{"id":"https://openalex.org/W2096635587","doi":"https://doi.org/10.1109/icassp.2012.6288994","title":"A deep architecture with bilinear modeling of hidden representations: Applications to phonetic recognition","display_name":"A deep architecture with bilinear modeling of hidden representations: Applications to phonetic recognition","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2096635587","doi":"https://doi.org/10.1109/icassp.2012.6288994","mag":"2096635587"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5033912251","display_name":"Brian Hutchinson","orcid":"https://orcid.org/0000-0002-5537-008X"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brian Hutchinson","raw_affiliation_strings":["EE Department, University of Washington, USA","EE Dept, University of Washington, USA"],"affiliations":[{"raw_affiliation_string":"EE Department, University of Washington, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"EE Dept, University of Washington, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Deng","raw_affiliation_strings":["Microsoft Research Redmond, USA","Microsoft Research, , Redmond, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, , Redmond, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Microsoft Research Redmond, USA","Microsoft Research, , Redmond, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, , Redmond, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033912251"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":4.5737,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.94189602,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4805","last_page":"4808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"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":0.9908999800682068,"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/timit","display_name":"TIMIT","score":0.799711287021637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7322030663490295},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5897454023361206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5683919191360474},{"id":"https://openalex.org/keywords/nasa-deep-space-network","display_name":"NASA Deep Space Network","score":0.533072292804718},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.45223021507263184},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.42520034313201904},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41967302560806274},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3986371159553528},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2774726152420044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12539082765579224}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.799711287021637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322030663490295},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5897454023361206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5683919191360474},{"id":"https://openalex.org/C187107819","wikidata":"https://www.wikidata.org/wiki/Q835696","display_name":"NASA Deep Space Network","level":3,"score":0.533072292804718},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.45223021507263184},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.42520034313201904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41967302560806274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3986371159553528},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2774726152420044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12539082765579224},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C29829512","wikidata":"https://www.wikidata.org/wiki/Q40218","display_name":"Spacecraft","level":2,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.4462","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.4462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/157583/T-DSN-ICASSP2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W1524763260","https://openalex.org/W1993882792","https://openalex.org/W2002984713","https://openalex.org/W2024165284","https://openalex.org/W2106347453","https://openalex.org/W2121989412","https://openalex.org/W2140372979","https://openalex.org/W2141778357","https://openalex.org/W2147768505","https://openalex.org/W2149600041","https://openalex.org/W2158825478","https://openalex.org/W6631555006","https://openalex.org/W6681419218","https://openalex.org/W6683317176"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W3164669818","https://openalex.org/W2539668349","https://openalex.org/W1573546415","https://openalex.org/W2906993205","https://openalex.org/W2142570240","https://openalex.org/W2071572975","https://openalex.org/W238071703","https://openalex.org/W2619993508","https://openalex.org/W2592921646"],"abstract_inverted_index":{"We":[0],"develop":[1],"and":[2,24,76,109,111],"describe":[3],"a":[4,26,66,70,82,124,131],"novel":[5],"deep":[6],"architecture,":[7],"the":[8,33,45,52,58,90,113,128],"Tensor":[9],"Deep":[10,99],"Stacking":[11],"Network":[12,101],"(T-DSN),":[13],"where":[14,25],"multiple":[15],"blocks":[16],"are":[17],"stacked":[18],"one":[19],"on":[20],"top":[21],"of":[22,44],"another":[23],"bilinear":[27],"mapping":[28],"from":[29],"hidden":[30],"representations":[31],"to":[32,40,65,84,123],"output":[34],"in":[35,56,89,104,112],"each":[36],"block":[37],"is":[38,54,63],"used":[39],"incorporate":[41],"higher-order":[42],"statistics":[43],"input":[46],"features.":[47],"A":[48],"learning":[49],"algorithm":[50],"for":[51,130],"T-DSN":[53,83,94,120],"presented,":[55],"which":[57],"main":[59],"parameter":[60],"estimation":[61],"burden":[62],"shifted":[64],"convex":[67],"sub-problem":[68],"with":[69],"closed-form":[71],"solution.":[72],"Using":[73],"an":[74,96],"efficient":[75],"scalable":[77],"parallel":[78],"implementation,":[79],"we":[80],"train":[81],"discriminate":[85],"standard":[86],"three-state":[87],"monophones":[88],"TIMIT":[91],"database.":[92],"The":[93],"outperforms":[95],"alternative":[97],"pretrained":[98],"Neural":[100],"(DNN)":[102],"architecture":[103],"frame-level":[105],"classification":[106],"(both":[107],"state":[108],"phone)":[110],"cross-entropy":[114],"measure.":[115],"For":[116],"continuous":[117],"phonetic":[118],"recognition,":[119],"performs":[121],"equivalently":[122],"DNN":[125],"but":[126],"without":[127],"need":[129],"hard-to-scale,":[132],"sequential":[133],"fine-tuning":[134],"step.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}