{"id":"https://openalex.org/W2403226894","doi":"https://doi.org/10.1109/icassp.2016.7472801","title":"Comparison of unsupervised sequence adaptations for deep neural networks","display_name":"Comparison of unsupervised sequence adaptations for deep neural networks","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2403226894","doi":"https://doi.org/10.1109/icassp.2016.7472801","mag":"2403226894"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5079042022","display_name":"Akio Kobayashi","orcid":"https://orcid.org/0000-0002-6927-7353"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Akio Kobayashi","raw_affiliation_strings":["NHK Engineering System. Inc, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NHK Engineering System. Inc, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112263347","display_name":"Kazuo Onoe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuo Onoe","raw_affiliation_strings":["NHK (Japan Broadcasting Coporation), Science and Technology Research Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Coporation), Science and Technology Research Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090880731","display_name":"Manon Ichiki","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Manon Ichiki","raw_affiliation_strings":["NHK (Japan Broadcasting Coporation), Science and Technology Research Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Coporation), Science and Technology Research Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109470000","display_name":"Shoei Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoei Sato","raw_affiliation_strings":["NHK (Japan Broadcasting Coporation), Science and Technology Research Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Coporation), Science and Technology Research Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I4210107548"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079042022"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02551514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"5860","last_page":"5864"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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":0.8172734975814819},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7705245018005371},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.647742509841919},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6444412469863892},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6098874807357788},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5843457579612732},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.573512077331543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.556738018989563},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5467012524604797},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.5249207615852356},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.45788848400115967},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4523027539253235},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4250409007072449},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.42146578431129456},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.29083019495010376},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.15640804171562195}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8172734975814819},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7705245018005371},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.647742509841919},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6444412469863892},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6098874807357788},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5843457579612732},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.573512077331543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.556738018989563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5467012524604797},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.5249207615852356},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.45788848400115967},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4523027539253235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4250409007072449},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.42146578431129456},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.29083019495010376},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.15640804171562195},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W71446690","https://openalex.org/W1524333225","https://openalex.org/W1932968309","https://openalex.org/W1973681148","https://openalex.org/W1984570643","https://openalex.org/W1987238397","https://openalex.org/W1989549063","https://openalex.org/W1993666847","https://openalex.org/W2033256038","https://openalex.org/W2073908845","https://openalex.org/W2094147890","https://openalex.org/W2119885976","https://openalex.org/W2124558353","https://openalex.org/W2131342762","https://openalex.org/W2145094598","https://openalex.org/W2145494108","https://openalex.org/W2148386535","https://openalex.org/W2160306971","https://openalex.org/W2293363371","https://openalex.org/W2293561511","https://openalex.org/W2997574889","https://openalex.org/W6631362777","https://openalex.org/W6681096077","https://openalex.org/W6681588610","https://openalex.org/W6683263180","https://openalex.org/W6697713518"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"This":[0],"paper":[1],"compares":[2],"unsupervised":[3,71,95,147],"sequence":[4,96,148],"training":[5],"techniques":[6,73],"for":[7,12,40,76,111],"deep":[8],"neural":[9],"networks":[10],"(DNN)":[11],"broadcast":[13,21],"transcriptions.":[14],"Recent":[15],"progress":[16],"in":[17,43],"digital":[18],"archiving":[19],"of":[20,31,146],"content":[22],"has":[23],"made":[24],"it":[25],"easier":[26],"to":[27,133],"access":[28],"large":[29],"amounts":[30],"speech":[32,49],"data.":[33],"Such":[34],"archived":[35,56],"data":[36],"will":[37],"be":[38],"helpful":[39],"acoustic/language":[41],"modeling":[42],"live-broadcast":[44],"captioning":[45],"based":[46],"on":[47],"automatic":[48],"recognition":[50],"(ASR).":[51],"In":[52,89],"Japanese":[53],"broadcasts,":[54],"however,":[55],"programs,":[57],"e.g.,":[58],"sports":[59,113],"news,":[60],"do":[61],"not":[62],"always":[63],"have":[64],"closed-captions":[65],"used":[66,84],"typically":[67],"as":[68,85,132],"references.":[69],"Thus,":[70],"adaptation":[72,97],"are":[74,139],"needed":[75],"performance":[77,121],"improvements":[78],"even":[79],"when":[80],"a":[81,100],"DNN":[82],"is":[83,122],"an":[86],"acoustic":[87],"model.":[88],"this":[90],"paper,":[91],"we":[92],"compared":[93],"three":[94],"techniques:":[98],"maximum":[99],"posteriori":[101],"(MAP),":[102],"entropy":[103],"minimization,":[104],"and":[105],"Bayes":[106,126],"risk":[107,127],"minimization.":[108],"Experimental":[109],"results":[110,138],"transcribing":[112],"news":[114],"programs":[115],"showed":[116],"that":[117],"the":[118,143],"best":[119],"ASR":[120],"brought":[123],"about":[124],"by":[125],"minimization":[128],"which":[129],"reflects":[130],"information":[131],"expected":[134],"errors,":[135],"while":[136],"comparable":[137],"obtained":[140],"with":[141],"MAP,":[142],"simplest":[144],"way":[145],"adaptation.":[149]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}