{"id":"https://openalex.org/W2786872741","doi":"https://doi.org/10.1109/asru.2017.8268933","title":"Sequence training of DNN acoustic models with natural gradient","display_name":"Sequence training of DNN acoustic models with natural gradient","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786872741","doi":"https://doi.org/10.1109/asru.2017.8268933","mag":"2786872741"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268933","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1804.02204","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006496564","display_name":"Adnan Haider","orcid":"https://orcid.org/0000-0002-7075-1796"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":true,"raw_author_name":"Adnan Haider","raw_affiliation_strings":["Engineering Dept., Cambridge University, Cambridge, U.K","Cambridge University Engineering Department, Trumpington St., Cambridge CB2 1PZ, U.K"],"affiliations":[{"raw_affiliation_string":"Engineering Dept., Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I4210096386","https://openalex.org/I241749"]},{"raw_affiliation_string":"Cambridge University Engineering Department, Trumpington St., Cambridge CB2 1PZ, U.K","institution_ids":["https://openalex.org/I4210096386","https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Philip C. Woodland","raw_affiliation_strings":["Engineering Dept., Cambridge University, Cambridge, U.K","Cambridge University Engineering Department, Trumpington St., Cambridge CB2 1PZ, U.K"],"affiliations":[{"raw_affiliation_string":"Engineering Dept., Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I4210096386","https://openalex.org/I241749"]},{"raw_affiliation_string":"Cambridge University Engineering Department, Trumpington St., Cambridge CB2 1PZ, U.K","institution_ids":["https://openalex.org/I4210096386","https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006496564"],"corresponding_institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20405303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"178","last_page":"184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9997000098228455,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7935580015182495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6780390739440918},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6438118815422058},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.5881840586662292},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5664966106414795},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5166464447975159},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5001652240753174},{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.46826082468032837},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4493532180786133},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4355493485927582},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.42302456498146057},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4182172119617462},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.41191136837005615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40729081630706787},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38816699385643005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32230663299560547},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.238750159740448}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7935580015182495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6780390739440918},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6438118815422058},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.5881840586662292},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5664966106414795},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5166464447975159},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5001652240753174},{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.46826082468032837},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4493532180786133},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4355493485927582},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.42302456498146057},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4182172119617462},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.41191136837005615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40729081630706787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38816699385643005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32230663299560547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.238750159740448},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/asru.2017.8268933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268933","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.02204","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.02204","pdf_url":"https://arxiv.org/pdf/1804.02204","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":"","raw_type":"text"},{"id":"mag:2786872741","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1804.02204.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:generic.eprints.org:976431","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/976431/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"","raw_type":"Conference or Workshop Item"},{"id":"doi:10.48550/arxiv.1804.02204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.02204","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1804.02204","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.02204","pdf_url":"https://arxiv.org/pdf/1804.02204","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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2786872741.pdf","grobid_xml":"https://content.openalex.org/works/W2786872741.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W38527073","https://openalex.org/W196761320","https://openalex.org/W1779452081","https://openalex.org/W1970789124","https://openalex.org/W2003123121","https://openalex.org/W2006903949","https://openalex.org/W2071310251","https://openalex.org/W2098841537","https://openalex.org/W2102865215","https://openalex.org/W2110798204","https://openalex.org/W2114016253","https://openalex.org/W2125234026","https://openalex.org/W2150907703","https://openalex.org/W2160815625","https://openalex.org/W2167729035","https://openalex.org/W2288371874","https://openalex.org/W2288402171","https://openalex.org/W2403195671","https://openalex.org/W2436219157","https://openalex.org/W4205130185","https://openalex.org/W6608133726","https://openalex.org/W6636915900","https://openalex.org/W6638005537","https://openalex.org/W6639024717","https://openalex.org/W6640002369","https://openalex.org/W6674632333","https://openalex.org/W6676481782","https://openalex.org/W6682398751","https://openalex.org/W6684497637","https://openalex.org/W6713606482"],"related_works":["https://openalex.org/W2963855604","https://openalex.org/W2962780420","https://openalex.org/W3136329410","https://openalex.org/W2403040875","https://openalex.org/W2904665590","https://openalex.org/W1932057668","https://openalex.org/W3134477793","https://openalex.org/W3096709315","https://openalex.org/W2945697643","https://openalex.org/W2905519666","https://openalex.org/W3203740280","https://openalex.org/W2785921341","https://openalex.org/W3025887512","https://openalex.org/W2944469930","https://openalex.org/W2737818580","https://openalex.org/W3146142312","https://openalex.org/W2759725600","https://openalex.org/W2963904364","https://openalex.org/W2886512927","https://openalex.org/W3119411509"],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Network":[2],"(DNN)":[3],"acoustic":[4],"models":[5],"often":[6],"use":[7],"discriminative":[8,96],"sequence":[9,95],"training":[10,28,97],"that":[11,16,51,116],"optimises":[12],"an":[13,45],"objective":[14],"function":[15],"better":[17],"approximates":[18],"the":[19,61,66,70,74,76,86,102,119,123,126],"word":[20],"error":[21],"rate":[22],"(WER)":[23],"than":[24,83],"frame-based":[25],"training.":[26,41],"Sequence":[27],"is":[29,105],"normally":[30],"implemented":[31],"using":[32,107],"Stochastic":[33],"Gradient":[34,55],"Descent":[35],"(SGD)":[36],"or":[37],"Hessian":[38],"Free":[39],"(HF)":[40],"This":[42],"paper":[43],"proposes":[44],"alternative":[46],"batch":[47],"style":[48],"optimisation":[49,78],"framework":[50],"employs":[52],"a":[53,110],"Natural":[54],"(NG)":[56],"approach":[57,89],"to":[58,69,93],"traverse":[59],"through":[60],"parameter":[62],"space.":[63],"By":[64],"correcting":[65],"gradient":[67],"according":[68],"local":[71],"curvature":[72],"of":[73,101,125],"KL-divergence,":[75],"NG":[77,88,103],"process":[79],"converges":[80],"more":[81],"quickly":[82],"HF.":[84],"Furthermore,":[85],"proposed":[87],"can":[90],"be":[91],"applied":[92],"any":[94],"criterion.":[98],"The":[99],"efficacy":[100],"method":[104],"shown":[106],"experiments":[108],"on":[109],"Multi-Genre":[111],"Broadcast":[112],"(MGB)":[113],"transcription":[114],"task":[115],"demonstrates":[117],"both":[118],"computational":[120],"efficiency":[121],"and":[122],"accuracy":[124],"resulting":[127],"DNN":[128],"models.":[129]},"counts_by_year":[],"updated_date":"2026-02-24T19:35:01.260952","created_date":"2025-10-10T00:00:00"}