{"id":"https://openalex.org/W2745710406","doi":"https://doi.org/10.21437/interspeech.2017-1784","title":"Exploiting Eigenposteriors for Semi-Supervised Training of DNN Acoustic Models with Sequence Discrimination","display_name":"Exploiting Eigenposteriors for Semi-Supervised Training of DNN Acoustic Models with Sequence Discrimination","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2745710406","doi":"https://doi.org/10.21437/interspeech.2017-1784","mag":"2745710406"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1784","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1784","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":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/230229","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063425263","display_name":"Pranay Dighe","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pranay Dighe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063249055","display_name":"Afsaneh Asaei","orcid":"https://orcid.org/0000-0002-1917-601X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Afsaneh Asaei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bourlard","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063425263"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6229,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7724466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3552","last_page":"3556"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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/T11309","display_name":"Music and Audio Processing","score":0.9922999739646912,"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/discriminative-model","display_name":"Discriminative model","score":0.7918468713760376},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7482479214668274},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5691065192222595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5603346228599548},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5491597056388855},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5149224996566772},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.5007913112640381},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4927816689014435},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4702279269695282},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44974732398986816},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4382113218307495},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37352651357650757}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7918468713760376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7482479214668274},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5691065192222595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5603346228599548},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5491597056388855},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5149224996566772},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.5007913112640381},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4927816689014435},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4702279269695282},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44974732398986816},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4382113218307495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37352651357650757},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2017-1784","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1784","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:infoscience.epfl.ch:230229","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/230229","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:230229","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/230229","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5299999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1504869774","https://openalex.org/W1524333225","https://openalex.org/W1555148682","https://openalex.org/W1821462560","https://openalex.org/W1993660824","https://openalex.org/W2052382192","https://openalex.org/W2058641082","https://openalex.org/W2085598899","https://openalex.org/W2131342762","https://openalex.org/W2189391786","https://openalex.org/W2214579952","https://openalex.org/W2269021004","https://openalex.org/W2294245963","https://openalex.org/W2294543795","https://openalex.org/W2295119550","https://openalex.org/W2319531463","https://openalex.org/W2337627957","https://openalex.org/W2402040300","https://openalex.org/W2507699225","https://openalex.org/W2535503132","https://openalex.org/W2586441793","https://openalex.org/W2963726581","https://openalex.org/W3146320432"],"related_works":["https://openalex.org/W2579148721","https://openalex.org/W4387893611","https://openalex.org/W2347335694","https://openalex.org/W2091056927","https://openalex.org/W2067407580","https://openalex.org/W4317486777","https://openalex.org/W4389669152","https://openalex.org/W2038514069","https://openalex.org/W1967233468","https://openalex.org/W2009181529"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"(DNN)":[3],"acoustic":[4,51],"models":[5],"yield":[6],"posterior":[7],"probabilities":[8],"of":[9,16,34,65,116],"senone":[10,20],"classes.Recent":[11],"studies":[12],"support":[13],"the":[14,35,54,73,104,117],"existence":[15],"low-dimensional":[17,32],"subspaces":[18],"underlying":[19],"posteriors.Principal":[21],"component":[22],"analysis":[23],"(PCA)":[24],"is":[25,120],"applied":[26,43],"to":[27,71,82,103,122],"identify":[28],"eigenposteriors":[29],"and":[30],"perform":[31],"projection":[33],"training":[36,48],"data":[37],"posteriors.The":[38],"resulted":[39],"enhanced":[40],"posteriors":[41],"are":[42],"as":[44],"soft":[45,118],"targets":[46,119],"for":[47],"better":[49],"DNN":[50,106],"model":[52],"under":[53],"student-teacher":[55],"framework.The":[56],"present":[57],"work":[58],"advances":[59],"this":[60,112],"approach":[61],"by":[62],"studying":[63],"incorporation":[64],"sequence":[66,80],"discriminative":[67],"training.We":[68],"demonstrate":[69],"how":[70],"combine":[72],"gains":[74],"from":[75],"eigenposterior":[76,114],"based":[77],"enhancement":[78,115],"with":[79,108],"discrimination":[81],"improve":[83],"ASR":[84],"using":[85,126],"semi-supervised":[86],"training.Evaluation":[87],"on":[88],"AMI":[89],"meeting":[90],"corpus":[91],"yields":[92],"nearly":[93],"4%":[94],"absolute":[95],"reduction":[96],"in":[97],"word":[98],"error":[99],"rate":[100],"(WER)":[101],"compared":[102],"baseline":[105],"trained":[107],"cross":[109],"entropy":[110],"objective.In":[111],"context,":[113],"crucial":[121],"enable":[123],"additive":[124],"improvement":[125],"out-of-domain":[127],"untranscribed":[128],"data.":[129]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}