{"id":"https://openalex.org/W1951281464","doi":"https://doi.org/10.1109/icassp.2015.7178841","title":"Multi-frame factorisation for long-span acoustic modelling","display_name":"Multi-frame factorisation for long-span acoustic modelling","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1951281464","doi":"https://doi.org/10.1109/icassp.2015.7178841","mag":"1951281464"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/9eb1f14e-d51c-4e2b-a88e-fa1203a275d5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","Centre for Speech Technology Research, University of Edinburgh,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","Centre for Speech Technology Research, University of Edinburgh,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh,UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"4595","last_page":"4599"},"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":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.6653882265090942},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6304680705070496},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5642363429069519},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5411123633384705},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5346730351448059},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.5274235010147095},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.49919748306274414},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4934755563735962},{"id":"https://openalex.org/keywords/joint-probability-distribution","display_name":"Joint probability distribution","score":0.4895726144313812},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4782544672489166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47290313243865967},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"Conditional independence","score":0.46716392040252686},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4600391983985901},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4433916509151459},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4420918822288513},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.41724854707717896},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.36928820610046387},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21826249361038208},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13421416282653809},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08416199684143066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6653882265090942},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6304680705070496},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5642363429069519},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5411123633384705},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5346730351448059},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.5274235010147095},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.49919748306274414},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4934755563735962},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.4895726144313812},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4782544672489166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47290313243865967},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.46716392040252686},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4600391983985901},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4433916509151459},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4420918822288513},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.41724854707717896},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.36928820610046387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21826249361038208},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13421416282653809},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08416199684143066},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2015.7178841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.717.1041","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.717.1041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2015/llu_icassp15.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/9eb1f14e-d51c-4e2b-a88e-fa1203a275d5","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/9eb1f14e-d51c-4e2b-a88e-fa1203a275d5","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, L & Renals, S 2015, Multi-frame factorisation for long-span acoustic modelling. in Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing.","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/9eb1f14e-d51c-4e2b-a88e-fa1203a275d5","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/9eb1f14e-d51c-4e2b-a88e-fa1203a275d5","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/9eb1f14e-d51c-4e2b-a88e-fa1203a275d5","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/9eb1f14e-d51c-4e2b-a88e-fa1203a275d5","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, L & Renals, S 2015, Multi-frame factorisation for long-span acoustic modelling. in Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing.","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W9486812","https://openalex.org/W811578723","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1967940534","https://openalex.org/W1978741356","https://openalex.org/W1979449467","https://openalex.org/W1981706894","https://openalex.org/W1993721840","https://openalex.org/W1993882792","https://openalex.org/W1994396704","https://openalex.org/W2001900102","https://openalex.org/W2012897754","https://openalex.org/W2014966567","https://openalex.org/W2071489795","https://openalex.org/W2083393647","https://openalex.org/W2104448323","https://openalex.org/W2106554350","https://openalex.org/W2111732304","https://openalex.org/W2125838338","https://openalex.org/W2131033001","https://openalex.org/W2142027531","https://openalex.org/W2147768505","https://openalex.org/W2151125621","https://openalex.org/W2160815625","https://openalex.org/W2165712214","https://openalex.org/W2166637769","https://openalex.org/W2169189000","https://openalex.org/W2294692935","https://openalex.org/W2793131830","https://openalex.org/W3099938644","https://openalex.org/W6600402101","https://openalex.org/W6631362777","https://openalex.org/W6675701829","https://openalex.org/W6697843868","https://openalex.org/W6891771408"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W1995680679","https://openalex.org/W1992295166","https://openalex.org/W2143508933","https://openalex.org/W4306317269","https://openalex.org/W4291632780","https://openalex.org/W2964200874","https://openalex.org/W4244332233"],"abstract_inverted_index":{"Acoustic":[0],"models":[1,6,91],"based":[2,90],"on":[3,92],"Gaussian":[4],"mixture":[5],"(GMMs)":[7],"typically":[8],"use":[9],"short":[10],"span":[11,49],"acoustic":[12,77],"feature":[13,65],"inputs.":[14],"This":[15],"does":[16],"not":[17],"capture":[18],"long-term":[19],"temporal":[20],"information":[21],"from":[22],"speech":[23],"owing":[24],"to":[25,58,72],"the":[26,44],"conditional":[27],"independence":[28],"assumption":[29],"of":[30,47,53,76],"hidden":[31],"Markov":[32],"models.":[33,78],"In":[34],"this":[35],"paper,":[36],"we":[37],"present":[38,80],"an":[39],"implicit":[40],"approach":[41,69],"that":[42,63],"approximates":[43],"joint":[45],"distribution":[46],"long":[48],"features":[50],"by":[51],"product":[52],"factorized":[54],"models,":[55],"in":[56],"contrast":[57],"deep":[59],"neural":[60],"networks":[61],"(DNNs)":[62],"model":[64],"correlations":[66],"directly.":[67],"The":[68],"is":[70],"applicable":[71],"a":[73],"broad":[74],"range":[75],"We":[79],"experiments":[81],"using":[82],"GMM":[83],"and":[84],"probabilistic":[85],"linear":[86],"discriminant":[87],"analysis":[88],"(PLDA)":[89],"Switchboard,":[93],"observing":[94],"consistent":[95],"word":[96],"error":[97],"rate":[98],"reductions.":[99]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}