{"id":"https://openalex.org/W2214579952","doi":"https://doi.org/10.1109/icassp.2016.7472767","title":"Exploiting low-dimensional structures to enhance DNN based acoustic modeling in speech recognition","display_name":"Exploiting low-dimensional structures to enhance DNN based acoustic modeling in speech recognition","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2214579952","doi":"https://doi.org/10.1109/icassp.2016.7472767","mag":"2214579952"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1601.05936","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063425263","display_name":"Pranay Dighe","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Pranay Dighe","raw_affiliation_strings":["Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084796834","display_name":"Gil Luyet","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]},{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Gil Luyet","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","University of Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"University of Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063249055","display_name":"Afsaneh Asaei","orcid":"https://orcid.org/0000-0002-1917-601X"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Afsaneh Asaei","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herve Bourlard","raw_affiliation_strings":["Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063425263"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":8.4248,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.9752904,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"5690","last_page":"5694"},"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":0.9997000098228455,"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":0.9991999864578247,"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":0.7400482892990112},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7152704000473022},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5587942004203796},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5241209268569946},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5177223086357117},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.5149617791175842},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.49475449323654175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47857192158699036},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.47007089853286743},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.45761340856552124},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.4509890675544739},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43383437395095825},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.4137917459011078},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.2569867670536041},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23374241590499878},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22757625579833984},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16120785474777222}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7400482892990112},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7152704000473022},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5587942004203796},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5241209268569946},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5177223086357117},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.5149617791175842},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.49475449323654175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47857192158699036},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.47007089853286743},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.45761340856552124},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.4509890675544739},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43383437395095825},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.4137917459011078},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2569867670536041},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23374241590499878},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22757625579833984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16120785474777222},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2016.7472767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1601.05936","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1601.05936","pdf_url":"https://arxiv.org/pdf/1601.05936","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:infoscience.epfl.ch:214702","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/214702","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:218112","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/218112","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:arXiv.org:1601.05936","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1601.05936","pdf_url":"https://arxiv.org/pdf/1601.05936","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"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":42,"referenced_works":["https://openalex.org/W204308143","https://openalex.org/W330298975","https://openalex.org/W1501109341","https://openalex.org/W1504869774","https://openalex.org/W1521499940","https://openalex.org/W1524333225","https://openalex.org/W1537895721","https://openalex.org/W1977690962","https://openalex.org/W1982309858","https://openalex.org/W1993962865","https://openalex.org/W1997201895","https://openalex.org/W2052382192","https://openalex.org/W2058641082","https://openalex.org/W2072128103","https://openalex.org/W2084253266","https://openalex.org/W2095705004","https://openalex.org/W2098110139","https://openalex.org/W2112447569","https://openalex.org/W2112984492","https://openalex.org/W2118595744","https://openalex.org/W2122994642","https://openalex.org/W2131342762","https://openalex.org/W2141310466","https://openalex.org/W2141520175","https://openalex.org/W2145962650","https://openalex.org/W2160815625","https://openalex.org/W2161742217","https://openalex.org/W2172097686","https://openalex.org/W2213952365","https://openalex.org/W2269021004","https://openalex.org/W2295676751","https://openalex.org/W3146320432","https://openalex.org/W4231109964","https://openalex.org/W4243044416","https://openalex.org/W4256161595","https://openalex.org/W6630955567","https://openalex.org/W6631362777","https://openalex.org/W6632372322","https://openalex.org/W6636799337","https://openalex.org/W6671639908","https://openalex.org/W6674330103","https://openalex.org/W6676727762"],"related_works":["https://openalex.org/W2890544631","https://openalex.org/W2067062989","https://openalex.org/W4205656132","https://openalex.org/W3004790527","https://openalex.org/W2203155458","https://openalex.org/W2111634407","https://openalex.org/W2783282829","https://openalex.org/W2138494306","https://openalex.org/W2539392819","https://openalex.org/W212310357"],"abstract_inverted_index":{"We":[0],"propose":[1],"to":[2,46,75,100,109],"model":[3],"the":[4,24,38,47,54,57,61,69,92,96],"acoustic":[5,105],"space":[6,48],"of":[7,18,37,49,60,71,91],"deep":[8],"neural":[9],"network":[10],"(DNN)":[11],"class-conditional":[12],"posterior":[13,62],"probabilities":[14],"as":[15],"a":[16,76,79],"union":[17],"low-dimensional":[19,86],"subspaces.":[20],"To":[21],"that":[22,56],"end,":[23],"training":[25,50],"posteriors":[26,40,73,93],"are":[27,64],"used":[28],"for":[29],"dictionary":[30,43],"learning":[31],"and":[32,68,94,126],"sparse":[33],"coding.":[34],"Sparse":[35],"representation":[36],"test":[39],"using":[41,116],"this":[42],"enables":[44],"projection":[45],"data.":[51],"Relying":[52],"on":[53],"fact":[55],"intrinsic":[58],"dimensions":[59],"subspaces":[63],"indeed":[65],"very":[66,80],"small":[67],"matrix":[70],"all":[72],"belonging":[74],"class":[77],"has":[78],"low":[81],"rank,":[82],"we":[83],"demonstrate":[84],"how":[85],"structures":[87],"enable":[88],"further":[89],"enhancement":[90],"rectify":[95],"spurious":[97],"errors":[98],"due":[99],"mismatch":[101],"conditions.":[102],"The":[103],"enhanced":[104],"modeling":[106],"method":[107],"leads":[108],"improvements":[110],"in":[111,123,134],"continuous":[112],"speech":[113],"recognition":[114],"task":[115],"hybrid":[117],"DNN-HMM":[118],"(hidden":[119],"Markov":[120],"model)":[121],"framework":[122],"both":[124],"clean":[125],"noisy":[127],"conditions,":[128],"where":[129],"upto":[130],"15.4%":[131],"relative":[132],"reduction":[133],"word":[135],"error":[136],"rate":[137],"(WER)":[138],"is":[139],"achieved.":[140]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}