{"id":"https://openalex.org/W2889322843","doi":"https://doi.org/10.21437/interspeech.2018-2462","title":"Exploring How Phone Classification Neural Networks Learn Phonetic Information by Visualising and Interpreting Bottleneck Features","display_name":"Exploring How Phone Classification Neural Networks Learn Phonetic Information by Visualising and Interpreting Bottleneck Features","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889322843","doi":"https://doi.org/10.21437/interspeech.2018-2462","mag":"2889322843"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2462","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.birmingham.ac.uk/en/publications/ce96eee5-cc0c-4aac-9411-60cde80e5499","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109403866","display_name":"Linxue Bai","orcid":"https://orcid.org/0009-0008-0538-2307"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Linxue Bai","raw_affiliation_strings":["School of Engineering, The University of Birmingham, Birmingham B15 2TT, UK"],"affiliations":[{"raw_affiliation_string":"School of Engineering, The University of Birmingham, Birmingham B15 2TT, UK","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102937478","display_name":"Philip Weber","orcid":"https://orcid.org/0000-0002-3121-9625"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip Weber","raw_affiliation_strings":["School of Engineering, The University of Birmingham, Birmingham B15 2TT, UK"],"affiliations":[{"raw_affiliation_string":"School of Engineering, The University of Birmingham, Birmingham B15 2TT, UK","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031388449","display_name":"Peter Jan\u010dovi\u010d","orcid":"https://orcid.org/0000-0002-8897-1762"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Jan\u010dovi\u010d","raw_affiliation_strings":["School of Engineering, The University of Birmingham, Birmingham B15 2TT, UK"],"affiliations":[{"raw_affiliation_string":"School of Engineering, The University of Birmingham, Birmingham B15 2TT, UK","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079477816","display_name":"Martin Russell","orcid":"https://orcid.org/0000-0002-8324-4961"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martin Russell","raw_affiliation_strings":["School of Engineering, The University of Birmingham, Birmingham B15 2TT, UK"],"affiliations":[{"raw_affiliation_string":"School of Engineering, The University of Birmingham, Birmingham B15 2TT, UK","institution_ids":["https://openalex.org/I79619799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109403866"],"corresponding_institution_ids":["https://openalex.org/I79619799"],"apc_list":null,"apc_paid":null,"fwci":0.4954,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63641185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1472","last_page":"1476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T10320","display_name":"Neural Networks and Applications","score":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6950350999832153},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6323894262313843},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6185513734817505},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5958014726638794},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4943561553955078},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.44231584668159485},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.41611409187316895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4100729823112488},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40945667028427124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6950350999832153},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6323894262313843},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6185513734817505},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5958014726638794},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4943561553955078},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44231584668159485},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.41611409187316895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4100729823112488},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40945667028427124},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2018-2462","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:Publications/ce96eee5-cc0c-4aac-9411-60cde80e5499","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"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:pure.atira.dk:openaire_cris_publications/ce96eee5-cc0c-4aac-9411-60cde80e5499","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/ce96eee5-cc0c-4aac-9411-60cde80e5499","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"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":"Bai, L, Weber, P, Jancovic, P & Russell, M 2018, Exploring how phone classification neural networks learn phonetic information by visualising and interpreting bottleneck features. in Proceedings of Interspeech 2018. Interspeech, vol. 2018, ISCA, Hyderabad, India, pp. 1472-1476, Interspeech 2018, Hyderabad , India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-2462","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/ce96eee5-cc0c-4aac-9411-60cde80e5499","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/ce96eee5-cc0c-4aac-9411-60cde80e5499","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"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":"Bai, L, Weber, P, Jancovic, P & Russell, M 2018, Exploring how phone classification neural networks learn phonetic information by visualising and interpreting bottleneck features. in Proceedings of Interspeech 2018. Interspeech, vol. 2018, ISCA, Hyderabad, India, pp. 1472-1476, Interspeech 2018, Hyderabad , India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-2462","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1606347560","https://openalex.org/W1802969839","https://openalex.org/W1849277567","https://openalex.org/W1875842236","https://openalex.org/W2032759346","https://openalex.org/W2116064496","https://openalex.org/W2172097686","https://openalex.org/W2238198527","https://openalex.org/W2288977568","https://openalex.org/W2295676751","https://openalex.org/W2397149834","https://openalex.org/W2397976876","https://openalex.org/W2402196427","https://openalex.org/W2511774920","https://openalex.org/W2513670523","https://openalex.org/W2524611247","https://openalex.org/W2562713410","https://openalex.org/W2792641098","https://openalex.org/W2963749936","https://openalex.org/W3082371797","https://openalex.org/W4229494842"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2153098279"],"abstract_inverted_index":{"Neural":[0],"networks":[1],"have":[2,37],"a":[3,68,113,139,178],"reputation":[4],"for":[5,109],"being":[6],"\"black":[7],"boxes\",":[8],"which":[9,181],"it":[10],"has":[11],"been":[12,38],"suggested":[13],"that":[14,36,146,184],"techniques":[15],"from":[16,59,67],"user":[17],"interface":[18],"development":[19],"and":[20,54,83,122,187],"visualisation":[21],"in":[22,40,48,75],"particular,":[23],"could":[24],"help":[25],"lift.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30,176],"explore":[31],"9-dimensional":[32,64,121],"bottleneck":[33,60],"features":[34,108,170],"(BNFs)":[35],"shown":[39],"our":[41],"earlier":[42],"work":[43],"to":[44,97,105,137,159,161,168],"well":[45],"represent":[46],"speech":[47,52],"the":[49,118,132,154,169,190,196],"context":[50],"of":[51,120,141,156,171],"recognition":[53],"2-dimensional":[55,76,90,123,133],"BNFs":[56,65,124],"directly":[57],"extracted":[58],"neural":[61,71,115,197],"networks.":[62,198],"The":[63,89],"obtained":[66],"phone":[69,111,129,162],"classification":[70],"network":[72],"are":[73,189],"visualised":[74],"spaces":[77],"using":[78],"linear":[79],"discriminant":[80],"analysis":[81],"(LDA)":[82],"t-distributed":[84],"stochastic":[85],"neighbour":[86],"embedding":[87],"(t-SNE).":[88],"BNF":[91,134],"space":[92,135],"is":[93,103],"analysed":[94],"with":[95],"regard":[96],"phonetic":[98,142],"features.":[99],"A":[100],"back-propagation":[101],"method":[102],"used":[104],"create":[106],"\"cardinal\"":[107],"each":[110,151],"under":[112],"particular":[114],"network.":[116],"Both":[117],"visualisations":[119],"show":[125],"distinctions":[126],"between":[127],"most":[128],"categories.":[130],"Particularly,":[131],"seems":[136],"be":[138],"union":[140],"category":[143],"related":[144],"subspaces":[145],"preserve":[147],"local":[148],"structures":[149],"within":[150],"subspace":[152],"where":[153],"organisations":[155],"phones":[157],"appear":[158],"correspond":[160],"production":[163],"mechanisms.":[164],"By":[165],"applying":[166],"LDA":[167],"higher":[172],"dimensional":[173],"non-bottleneck":[174],"layers,":[175],"observe":[177],"triangular":[179],"pattern":[180],"may":[182],"indicate":[183],"silence,":[185],"friction":[186],"voicing":[188],"three":[191],"main":[192],"properties":[193],"learned":[194],"by":[195]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}