{"id":"https://openalex.org/W17156489","doi":"https://doi.org/10.21437/interspeech.2013-526","title":"Improving low-resource CD-DNN-HMM using dropout and multilingual DNN training","display_name":"Improving low-resource CD-DNN-HMM using dropout and multilingual DNN training","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W17156489","doi":"https://doi.org/10.21437/interspeech.2013-526","mag":"17156489"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-526","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Improving_Low-Resource_CD-DNN-HMM_Using_Dropout_and_Multilingual_DNN_Training/6473423","any_repository_has_fulltext":true},"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":8.0083,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.98320214,"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":"2237","last_page":"2241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.998199999332428,"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":0.9976999759674072,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.880692720413208},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8393338918685913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8069770336151123},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.7211851477622986},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6158978939056396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6106181144714355},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5800837278366089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5279863476753235},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5259948968887329},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46746304631233215},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.46420368552207947},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4482746124267578},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39972102642059326},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3792634606361389}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.880692720413208},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8393338918685913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8069770336151123},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.7211851477622986},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6158978939056396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6106181144714355},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5800837278366089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5279863476753235},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5259948968887329},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46746304631233215},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.46420368552207947},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4482746124267578},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39972102642059326},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3792634606361389},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2013-526","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:lti-1090","is_oa":false,"landing_page_url":"http://repository.cmu.edu/lti/99","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Language Technologies Institute","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.710.7517","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.710.7517","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/dropout_final_is13.pdf","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/6473423","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Improving_Low-Resource_CD-DNN-HMM_Using_Dropout_and_Multilingual_DNN_Training/6473423","pdf_url":null,"source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.1184/r1/6473423.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473423.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6473423","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Improving_Low-Resource_CD-DNN-HMM_Using_Dropout_and_Multilingual_DNN_Training/6473423","pdf_url":null,"source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W66627554","https://openalex.org/W66838807","https://openalex.org/W1501286448","https://openalex.org/W1604771987","https://openalex.org/W1904365287","https://openalex.org/W1970088388","https://openalex.org/W1970890968","https://openalex.org/W1991180839","https://openalex.org/W2025487094","https://openalex.org/W2062227835","https://openalex.org/W2089177488","https://openalex.org/W2090764203","https://openalex.org/W2112984492","https://openalex.org/W2120209245","https://openalex.org/W2145094598","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2294059674","https://openalex.org/W2394932179","https://openalex.org/W2616657226"],"related_works":["https://openalex.org/W4298017035","https://openalex.org/W3128220493","https://openalex.org/W2792147139","https://openalex.org/W3110700750","https://openalex.org/W2998675825","https://openalex.org/W4226354336","https://openalex.org/W4394636190","https://openalex.org/W2736804899","https://openalex.org/W2897443685","https://openalex.org/W4307654087"],"abstract_inverted_index":{"We":[0],"investigate":[1],"two":[2,123],"strategies":[3,100],"to":[4],"improve":[5],"the":[6,21,67,86,102],"context-dependent":[7],"deep":[8],"neural":[9],"network":[10],"hidden":[11,82],"Markov":[12],"model":[13,25,61],"(CD-DNN-HMM)":[14],"in":[15,56,109,112],"low-resource":[16],"speech":[17],"recognition.":[18],"Although":[19],"outperforming":[20],"conventional":[22],"Gaussian":[23],"mixture":[24],"(GMM)":[26],"HMM":[27],"on":[28,122],"various":[29],"tasks,":[30],"CD-DNN-HMM":[31],"acoustic":[32],"modeling":[33],"becomes":[34],"challenging":[35],"with":[36],"limited":[37,124],"transcribed":[38],"speech,":[39],"e.g.,":[40],"less":[41],"than":[42],"10":[43],"hours.":[44],"To":[45],"resolve":[46],"this":[47],"issue,":[48],"we":[49],"firstly":[50],"exploit":[51],"dropout":[52],"which":[53],"prevents":[54],"overfitting":[55],"DNN":[57,71],"finetuning":[58],"and":[59,91,118],"improves":[60],"robustness":[62],"under":[63],"data":[64,125],"sparseness.":[65],"Then,":[66],"effectiveness":[68],"of":[69,85],"multilingual":[70],"training":[72],"is":[73],"evaluated":[74],"when":[75],"additional":[76],"auxiliary":[77],"languages":[78],"are":[79,89],"available.":[80],"The":[81],"layer":[83],"parameters":[84],"target":[87],"language":[88],"shared":[90],"learned":[92],"over":[93],"multiple":[94],"languages.":[95],"Experiments":[96],"show":[97],"that":[98],"both":[99],"boost":[101],"recognition":[103],"performance":[104],"significantly.":[105],"Combining":[106],"them":[107],"results":[108],"further":[110],"reduction":[111],"word":[113],"error":[114],"rate,":[115],"achieving":[116],"11.6%":[117],"6.2%":[119],"relative":[120],"improvement":[121],"conditions.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}