{"id":"https://openalex.org/W2593894653","doi":"https://doi.org/10.1109/icassp.2017.7953111","title":"Joint optimisation of tandem systems using Gaussian mixture density neural network discriminative sequence training","display_name":"Joint optimisation of tandem systems using Gaussian mixture density neural network discriminative sequence training","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2593894653","doi":"https://doi.org/10.1109/icassp.2017.7953111","mag":"2593894653"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953111","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":"conference-paper","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/A5007989522","display_name":"C. Zhang","orcid":"https://orcid.org/0000-0002-2173-6872"},"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"C. Zhang","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Cambridge, U.K","institution_ids":["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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"P. C. Woodland","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5015","last_page":"5019"},"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":0.9988999962806702,"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":0.9983999729156494,"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":0.9228652715682983},{"id":"https://openalex.org/keywords/tandem","display_name":"Tandem","score":0.7564398050308228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7445478439331055},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7326886057853699},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6359330415725708},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6016285419464111},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5787392854690552},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5625160932540894},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5225531458854675},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.513892412185669},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4630567729473114},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4471026360988617},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4426569640636444},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42650914192199707},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.41982147097587585},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06556981801986694}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9228652715682983},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.7564398050308228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445478439331055},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7326886057853699},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6359330415725708},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6016285419464111},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5787392854690552},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5625160932540894},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5225531458854675},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.513892412185669},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4630567729473114},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4471026360988617},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4426569640636444},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42650914192199707},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.41982147097587585},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06556981801986694},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2017.7953111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953111","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:generic.eprints.org:922325","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/922325/","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7699999809265137}],"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":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W14913773","https://openalex.org/W38527073","https://openalex.org/W1521415669","https://openalex.org/W1538748823","https://openalex.org/W1553004968","https://openalex.org/W1558606374","https://openalex.org/W1665214252","https://openalex.org/W1992912377","https://openalex.org/W2002257715","https://openalex.org/W2012897754","https://openalex.org/W2019973879","https://openalex.org/W2098601596","https://openalex.org/W2100969003","https://openalex.org/W2125234026","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2154887136","https://openalex.org/W2158069733","https://openalex.org/W2160650576","https://openalex.org/W2165712214","https://openalex.org/W2288402171","https://openalex.org/W2291282366","https://openalex.org/W2296705629","https://openalex.org/W2394932179","https://openalex.org/W2396630453","https://openalex.org/W2401430117","https://openalex.org/W2407299475","https://openalex.org/W2407698769","https://openalex.org/W2594639291","https://openalex.org/W3149335959","https://openalex.org/W6600588093","https://openalex.org/W6601546718","https://openalex.org/W6637242042","https://openalex.org/W6678457041","https://openalex.org/W6697336780","https://openalex.org/W6711808165","https://openalex.org/W6711962127","https://openalex.org/W6713507411","https://openalex.org/W6713606482"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2146591867","https://openalex.org/W2162582511","https://openalex.org/W2032826752","https://openalex.org/W1992295166","https://openalex.org/W2143508933"],"abstract_inverted_index":{"The":[0,138],"use":[1,41],"of":[2,42,83,96,131,161],"deep":[3],"neural":[4,34],"networks":[5],"(DNNs)":[6],"for":[7,15],"feature":[8,61],"extraction":[9,62],"and":[10,25,64,105],"Gaussian":[11,31],"mixture":[12,32],"models":[13,68],"(GMMs)":[14],"acoustic":[16,48,67,86],"modelling":[17],"is":[18,98],"often":[19],"termed":[20],"a":[21,30,55,75,121,132],"tandem":[22,51,85,136,142],"system":[23],"configuration":[24],"can":[26],"be":[27],"viewed":[28],"as":[29],"density":[33],"network":[35],"(MDNN).":[36],"Compared":[37],"to":[38,79,100,148],"the":[39,47,50,60,65,81,84,102,109,117,158],"direct":[40],"DNN":[43,150],"output":[44],"probabilities":[45],"in":[46,58,146],"model,":[49],"approach":[52,78],"suffers":[53],"from":[54],"major":[56],"weakness":[57],"that":[59,116,130],"stage":[63],"final":[66],"are":[69,144],"optimised":[70,141,152],"separately.":[71],"This":[72],"paper":[73],"proposes":[74],"joint":[76],"optimisation":[77],"all":[80],"stages":[82],"model":[87],"by":[88],"using":[89,108,153],"MDNN":[90],"discriminative":[91,154],"sequence":[92,155],"training.":[93],"A":[94],"set":[95],"techniques":[97],"used":[99],"improve":[101],"training":[103,156],"performance":[104],"stability.":[106],"Experiments":[107],"multi-genre":[110],"broadcast":[111],"(MGB)":[112],"English":[113],"data":[114],"show":[115],"proposed":[118],"method":[119],"produced":[120],"6%":[122],"relative":[123],"lower":[124],"word":[125],"error":[126],"rate":[127],"(WER)":[128],"than":[129],"traditional":[133],"discriminatively":[134],"trained":[135],"system.":[137],"resulting":[139],"jointly":[140],"systems":[143,151],"comparable":[145],"WER":[147],"hybrid":[149],"with":[157],"same":[159],"number":[160],"parameters.":[162]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}