{"id":"https://openalex.org/W2746517539","doi":"https://doi.org/10.21437/interspeech.2017-1233","title":"Deep Activation Mixture Model for Speech Recognition","display_name":"Deep Activation Mixture Model for Speech Recognition","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2746517539","doi":"https://doi.org/10.21437/interspeech.2017-1233","mag":"2746517539"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1233","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.17863/cam.21414","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101579713","display_name":"Chunyang Wu","orcid":"https://orcid.org/0000-0002-0269-3555"},"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":"Chunyang Wu","raw_affiliation_strings":["Trumpington St., Cambridge, CB2 1PZ, U.K","Cambridge University Engineering Dept,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Trumpington St., Cambridge, CB2 1PZ, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Cambridge University Engineering Dept,","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"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":"Mark J.F. Gales","raw_affiliation_strings":["Trumpington St., Cambridge, CB2 1PZ, U.K","Cambridge University Engineering Dept,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Trumpington St., Cambridge, CB2 1PZ, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Cambridge University Engineering Dept,","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1611","last_page":"1615"},"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":0.9986000061035156,"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":0.9973000288009644,"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":0.786855936050415},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6923251748085022},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6543446779251099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5867834687232971},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5834052562713623},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5480289459228516},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.538946270942688},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5367281436920166},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.508468508720398},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.508361279964447},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.504379153251648},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4977777302265167},{"id":"https://openalex.org/keywords/activation-function","display_name":"Activation function","score":0.4701923131942749},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.44259345531463623},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43663308024406433},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43648481369018555},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4318457841873169},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28542232513427734},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10572761297225952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786855936050415},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6923251748085022},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6543446779251099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867834687232971},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5834052562713623},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5480289459228516},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.538946270942688},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5367281436920166},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.508468508720398},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.508361279964447},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.504379153251648},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4977777302265167},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.4701923131942749},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.44259345531463623},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43663308024406433},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43648481369018555},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4318457841873169},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28542232513427734},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10572761297225952},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2017-1233","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:962790","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/962790/","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":"pmh:oai:www.repository.cam.ac.uk:1810/274290","is_oa":false,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/274290","pdf_url":null,"source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":"Conference Object"},{"id":"doi:10.17863/cam.21414","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.21414","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Other"}],"best_oa_location":{"id":"doi:10.17863/cam.21414","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.21414","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Other"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5746128741","display_name":null,"funder_award_id":"4912046943","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"}],"funders":[{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W1218987319","https://openalex.org/W1513820424","https://openalex.org/W1525807100","https://openalex.org/W1539668574","https://openalex.org/W1545083717","https://openalex.org/W1558606374","https://openalex.org/W1567690964","https://openalex.org/W1571447047","https://openalex.org/W1579853615","https://openalex.org/W1961429348","https://openalex.org/W1990505856","https://openalex.org/W2080005694","https://openalex.org/W2094035326","https://openalex.org/W2094147890","https://openalex.org/W2095705004","https://openalex.org/W2117130368","https://openalex.org/W2147768505","https://openalex.org/W2148464528","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2187089797","https://openalex.org/W2288977568","https://openalex.org/W2397184916","https://openalex.org/W2397381476","https://openalex.org/W2403731734","https://openalex.org/W2407299475","https://openalex.org/W2508220198"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2803957979","https://openalex.org/W2735380212"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"approaches":[2],"achieve":[3],"state-of-the-art":[4],"performance":[5,127,143],"in":[6],"a":[7,63,97,115,124],"range":[8],"of":[9,17,53,62,87],"applications,":[10],"including":[11],"speech":[12],"recognition.":[13],"However,":[14],"the":[15,18,41,60,77,83,88,101,129,134,138],"parameters":[16],"deep":[19,42],"neural":[20],"network":[21],"(DNN)":[22],"are":[23],"hard":[24],"to":[25,32,47],"interpret,":[26],"which":[27],"makes":[28],"regularisation":[29,99],"and":[30,65,132],"adaptation":[31,107],"speaker":[33],"or":[34],"acoustic":[35],"conditions":[36],"challenging.":[37],"This":[38],"paper":[39],"proposes":[40],"activation":[43,73],"mixture":[44,64,69,89],"model":[45,70,90],"(DAMM)":[46],"address":[48],"these":[49],"problems.":[50],"The":[51,68,85,109],"output":[52],"one":[54,79],"hidden":[55],"layer":[56],"is":[57,112],"modelled":[58],"as":[59],"sum":[61],"residual":[66,78],"models.":[67],"forms":[71],"an":[72],"function":[74],"contour":[75],"while":[76],"models":[80],"fluctuations":[81],"around":[82],"contour.":[84],"use":[86],"gives":[91],"two":[92],"advantages:":[93],"First,":[94],"it":[95,104],"introduces":[96],"novel":[98,106],"on":[100,114,133],"DNN.":[102],"Second,":[103],"allows":[105],"schemes.":[108],"proposed":[110],"approach":[111],"evaluated":[113],"large-vocabulary":[116],"U.S.":[117],"English":[118],"broadcast":[119],"news":[120],"task.":[121],"It":[122],"yields":[123],"slightly":[125],"better":[126],"than":[128],"DNN":[130],"baselines,":[131],"utterance-level":[135],"unsupervised":[136],"adaptation,":[137],"adapted":[139],"DAMM":[140],"acquires":[141],"further":[142],"gains.":[144]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}