{"id":"https://openalex.org/W2401464865","doi":"https://doi.org/10.21437/interspeech.2011-184","title":"Towards unsupervised training of speaker independent acoustic models","display_name":"Towards unsupervised training of speaker independent acoustic models","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2401464865","doi":"https://doi.org/10.21437/interspeech.2011-184","mag":"2401464865"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-184","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5103622427","display_name":"Aren Jansen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aren Jansen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016543371","display_name":"Kenneth Church","orcid":"https://orcid.org/0000-0001-8378-6069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenneth Church","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103622427"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.5446,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.98544678,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1693","last_page":"1696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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":0.8252279758453369},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7739903926849365},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7271558046340942},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6925162672996521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5352628231048584},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5252998471260071},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4965851902961731},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46238911151885986},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4536662697792053},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44097018241882324},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39216020703315735},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2731248736381531},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08608779311180115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252279758453369},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7739903926849365},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7271558046340942},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6925162672996521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5352628231048584},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5252998471260071},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4965851902961731},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46238911151885986},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4536662697792053},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44097018241882324},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39216020703315735},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2731248736381531},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08608779311180115},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-184","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W308497914","https://openalex.org/W1539935047","https://openalex.org/W1606268232","https://openalex.org/W1964917299","https://openalex.org/W2079460648","https://openalex.org/W2099415988","https://openalex.org/W2114347655","https://openalex.org/W2117041980","https://openalex.org/W2167655920"],"related_works":["https://openalex.org/W2944691285","https://openalex.org/W2121652828","https://openalex.org/W2126322296","https://openalex.org/W2163537793","https://openalex.org/W4386794561","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W3021690593","https://openalex.org/W2125343999","https://openalex.org/W4200200210"],"abstract_inverted_index":{"Can":[0],"we":[1,90],"automatically":[2,25],"discover":[3,26],"speaker":[4],"independent":[5],"phonemelike":[6],"subword":[7,84],"units":[8],"with":[9,51,97],"zero":[10],"resources":[11],"in":[12,64],"a":[13,19,31,52,92],"surprise":[14],"language?":[15],"There":[16],"have":[17],"been":[18],"number":[20],"of":[21,38,56,73,83],"recent":[22],"efforts":[23],"to":[24],"repeated":[27],"spoken":[28],"terms":[29],"without":[30],"recognizer.":[32],"This":[33],"paper":[34],"investigates":[35],"the":[36,65,74,79,107,116,131],"feasibility":[37],"using":[39,110],"these":[40],"results":[41],"as":[42,59,61],"constraints":[43],"for":[44],"unsupervised":[45],"acoustic":[46,137,141],"model":[47,96],"training.":[48],"We":[49,113],"start":[50],"relatively":[53],"small":[54],"set":[55],"word":[57,77,88,108,129],"types,":[58],"well":[60,122],"their":[62],"locations":[63],"speech.":[66],"The":[67],"training":[68],"process":[69],"assumes":[70],"that":[71,115],"repetitions":[72],"same":[75,80],"(unknown)":[76,81],"share":[78],"sequence":[82],"units.":[85],"For":[86],"each":[87],"type,":[89],"train":[91],"whole-word":[93],"hidden":[94],"Markov":[95],"Gaussian":[98],"mixture":[99],"observation":[100],"densities":[101],"and":[102,139],"collapse":[103],"correlated":[104],"states":[105],"across":[106],"types":[109],"spectral":[111],"clustering.":[112],"find":[114],"resulting":[117],"state":[118],"clusters":[119],"align":[120],"reasonably":[121],"along":[123],"phonetic":[124],"lines.":[125],"In":[126],"evaluating":[127],"cross-speaker":[128],"similarity,":[130],"proposed":[132],"techniques":[133],"outperform":[134],"both":[135],"raw":[136],"features":[138],"language-mismatched":[140],"models.":[142]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}