{"id":"https://openalex.org/W2107553890","doi":"https://doi.org/10.1109/asru.2013.6707754","title":"DNN acoustic modeling with modular multi-lingual feature extraction networks","display_name":"DNN acoustic modeling with modular multi-lingual feature extraction networks","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2107553890","doi":"https://doi.org/10.1109/asru.2013.6707754","mag":"2107553890"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/DNN_acoustic_modeling_with_modular_multi-lingual_feature_extraction_networks/6473330","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":true,"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"],"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/A5001160212","display_name":"Qu\u1ed1c B\u1ea3o Nguy\u1ec5n","orcid":"https://orcid.org/0000-0001-8172-8578"},"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":"Quoc Bao Nguyen","raw_affiliation_strings":["Interactive Systems Lab, Karlsruhe Institute of Technology, Germany","Interactive Syst. Lab., Karlsruhe Inst. of Technol., Karlsruhe, Germany"],"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/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"],"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"],"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":4,"corresponding_author_ids":["https://openalex.org/A5069183549"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":5.4383,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.95580244,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"344","last_page":"349"},"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":0.9994999766349792,"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":0.9987000226974487,"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":0.8361480236053467},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6377557516098022},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6315062046051025},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5693857669830322},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5568973422050476},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5044568777084351},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5012636184692383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4983079433441162},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4941270649433136},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45704323053359985},{"id":"https://openalex.org/keywords/tagalog","display_name":"Tagalog","score":0.45319023728370667},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4153149425983429},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.349536657333374},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33868712186813354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8361480236053467},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6377557516098022},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6315062046051025},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5693857669830322},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5568973422050476},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5044568777084351},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5012636184692383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4983079433441162},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4941270649433136},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45704323053359985},{"id":"https://openalex.org/C2779388314","wikidata":"https://www.wikidata.org/wiki/Q34057","display_name":"Tagalog","level":2,"score":0.45319023728370667},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4153149425983429},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.349536657333374},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33868712186813354},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/asru.2013.6707754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:lti-1080","is_oa":false,"landing_page_url":"http://repository.cmu.edu/cgi/viewcontent.cgi?article=1080&context=lti","pdf_url":null,"source":{"id":"https://openalex.org/S4306400668","display_name":"Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"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/r1/6473330","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:figshare.com:article/6473330","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/DNN_acoustic_modeling_with_modular_multi-lingual_feature_extraction_networks/6473330","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/r1/6473330.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473330.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":[],"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/6473330","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/DNN_acoustic_modeling_with_modular_multi-lingual_feature_extraction_networks/6473330","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W319941341","https://openalex.org/W811578723","https://openalex.org/W1495547083","https://openalex.org/W1501286448","https://openalex.org/W1553004968","https://openalex.org/W1970088388","https://openalex.org/W1970890968","https://openalex.org/W1978660892","https://openalex.org/W1994606281","https://openalex.org/W1997547570","https://openalex.org/W2004245236","https://openalex.org/W2012897754","https://openalex.org/W2013598660","https://openalex.org/W2078031782","https://openalex.org/W2087395764","https://openalex.org/W2110798204","https://openalex.org/W2117671523","https://openalex.org/W2120209245","https://openalex.org/W2129070077","https://openalex.org/W2141404479","https://openalex.org/W2144792281","https://openalex.org/W2145094598","https://openalex.org/W2147768505","https://openalex.org/W2149814369","https://openalex.org/W2152175008","https://openalex.org/W2169415433","https://openalex.org/W2394932179","https://openalex.org/W2397534874","https://openalex.org/W2407441242","https://openalex.org/W2997574889","https://openalex.org/W6608710415","https://openalex.org/W6676481782","https://openalex.org/W6681096077","https://openalex.org/W6712029055","https://openalex.org/W6950824044"],"related_works":["https://openalex.org/W171544630","https://openalex.org/W3212836698","https://openalex.org/W2468068997","https://openalex.org/W4240433226","https://openalex.org/W2315343956","https://openalex.org/W2128446822","https://openalex.org/W4237692438","https://openalex.org/W611807403","https://openalex.org/W2336826924","https://openalex.org/W1560348878"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,61,109],"propose":[4],"several":[5],"deep":[6],"neural":[7],"network":[8],"architectures":[9,114],"that":[10,63,81],"are":[11,123,163],"able":[12],"to":[13,52,92,101,115,153],"leverage":[14],"data":[15,137],"from":[16,68],"multiple":[17],"languages.":[18],"Modularity":[19],"is":[20,142],"achieved":[21],"by":[22],"training":[23,141],"networks":[24,73,84,104],"for":[25,30,40,56,138],"extracting":[26],"high-level":[27],"features":[28],"and":[29,36,59,148,155,160],"estimating":[31],"phoneme":[32],"state":[33],"posteriors":[34],"separately,":[35],"then":[37],"combining":[38],"them":[39],"decoding":[41],"in":[42,88,111,133,144],"a":[43,89,94,126],"hybrid":[44],"DNN/HMM":[45],"setup.":[46],"This":[47],"approach":[48],"has":[49],"been":[50],"shown":[51],"achieve":[53,93],"superior":[54],"performance":[55,98],"single-language":[57],"systems,":[58],"here":[60],"demonstrate":[62],"feature":[64],"extractors":[65],"benefit":[66],"significantly":[67],"being":[69],"trained":[70],"as":[71],"multi-lingual":[72,106],"with":[74],"shared":[75],"hidden":[76],"representations.":[77],"We":[78],"also":[79],"show":[80],"existing":[82],"mono-lingual":[83,158],"can":[85],"be":[86],"re-used":[87],"modular":[90],"fashion":[91],"similar":[95],"level":[96],"of":[97,118,151],"without":[99],"having":[100],"train":[102],"new":[103],"on":[105,125],"data.":[107],"Furthermore,":[108],"investigate":[110],"extending":[112],"these":[113],"make":[116],"use":[117],"language-specific":[119],"acoustic":[120,139],"features.":[121],"Evaluations":[122],"performed":[124],"low-resource":[127],"conversational":[128],"telephone":[129],"speech":[130],"transcription":[131],"task":[132],"Vietnamese,":[134],"while":[135],"additional":[136],"model":[140],"provided":[143],"Pashto,":[145],"Tagalog,":[146],"Turkish,":[147],"Cantonese.":[149],"Improvements":[150],"up":[152],"17.4%":[154],"13.8%":[156],"over":[157],"GMMs":[159],"DNNs,":[161],"respectively,":[162],"obtained.":[164]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}