{"id":"https://openalex.org/W2403524927","doi":"https://doi.org/10.21437/interspeech.2015-290","title":"On speaker adaptation of long short-term memory recurrent neural networks","display_name":"On speaker adaptation of long short-term memory recurrent neural networks","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2403524927","doi":"https://doi.org/10.21437/interspeech.2015-290","mag":"2403524927"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-290","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003251887","display_name":"Yajie Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yajie Miao","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":6.1729,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.97402389,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9962000250816345,"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":0.9904000163078308,"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":0.7624269723892212},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.7188972234725952},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6535118222236633},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5949925780296326},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4829637110233307},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.47273480892181396},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.45365798473358154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36617374420166016},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09564328193664551},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.06134289503097534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7624269723892212},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7188972234725952},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6535118222236633},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5949925780296326},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4829637110233307},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.47273480892181396},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.45365798473358154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36617374420166016},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09564328193664551},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.06134289503097534},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2015-290","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.8869","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.8869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Eymiao/pub/is2015_lstm.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W111477576","https://openalex.org/W567546468","https://openalex.org/W587565084","https://openalex.org/W596888916","https://openalex.org/W619799124","https://openalex.org/W655723668","https://openalex.org/W1502809942","https://openalex.org/W1524333225","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W1995562189","https://openalex.org/W2002342963","https://openalex.org/W2005708641","https://openalex.org/W2010362084","https://openalex.org/W2028706510","https://openalex.org/W2045317385","https://openalex.org/W2064675550","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2089917322","https://openalex.org/W2094147890","https://openalex.org/W2107878631","https://openalex.org/W2112739286","https://openalex.org/W2119615570","https://openalex.org/W2136922672","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2213952365","https://openalex.org/W2290318471","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2295119550","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2566606998","https://openalex.org/W2406264770","https://openalex.org/W4366149782","https://openalex.org/W1897240248","https://openalex.org/W3103945224","https://openalex.org/W1583001605","https://openalex.org/W2890401420","https://openalex.org/W3015193452","https://openalex.org/W3038306631","https://openalex.org/W2755891984"],"abstract_inverted_index":{"Long":[0,150],"Short-Term":[1,151],"Memory":[2],"(LSTM)":[3],"is":[4,135],"a":[5,67,129],"recurrent":[6,153],"neural":[7,154],"net-work":[8],"(RNN)":[9],"architecture":[10],"specializing":[11],"in":[12],"modeling":[13,19],"long-range":[14],"temporal":[15],"dynamics.":[16],"On":[17],"acoustic":[18,52,156],"tasks,":[20],"LSTM-RNNs":[21,85],"have":[22,58],"shown":[23],"better":[24],"performance":[25],"than":[26],"DNNs":[27],"and":[28,54],"conventional":[29],"RNNs.":[30],"In":[31],"this":[32,63],"paper,":[33],"we":[34,102,141],"conduct":[35],"an":[36],"extensive":[37],"study":[38],"on":[39,66,77],"speaker":[40,118,158],"adaptation":[41,45,73,79,105,119,159],"of":[42,80],"LSTM-RNNs.":[43,81,114],"Speaker":[44],"helps":[46],"to":[47,137],"reduce":[48],"the":[49,70,78,109],"mismatch":[50],"between":[51],"models":[53],"testing":[55],"speakers.":[56],"We":[57,82],"two":[59,104],"main":[60],"goals":[61],"for":[62,113,145],"study.":[64],"First,":[65],"benchmark":[68],"dataset,":[69],"existing":[71],"DNN":[72],"techniques":[74],"are":[75],"evaluated":[76],"observe":[83],"that":[84,107],"can":[86],"be":[87],"effectively":[88],"adapted":[89],"by":[90,96,124],"using":[91],"speaker-adaptive":[92],"(SA)":[93],"front-end,":[94],"or":[95],"inserting":[97],"speaker-dependent":[98],"(SD)":[99],"layers.":[100],"Second,":[101],"propose":[103],"approaches":[106],"implement":[108],"SD-layer-insertion":[110],"idea":[111],"specifically":[112],"Us-ing":[115],"these":[116],"approaches,":[117],"improves":[120],"word":[121],"error":[122],"rates":[123],"3-4":[125],"%":[126,139],"relative":[127],"over":[128],"strong":[130],"LSTM-RNN":[131],"baseline.":[132],"This":[133],"improvement":[134],"enlarged":[136],"6-7":[138],"if":[140],"exploit":[142],"SA":[143],"features":[144],"further":[146],"adaptation.":[147],"Index":[148],"Terms:":[149],"Memory,":[152],"net-work,":[155],"modeling,":[157]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}