{"id":"https://openalex.org/W2900200882","doi":"https://doi.org/10.1109/slt.2018.8639036","title":"Analyzing Deep CNN-Based Utterance Embeddings for Acoustic Model Adaptation","display_name":"Analyzing Deep CNN-Based Utterance Embeddings for Acoustic Model Adaptation","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2900200882","doi":"https://doi.org/10.1109/slt.2018.8639036","mag":"2900200882"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.04708","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026578899","display_name":"Joanna Rownicka","orcid":null},"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":"Joanna Rownicka","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","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":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","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":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","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":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"235","last_page":"241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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":0.9977999925613403,"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":0.8016268014907837},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6463289856910706},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6094224452972412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.596577525138855},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5787292718887329},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5724359154701233},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5707157254219055},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.560375988483429},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5450234413146973},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4582881033420563},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45508673787117004},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4320388436317444},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4288424849510193},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42213866114616394},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4165025055408478},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.23110324144363403},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08009707927703857},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06587338447570801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016268014907837},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6463289856910706},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6094224452972412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.596577525138855},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5787292718887329},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5724359154701233},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5707157254219055},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.560375988483429},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5450234413146973},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4582881033420563},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45508673787117004},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4320388436317444},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4288424849510193},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42213866114616394},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4165025055408478},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.23110324144363403},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08009707927703857},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06587338447570801},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":4,"locations":[{"id":"doi:10.1109/slt.2018.8639036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.04708","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.04708","pdf_url":"https://arxiv.org/pdf/1811.04708","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":"pmh:oai:pure.ed.ac.uk:publications/c396c8e9-e810-445e-b6ad-2be94fbe760f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/c396c8e9-e810-445e-b6ad-2be94fbe760f","pdf_url":"https://www.research.ed.ac.uk/files/80931278/slt18_embeddings.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"R\u00f3wnicka, J, Bell, P & Renals, S 2019, Analyzing deep CNN-based utterance embeddings for acoustic model adaptation. in 2018 IEEE Spoken Language Technology Workshop (SLT). Institute of Electrical and Electronics Engineers, pp. 235-241, 2018 IEEE Workshop on Spoken Language Technology (SLT), Athens, Greece, 18/12/18. https://doi.org/10.1109/SLT.2018.8639036","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/c396c8e9-e810-445e-b6ad-2be94fbe760f","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/c396c8e9-e810-445e-b6ad-2be94fbe760f","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:arXiv.org:1811.04708","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.04708","pdf_url":"https://arxiv.org/pdf/1811.04708","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1987841215","https://openalex.org/W1995562189","https://openalex.org/W2079623482","https://openalex.org/W2097117768","https://openalex.org/W2117671523","https://openalex.org/W2150769028","https://openalex.org/W2163605009","https://openalex.org/W2188183693","https://openalex.org/W2198724430","https://openalex.org/W2292414329","https://openalex.org/W2398319612","https://openalex.org/W2398776621","https://openalex.org/W2402146185","https://openalex.org/W2515863432","https://openalex.org/W2519224033","https://openalex.org/W2533523411","https://openalex.org/W2657631929","https://openalex.org/W2735006420","https://openalex.org/W2786152338","https://openalex.org/W2792641098","https://openalex.org/W2797187289","https://openalex.org/W2890964092","https://openalex.org/W2916979304","https://openalex.org/W2962835968","https://openalex.org/W2963174142","https://openalex.org/W4229494842","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6712474730","https://openalex.org/W6712930963","https://openalex.org/W6726720044","https://openalex.org/W6728841359","https://openalex.org/W6748624906"],"related_works":["https://openalex.org/W2944691285","https://openalex.org/W151018310","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W4385611764"],"abstract_inverted_index":{"We":[0,26,82,111,133],"explore":[1,53],"why":[2],"deep":[3,32,38,136,151],"convolutional":[4],"neural":[5,39,123],"networks":[6],"(CNNs)":[7],"with":[8,37],"small":[9],"two-dimensional":[10],"kernels,":[11],"primarily":[12],"used":[13],"for":[14,120,126,142],"modeling":[15],"spatial":[16],"relations":[17],"in":[18,23,45,155],"images,":[19],"are":[20],"also":[21,112],"effective":[22],"speech":[24],"recognition.":[25],"analyze":[27],"the":[28,46,61,79,90,94,104,109,117,127],"representations":[29,42,63,115],"learned":[30,62,92,114],"by":[31],"CNNs":[33],"and":[34,43,76,97,129,146],"compare":[35],"them":[36],"network":[40,124],"(DNN)":[41],"i-vectors,":[44],"context":[47],"of":[48,103,106],"acoustic":[49,72,143],"model":[50,86,144],"adaptation.":[51],"To":[52],"whether":[54],"interpretable":[55],"information":[56,91,107],"can":[57],"be":[58],"decoded":[59],"from":[60],"we":[64],"evaluate":[65],"their":[66],"ability":[67],"to":[68,160],"discriminate":[69],"between":[70],"speakers,":[71],"conditions,":[73],"noise":[74],"type,":[75],"gender":[77],"using":[78],"Aurora-4":[80,128],"dataset.":[81],"extract":[83],"both":[84],"whole":[85,95],"embeddings":[87,99,138,141,153],"(to":[88],"capture":[89],"across":[93,108],"network)":[96],"layer-specific":[98],"which":[100],"enable":[101],"understanding":[102],"flow":[105],"network.":[110],"use":[113],"as":[116],"additional":[118],"input":[119],"a":[121],"time-delay":[122],"(TDNN)":[125],"MGB-3":[130],"English":[131],"datasets.":[132],"find":[134],"that":[135],"CNN":[137,152],"outperform":[139],"DNN":[140],"adaptation":[145],"auxiliary":[147],"features":[148],"based":[149],"on":[150],"result":[154],"similar":[156],"word":[157],"error":[158],"rates":[159],"i-vectors.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-08-02T00:00:00"}