":[42],"spoken":[43],"by":[44],"different":[45],"speakers":[46],"and":[47,162,204],"to":[48,107],"derive":[49],"these":[50],"a":[53,91,109,119],"manner.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,131,176],"explore":[61],"use":[63,132],"Hidden":[65],"Markov":[66],"Model":[67,99],"(HMM)":[68],"based":[69,182],"posteriograms":[70],"for":[71,145,158,200,206],"unsupervised":[72],"modeling.":[75],"states":[77],"HMM":[80,103,136,181],"(which":[81],"represent":[82],"units)":[87],"are":[88,115],"initialized":[89],"using":[90,192],"Gaussian":[92],"mixture":[93],"model":[94],"(GMM)":[95],"-":[96],"Universal":[97],"Background":[98],"(UBM).":[100],"trained":[102],"subsequently":[105],"used":[106],"generate":[108],"temporally":[110],"contiguous":[111],"state":[112,137],"alignment":[113],"which":[114],"then":[116],"modeled":[117],"hybrid":[120],"deep":[121],"neural":[122],"network":[123],"(DNN)":[124],"model.":[125],"For":[126],"purpose":[128],"testing,":[130],"frame":[134],"level":[135],"posteriors":[138],"obtained":[139],"from":[140],"DNN":[142],"as":[143],"features":[144,184,194],"ZeroSpeech":[147,174],"task.":[149],"minimal":[151],"pair":[152],"ABX":[153],"error":[154],"rate":[155],"measured":[157],"both":[159],"within":[161,201],"across":[163,207],"speaker":[164,202,208],"pairs.":[165],"With":[166],"several":[167],"experiments":[168,212],"on":[169],"multiple":[170],"languages":[171],"corpus,":[175],"show":[177],"proposed":[180,223],"posterior":[183],"provides":[185],"improvements":[187,197],"baseline":[190],"system":[191],"MFCC":[193],"(average":[195],"relative":[196],"25%":[199],"pairs":[203],"40%":[205],"pairs).":[209],"Furthermore,":[210],"where":[213],"target":[215],"not":[218],"seen":[219],"training":[220],"illustrate":[221],"approach":[225],"capable":[227],"learning":[229],"global":[230],"representations.":[233]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}