{"id":"https://openalex.org/W2586564256","doi":"https://doi.org/10.1109/devlrn.2016.7846782","title":"Direct word discovery from speech signals based on hierarchical Dirichlet process-hidden language model and deep sparse autoencoder","display_name":"Direct word discovery from speech signals based on hierarchical Dirichlet process-hidden language model and deep sparse autoencoder","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2586564256","doi":"https://doi.org/10.1109/devlrn.2016.7846782","mag":"2586564256"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2016.7846782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2016.7846782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","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/A5023160093","display_name":"Tadahiro Taniguchi","orcid":"https://orcid.org/0000-0002-5682-2076"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tadahiro Taniguchi","raw_affiliation_strings":["College of Information Science and Engineering, Ritsumeikan University, Shiga, Japan"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113898629","display_name":"Ryo Nakashima","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120159","display_name":"SoftBank Group (Japan)","ror":"https://ror.org/02ew2ks20","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210120159"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Nakashima","raw_affiliation_strings":["Graduate School of Science and Engineering, SoftBank Corp"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, SoftBank Corp","institution_ids":["https://openalex.org/I4210120159"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035645797","display_name":"Shogo Nagasaka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shogo Nagasaka","raw_affiliation_strings":["Graduate School of Science and Engineering, Donuts Inc"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Donuts Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023160093"],"corresponding_institution_ids":["https://openalex.org/I135768898"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.20120506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"23","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10730","display_name":"Language Development and Disorders","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10730","display_name":"Language Development and Disorders","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9968000054359436,"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/T10028","display_name":"Topic Modeling","score":0.9873999953269958,"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":0.8208593130111694},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7650647759437561},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6953978538513184},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5664460062980652},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.533143937587738},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5144086480140686},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5003018379211426},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4854184091091156},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4794943928718567},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4411436915397644},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3816549777984619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8208593130111694},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7650647759437561},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6953978538513184},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5664460062980652},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.533143937587738},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5144086480140686},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5003018379211426},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4854184091091156},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4794943928718567},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4411436915397644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3816549777984619},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/devlrn.2016.7846782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2016.7846782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1778492285","https://openalex.org/W1942713348","https://openalex.org/W1980862600","https://openalex.org/W2005958977","https://openalex.org/W2140991203","https://openalex.org/W2142390309","https://openalex.org/W2335112305","https://openalex.org/W3102667484","https://openalex.org/W6640777149"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W2806873178","https://openalex.org/W2965146396","https://openalex.org/W2770818364","https://openalex.org/W4312416532","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Word":[0],"discovery":[1,24,127],"is":[2,29,88,97,112],"a":[3,31,59,98],"critical":[4],"part":[5],"of":[6,142],"language":[7,65,94,103,143],"acquisition":[8,144],"for":[9,34],"infants.":[10],"Human":[11],"infants":[12],"can":[13,70],"discover":[14],"words":[15],"from":[16,25,73,128],"human":[17,146],"speech":[18,27,75],"signals":[19,28,76],"directly.":[20],"However,":[21],"direct":[22,125],"word":[23,126],"raw":[26,74],"still":[30],"challenging":[32],"problem":[33],"recent":[35],"artificial":[36],"intelligence":[37],"technology.":[38],"This":[39],"paper":[40],"describes":[41],"our":[42,121],"new":[43,122],"experimental":[44],"result":[45],"based":[46,89],"on":[47,90],"the":[48,139],"state-of-the-art":[49],"machine":[50],"learning":[51,116],"method,":[52],"which":[53,96,111],"we":[54],"previously":[55],"proposed,":[56],"that":[57,101],"enables":[58],"robot":[60,69],"to":[61,135],"acquire":[62,71],"acoustic":[63,105],"and":[64,104,107],"models":[66],"simultaneously.":[67],"A":[68],"them":[72],"without":[77],"any":[78],"transcribed":[79],"data,":[80],"i.e.,":[81],"in":[82,145],"an":[83,113],"unsupervised":[84,114],"manner.":[85],"The":[86,131],"method":[87],"hierarchical":[91],"Dirichlet":[92],"process-hidden":[93],"model,":[95],"generative":[99],"model":[100],"integrate":[102],"models,":[106],"deep":[108,115],"sparse":[109],"autoencoder,":[110],"method.":[117],"We":[118],"also":[119],"report":[120],"results":[123,132],"about":[124,138],"vowel":[129],"sequences.":[130],"lead":[133],"us":[134],"open":[136],"discussion":[137],"computational":[140],"process":[141],"development.":[147]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}