{"id":"https://openalex.org/W2750322757","doi":"https://doi.org/10.21437/interspeech.2017-1136","title":"Learning Factorized Transforms for Unsupervised Adaptation of LSTM-RNN Acoustic Models","display_name":"Learning Factorized Transforms for Unsupervised Adaptation of LSTM-RNN Acoustic Models","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2750322757","doi":"https://doi.org/10.21437/interspeech.2017-1136","mag":"2750322757"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1136","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1136","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004424826","display_name":"Lahiru Samarakoon","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lahiru Samarakoon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059141717","display_name":"Brian Mak","orcid":"https://orcid.org/0000-0001-6787-5555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Mak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032798707","display_name":"Khe Chai Sim","orcid":"https://orcid.org/0000-0002-0866-2223"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khe Chai Sim","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004424826"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1701,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84279735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"744","last_page":"748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973000288009644,"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/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"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":0.7201163172721863},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7049914598464966},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6255766153335571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5206258296966553},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4749579429626465},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44857653975486755},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3458421230316162},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1630542278289795},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09936943650245667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7201163172721863},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7049914598464966},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6255766153335571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5206258296966553},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4749579429626465},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44857653975486755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3458421230316162},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1630542278289795},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09936943650245667},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2017-1136","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1136","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:repository.hkust.edu.hk:1783.1-88695","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-88695","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W330298975","https://openalex.org/W1569447338","https://openalex.org/W1592672653","https://openalex.org/W1599512239","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2015633636","https://openalex.org/W2069631319","https://openalex.org/W2079623482","https://openalex.org/W2100969003","https://openalex.org/W2106554350","https://openalex.org/W2146871184","https://openalex.org/W2181607856","https://openalex.org/W2239847623","https://openalex.org/W2293634267","https://openalex.org/W2400607496","https://openalex.org/W2400957076","https://openalex.org/W2406264770","https://openalex.org/W2508162385","https://openalex.org/W2616139854","https://openalex.org/W2682975603","https://openalex.org/W2964084166"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W3196155444","https://openalex.org/W4321844043","https://openalex.org/W3210156800","https://openalex.org/W4390062853","https://openalex.org/W4297883248","https://openalex.org/W4255830763","https://openalex.org/W1583266947","https://openalex.org/W4286799911","https://openalex.org/W3165437720"],"abstract_inverted_index":{"Factorized":[0],"Hidden":[1],"Layer":[2],"(FHL)":[3],"adaptation":[4,10],"has":[5],"been":[6],"proposed":[7],"for":[8,95,125],"speaker":[9],"of":[11,47,58,92,107],"deep":[12],"neural":[13],"network":[14],"(DNN)":[15],"based":[16],"acoustic":[17,76,97],"models.":[18,98],"In":[19,85],"FHL":[20],"adaptation,":[21],"a":[22,44,55],"speaker-dependent":[23],"(SD)":[24],"transformation":[25,42],"matrix":[26],"and":[27,116,129],"an":[28],"SD":[29,41,52,93,112],"bias":[30,53],"are":[31],"included":[32],"in":[33,78],"addition":[34],"to":[35,73],"the":[36,51,61,90,121,126],"standard":[37],"affine":[38],"transformation.":[39],"The":[40],"is":[43,54],"linear":[45,56],"combination":[46,57],"rank-1":[48],"matrices":[49],"whereas":[50],"vectors.":[59],"Recently,":[60],"Long":[62],"Short-":[63],"Term":[64],"Memory":[65],"(LSTM)":[66],"Recurrent":[67],"Neural":[68],"Networks":[69],"(RNNs)":[70],"have":[71],"shown":[72],"outperform":[74],"DNN":[75],"models":[77],"many":[79],"Automatic":[80],"Speech":[81],"Recognition":[82],"(ASR)":[83],"tasks.":[84],"this":[86],"work,":[87],"we":[88],"investigate":[89],"effectiveness":[91],"transformations":[94,113],"LSTM-RNN":[96],"Experimental":[99],"results":[100],"show":[101],"that":[102],"when":[103],"combined":[104],"with":[105],"scaling":[106],"LSTM":[108,123],"cell":[109],"states'":[110],"outputs,":[111],"achieve":[114],"2.3%":[115],"2.1%":[117],"absolute":[118],"improvements":[119],"over":[120],"baseline":[122],"systems":[124],"AMI":[127,130],"IHM":[128],"SDM":[131],"tasks":[132],"respectively.":[133]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}