{"id":"https://openalex.org/W1970088388","doi":"https://doi.org/10.1109/icassp.2013.6638284","title":"Extracting deep bottleneck features using stacked auto-encoders","display_name":"Extracting deep bottleneck features using stacked auto-encoders","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1970088388","doi":"https://doi.org/10.1109/icassp.2013.6638284","mag":"1970088388"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/Extracting_deep_bottleneck_features_using_stacked_auto-encoders/6473369","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069183549","display_name":"Jonas Gehring","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonas Gehring","raw_affiliation_strings":["Interactive Systems Lab, Karlsruhe Institute of Technology; Germany","Interactive Syst. Lab., Karlsruhe Inst. of Technol., Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Systems Lab, Karlsruhe Institute of Technology; Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Interactive Syst. Lab., Karlsruhe Inst. of Technol., Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","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":["Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA; USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA; USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","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":["Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA; USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA; USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110453805","display_name":"Alex Waibel","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alex Waibel","raw_affiliation_strings":["Interactive Systems Lab, Karlsruhe Institute of Technology; Germany","Interactive Syst. Lab., Karlsruhe Inst. of Technol., Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Systems Lab, Karlsruhe Institute of Technology; Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Interactive Syst. Lab., Karlsruhe Inst. of Technol., Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.5334,"has_fulltext":false,"cited_by_count":280,"citation_normalized_percentile":{"value":0.99593236,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3377","last_page":"3381"},"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":0.9993000030517578,"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":0.9973999857902527,"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":0.8273792266845703},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8049056529998779},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.622536838054657},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5615759491920471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5445864200592041},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5246168375015259},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5246113538742065},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5195179581642151},{"id":"https://openalex.org/keywords/tagalog","display_name":"Tagalog","score":0.486405611038208},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4827682077884674},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4273705780506134},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.401943176984787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273792266845703},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8049056529998779},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.622536838054657},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5615759491920471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5445864200592041},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5246168375015259},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5246113538742065},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5195179581642151},{"id":"https://openalex.org/C2779388314","wikidata":"https://www.wikidata.org/wiki/Q34057","display_name":"Tagalog","level":2,"score":0.486405611038208},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4827682077884674},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4273705780506134},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.401943176984787},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp.2013.6638284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:lti-1097","is_oa":false,"landing_page_url":"http://repository.cmu.edu/cgi/viewcontent.cgi?article=1097&context=lti","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:doi:10.1184/r1/6473369","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"raw_type":"Journal contribution"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.459.9226","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.459.9226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://isl.anthropomatik.kit.edu/cmu-kit/downloads/0003377.pdf","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/6473369","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Extracting_deep_bottleneck_features_using_stacked_auto-encoders/6473369","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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/r1/6473369.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473369.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":"JournalArticle"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6473369","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Extracting_deep_bottleneck_features_using_stacked_auto-encoders/6473369","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W1520177497","https://openalex.org/W1553004968","https://openalex.org/W1993561131","https://openalex.org/W2025768430","https://openalex.org/W2105099419","https://openalex.org/W2110798204","https://openalex.org/W2117671523","https://openalex.org/W2123237149","https://openalex.org/W2134756243","https://openalex.org/W2136922672","https://openalex.org/W2139427956","https://openalex.org/W2141404479","https://openalex.org/W2144792281","https://openalex.org/W2147768505","https://openalex.org/W2152175008","https://openalex.org/W2159948109","https://openalex.org/W2160815625","https://openalex.org/W2165712214","https://openalex.org/W2166637769","https://openalex.org/W2169415433","https://openalex.org/W2172097686","https://openalex.org/W2184045248","https://openalex.org/W2394932179","https://openalex.org/W6676481782","https://openalex.org/W6684249834"],"related_works":["https://openalex.org/W171544630","https://openalex.org/W2468068997","https://openalex.org/W3212836698","https://openalex.org/W4240433226","https://openalex.org/W2595172197","https://openalex.org/W2128446822","https://openalex.org/W2315343956","https://openalex.org/W2084856301","https://openalex.org/W4237692438","https://openalex.org/W2944691285"],"abstract_inverted_index":{"In":[0,112],"this":[1],"work,":[2],"a":[3,26,55],"novel":[4],"training":[5,82],"scheme":[6],"for":[7,90],"generating":[8],"bottleneck":[9,32],"features":[10],"from":[11],"deep":[12],"neural":[13],"networks":[14],"is":[15,22,44,84],"proposed.":[16],"A":[17],"stack":[18],"of":[19,67,109,114,120],"denoising":[20],"auto-encoders":[21,68],"first":[23],"trained":[24],"in":[25,69],"layer-wise,":[27],"unsupervised":[28],"manner.":[29],"Afterwards,":[30],"the":[31,41,65,70,106],"layer":[33,37],"and":[34,40,61,100,136],"an":[35],"additional":[36,94],"are":[38,139],"added":[39],"whole":[42],"network":[43,71,132],"fine-tuned":[45],"to":[46],"predict":[47],"target":[48],"phoneme":[49],"states.":[50],"We":[51],"perform":[52],"experiments":[53],"on":[54,97,101],"Cantonese":[56],"conversational":[57],"telephone":[58],"speech":[59],"corpus":[60],"find":[62],"that":[63],"increasing":[64],"number":[66],"produces":[72],"more":[73,87],"useful":[74],"features,":[75],"but":[76],"requires":[77],"pre-training,":[78],"especially":[79],"when":[80],"little":[81],"data":[83,89],"available.":[85],"Using":[86],"unlabeled":[88],"pre-training":[91],"only":[92],"yields":[93],"gains.":[95],"Evaluations":[96],"larger":[98],"datasets":[99],"different":[102],"system":[103],"setups":[104],"demonstrate":[105],"general":[107],"applicability":[108],"our":[110],"approach.":[111],"terms":[113],"word":[115],"error":[116],"rate,":[117],"relative":[118],"improvements":[119],"9.2%":[121],"(Cantonese,":[122],"ML":[123],"training),":[124,128],"9.3%":[125],"(Tagalog,":[126,130],"BMMI-SAT":[127],"12%":[129],"confusion":[131],"combinations":[133],"with":[134],"MFCCs),":[135],"8.7%":[137],"(Switchboard)":[138],"achieved.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":41},{"year":2018,"cited_by_count":31},{"year":2017,"cited_by_count":31},{"year":2016,"cited_by_count":35},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}