{"id":"https://openalex.org/W2535503132","doi":"https://doi.org/10.1109/icassp.2017.7953161","title":"Low-rank and sparse soft targets to learn better DNN acoustic models","display_name":"Low-rank and sparse soft targets to learn better DNN acoustic models","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2535503132","doi":"https://doi.org/10.1109/icassp.2017.7953161","mag":"2535503132"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/1610.05688","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/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":true,"raw_author_name":"Pranay Dighe","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale 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/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/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":false,"raw_author_name":"Herve Bourlard","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale 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":3,"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":1.2459,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84442198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"88","issue":null,"first_page":"5265","last_page":"5269"},"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":0.9995999932289124,"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":0.9987999796867371,"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":0.7372490167617798},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7231836318969727},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6244402527809143},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5867642760276794},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5442325472831726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5381482839584351},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.526429295539856},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.4713434875011444},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.46242207288742065},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45185744762420654},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44821539521217346},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4252644181251526},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13681727647781372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7372490167617798},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7231836318969727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6244402527809143},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5867642760276794},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5442325472831726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5381482839584351},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.526429295539856},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.4713434875011444},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.46242207288742065},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45185744762420654},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44821539521217346},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4252644181251526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13681727647781372},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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":3,"locations":[{"id":"doi:10.1109/icassp.2017.7953161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1610.05688","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1610.05688","pdf_url":"https://arxiv.org/pdf/1610.05688","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:223748","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/223748","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:1610.05688","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1610.05688","pdf_url":"https://arxiv.org/pdf/1610.05688","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1489048302","https://openalex.org/W1494198834","https://openalex.org/W1504869774","https://openalex.org/W1524333225","https://openalex.org/W1537895721","https://openalex.org/W1555148682","https://openalex.org/W1569447338","https://openalex.org/W1591607137","https://openalex.org/W1644797180","https://openalex.org/W1821462560","https://openalex.org/W1975900269","https://openalex.org/W1978741356","https://openalex.org/W1986184096","https://openalex.org/W1997201895","https://openalex.org/W2008732654","https://openalex.org/W2029867605","https://openalex.org/W2052382192","https://openalex.org/W2058641082","https://openalex.org/W2112447569","https://openalex.org/W2112984492","https://openalex.org/W2120209245","https://openalex.org/W2130259898","https://openalex.org/W2135046866","https://openalex.org/W2136933783","https://openalex.org/W2147511255","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2214579952","https://openalex.org/W2269021004","https://openalex.org/W2294543795","https://openalex.org/W2294692935","https://openalex.org/W2319531463","https://openalex.org/W2337627957","https://openalex.org/W2402040300","https://openalex.org/W2515838467","https://openalex.org/W2949902569","https://openalex.org/W2963726581","https://openalex.org/W3146320432","https://openalex.org/W4206310440","https://openalex.org/W6632372322","https://openalex.org/W6633204899","https://openalex.org/W6633847657","https://openalex.org/W6636799337","https://openalex.org/W6638523607","https://openalex.org/W6676727762","https://openalex.org/W6680549991","https://openalex.org/W6696912008"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"Conventional":[0],"deep":[1],"neural":[2],"networks":[3],"(DNN)":[4],"for":[5,28,54,128],"speech":[6,34],"acoustic":[7,79,130],"modeling":[8],"rely":[9],"on":[10,141],"Gaussian":[11],"mixture":[12],"models":[13],"(GMM)":[14],"and":[15,100,108,121],"hidden":[16],"Markov":[17],"model":[18],"(HMM)":[19],"to":[20,38,76,111],"obtain":[21],"binary":[22,69],"class":[23],"labels":[24,70],"as":[25,89,126],"the":[26,60,95,113],"targets":[27,75],"DNN":[29,55,66,82,129],"training.":[30,56],"Subword":[31],"classes":[32],"in":[33,148],"recognition":[35],"systems":[36],"correspond":[37],"context-dependent":[39],"tied":[40],"states":[41],"or":[42],"senones.":[43],"The":[44],"present":[45],"work":[46],"addresses":[47],"some":[48],"limitations":[49],"of":[50],"GMM-HMM":[51],"senone":[52,61,114],"alignments":[53],"We":[57,102],"hypothesize":[58],"that":[59,132],"probabilities":[62,117],"obtained":[63,118],"from":[64,119],"a":[65],"trained":[67],"with":[68,136],"can":[71],"provide":[72],"more":[73],"accurate":[74],"learn":[77],"better":[78],"models.":[80],"However,":[81],"outputs":[83],"bear":[84],"inaccuracies":[85],"which":[86],"are":[87,98,124],"exhibited":[88],"high":[90],"dimensional":[91],"unstructured":[92],"noise,":[93],"whereas":[94],"informative":[96],"components":[97],"structured":[99],"low-dimensional.":[101],"exploit":[103],"principal":[104],"component":[105],"analysis":[106],"(PCA)":[107],"sparse":[109,122],"coding":[110],"characterize":[112],"subspaces.":[115],"Enhanced":[116],"low-rank":[120],"reconstructions":[123],"used":[125],"soft-targets":[127],"modeling,":[131],"also":[133],"enables":[134],"training":[135],"untranscribed":[137],"data.":[138],"Experiments":[139],"conducted":[140],"AMI":[142],"corpus":[143],"shows":[144],"4.6%":[145],"relative":[146],"reduction":[147],"word":[149],"error":[150],"rate.":[151]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}