{"id":"https://openalex.org/W2938255784","doi":"https://doi.org/10.1109/icassp.2019.8683330","title":"On the Usefulness of Statistical Normalisation of Bottleneck Features for Speech Recognition","display_name":"On the Usefulness of Statistical Normalisation of Bottleneck Features for Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938255784","doi":"https://doi.org/10.1109/icassp.2019.8683330","mag":"2938255784"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/0d5be74b-e488-4aac-9645-d073212b2e32","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042184515","display_name":"Erfan Loweimi","orcid":"https://orcid.org/0000-0002-8761-021X"},"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":"Erfan Loweimi","raw_affiliation_strings":["Centre for Speech Technology Research (CSTR), School of Informatics, The University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), School of Informatics, The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"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":"Peter Bell","raw_affiliation_strings":["Centre for Speech Technology Research (CSTR), School of Informatics, The University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), School of Informatics, The University of Edinburgh","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 (CSTR), School of Informatics, The University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), School of Informatics, The University of Edinburgh","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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3862","last_page":"3866"},"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":0.9994999766349792,"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":0.9958999752998352,"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/bottleneck","display_name":"Bottleneck","score":0.8237528800964355},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.6709694862365723},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6610069274902344},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5948305130004883},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5663652420043945},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.5155941843986511},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.49955320358276367},{"id":"https://openalex.org/keywords/probability-density-function","display_name":"Probability density function","score":0.4838653802871704},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4830351769924164},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4769377112388611},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41490811109542847},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41311943531036377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40011146664619446},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22029250860214233},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20017951726913452},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14089366793632507},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11522957682609558}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8237528800964355},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.6709694862365723},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6610069274902344},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5948305130004883},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5663652420043945},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.5155941843986511},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.49955320358276367},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.4838653802871704},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4830351769924164},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4769377112388611},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41490811109542847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41311943531036377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40011146664619446},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22029250860214233},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20017951726913452},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14089366793632507},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11522957682609558},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8683330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/0d5be74b-e488-4aac-9645-d073212b2e32","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/0d5be74b-e488-4aac-9645-d073212b2e32","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":"Loweimi, E, Bell, P & Renals, S 2019, On the Usefulness of Statistical Normalisation of Bottleneck Features for Speech Recognition. in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, Brighton, United Kingdom, pp. 3862-3866, 44th International Conference on Acoustics, Speech, and Signal Processing, Brighton , United Kingdom, 12/05/19. https://doi.org/10.1109/ICASSP.2019.8683330","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/0d5be74b-e488-4aac-9645-d073212b2e32","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/0d5be74b-e488-4aac-9645-d073212b2e32","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":""},{"id":"pmh:oai:repository@napier.ac.uk:3585904","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3585904","pdf_url":null,"source":{"id":"https://openalex.org/S4306402591","display_name":"Edinburgh Napier Research Repository (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"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":"Presentation / Conference Contribution"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/0d5be74b-e488-4aac-9645-d073212b2e32","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/0d5be74b-e488-4aac-9645-d073212b2e32","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":"Loweimi, E, Bell, P & Renals, S 2019, On the Usefulness of Statistical Normalisation of Bottleneck Features for Speech Recognition. in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, Brighton, United Kingdom, pp. 3862-3866, 44th International Conference on Acoustics, Speech, and Signal Processing, Brighton , United Kingdom, 12/05/19. https://doi.org/10.1109/ICASSP.2019.8683330","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3297227137","display_name":null,"funder_award_id":"EP/R012180/1","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":32,"referenced_works":["https://openalex.org/W1512746852","https://openalex.org/W1523985187","https://openalex.org/W1524333225","https://openalex.org/W1589170661","https://openalex.org/W1985368711","https://openalex.org/W2012897754","https://openalex.org/W2042422091","https://openalex.org/W2046245205","https://openalex.org/W2062164080","https://openalex.org/W2117671523","https://openalex.org/W2126597753","https://openalex.org/W2156387975","https://openalex.org/W2159948109","https://openalex.org/W2171000037","https://openalex.org/W2397634864","https://openalex.org/W2510217521","https://openalex.org/W2533523411","https://openalex.org/W2604132379","https://openalex.org/W2746013913","https://openalex.org/W2801848743","https://openalex.org/W2805215415","https://openalex.org/W2942228371","https://openalex.org/W2963266252","https://openalex.org/W2963285578","https://openalex.org/W6631362777","https://openalex.org/W6635241538","https://openalex.org/W6682889407","https://openalex.org/W6685562342","https://openalex.org/W6712325649","https://openalex.org/W6728841359","https://openalex.org/W6735593169","https://openalex.org/W6752308553"],"related_works":["https://openalex.org/W2385368906","https://openalex.org/W2902924992","https://openalex.org/W2626642044","https://openalex.org/W2619807045","https://openalex.org/W2388758053","https://openalex.org/W93537448","https://openalex.org/W2949734191","https://openalex.org/W2061808167","https://openalex.org/W1937731701","https://openalex.org/W2545529375"],"abstract_inverted_index":{"DNNs":[0,42],"play":[1],"a":[2,44,90,94],"major":[3],"role":[4],"in":[5,81,149],"the":[6,31,49,55,58,78,82,101,109,113,115,150],"state-of-the-art":[7],"ASR":[8],"systems.":[9],"They":[10],"can":[11,85],"be":[12,86],"used":[13],"for":[14,21],"extracting":[15],"features":[16,122],"and":[17,23,60,64,69,97,99,135,141],"building":[18],"probabilistic":[19],"models":[20],"acoustic":[22],"language":[24],"modelling.":[25],"Despite":[26],"their":[27],"huge":[28],"practical":[29],"success,":[30],"level":[32],"of":[33,51,57,112,117,120],"theoretical":[34],"understanding":[35],"has":[36],"remained":[37],"shallow.":[38],"This":[39,72],"paper":[40],"investigates":[41],"from":[43,66],"statistical":[45,110,118],"standpoint.":[46],"In":[47],"particular,":[48],"effect":[50],"activation":[52,103],"functions":[53],"on":[54],"distribution":[56],"pre-activations":[59],"activations":[61],"is":[62],"investigated":[63],"discussed":[65],"both":[67],"analytic":[68],"empirical":[70],"viewpoints.":[71],"study,":[73],"among":[74],"others,":[75],"shows":[76],"that":[77],"pre-activation":[79],"density":[80],"bottleneck":[83,121],"layer":[84],"well":[87],"fitted":[88],"with":[89,93],"diagonal":[91],"GMM":[92],"few":[95],"Gaussians":[96],"how":[98],"why":[100],"ReLU":[102],"function":[104],"promotes":[105],"sparsity.":[106],"Motivated":[107],"by":[108],"properties":[111],"pre-activations,":[114],"usefulness":[116],"normalisation":[119],"was":[123],"also":[124],"investigated.":[125],"To":[126],"this":[127],"end,":[128],"methods":[129],"such":[130],"as":[131],"mean(-variance)":[132],"normalisation,":[133],"Gaussianisation,":[134],"histogram":[136],"equalisation":[137],"(HEQ)":[138],"were":[139],"employed":[140],"up":[142],"to":[143],"2%":[144],"(absolute)":[145],"WER":[146],"reduction":[147],"achieved":[148],"Aurora-4":[151],"task.":[152]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}