{"id":"https://openalex.org/W2747774782","doi":"https://doi.org/10.21437/interspeech.2017-1179","title":"Phone Classification Using a Non-Linear Manifold with Broad Phone Class Dependent DNNs","display_name":"Phone Classification Using a Non-Linear Manifold with Broad Phone Class Dependent DNNs","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2747774782","doi":"https://doi.org/10.21437/interspeech.2017-1179","mag":"2747774782"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1179","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1179","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.birmingham.ac.uk/en/publications/e385dedf-38a7-4da5-924e-d290edbd831f","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":["Department of Electronic Electrical and Systems Engineering, The University of Birmingham, Birmingham B15 2TT, UK"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Electrical and Systems 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":["Department of Electronic Electrical and Systems Engineering, The University of Birmingham, Birmingham B15 2TT, UK"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Electrical and Systems Engineering, The University of Birmingham, Birmingham B15 2TT, UK","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","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":["Department of Electronic Electrical and Systems Engineering, The University of Birmingham, Birmingham B15 2TT, UK"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Electrical and Systems 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":["Department of Electronic Electrical and Systems Engineering, The University of Birmingham, Birmingham B15 2TT, UK"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Electrical and Systems Engineering, The University of Birmingham, Birmingham B15 2TT, UK","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"last","author":{"id":null,"display_name":"Steve Houghton","orcid":null},"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":"Steve Houghton","raw_affiliation_strings":["Department of Electronic Electrical and Systems Engineering, The University of Birmingham, Birmingham B15 2TT, UK"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Electrical and Systems Engineering, The University of Birmingham, Birmingham B15 2TT, UK","institution_ids":["https://openalex.org/I79619799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109403866"],"corresponding_institution_ids":["https://openalex.org/I79619799"],"apc_list":null,"apc_paid":null,"fwci":0.5596,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65604141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"319","last_page":"323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":0.9998000264167786,"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":0.9998000264167786,"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/timit","display_name":"TIMIT","score":0.8235898613929749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7056899070739746},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6795958280563354},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6179283261299133},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5483031868934631},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5261306762695312},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.46614280343055725},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4497912526130676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43419700860977173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42886820435523987},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3559767007827759},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3291783630847931}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8235898613929749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056899070739746},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6795958280563354},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6179283261299133},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5483031868934631},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5261306762695312},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.46614280343055725},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4497912526130676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43419700860977173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42886820435523987},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3559767007827759},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3291783630847931},{"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/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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2017-1179","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1179","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:pure.atira.dk:Publications/e385dedf-38a7-4da5-924e-d290edbd831f","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/e385dedf-38a7-4da5-924e-d290edbd831f","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/e385dedf-38a7-4da5-924e-d290edbd831f","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, Jancovic, P, Russell, M, Weber, P & Houghton, S 2017, Phone classification using a non-linear manifold with broad phone class dependent DNNs. in Proceedings of Interspeech 2017. Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-1179","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:publications/e385dedf-38a7-4da5-924e-d290edbd831f","is_oa":false,"landing_page_url":"https://www.isca-speech.org/archive/Interspeech_2017/index.html","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":null}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/e385dedf-38a7-4da5-924e-d290edbd831f","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/e385dedf-38a7-4da5-924e-d290edbd831f","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, Jancovic, P, Russell, M, Weber, P & Houghton, S 2017, Phone classification using a non-linear manifold with broad phone class dependent DNNs. in Proceedings of Interspeech 2017. Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-1179","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1512581325","https://openalex.org/W1606347560","https://openalex.org/W1932968309","https://openalex.org/W1980076831","https://openalex.org/W1980399492","https://openalex.org/W1998523266","https://openalex.org/W2032625358","https://openalex.org/W2072149862","https://openalex.org/W2077804127","https://openalex.org/W2078279533","https://openalex.org/W2102898380","https://openalex.org/W2238198527","https://openalex.org/W2397149834","https://openalex.org/W2402340204","https://openalex.org/W2513670523"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W4300326282","https://openalex.org/W2742395793","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2915887922","https://openalex.org/W2903939003"],"abstract_inverted_index":{"Most":[0],"state-of-the-art":[1],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"systems":[6],"use":[7,69,128],"a":[8,63,71,89,104,174],"single":[9,48,175],"deep":[10],"neural":[11],"network":[12],"(DNN)":[13],"to":[14,19,45,137,173],"map":[15],"the":[16,20,68,100,113,122,127,130,138,142,160,184,188],"acoustic":[17],"space":[18],"decision":[21],"space.":[22],"However,":[23],"different":[24,28,36,144],"phonetic":[25],"classes":[26],"employ":[27],"production":[29],"mechanisms":[30],"and":[31,99,111,141,190,193],"are":[32,118,151],"best":[33],"described":[34],"by":[35,187],"types":[37],"of":[38,70,91,109,124,129,183,195],"features.":[39],"Hence":[40],"it":[41],"may":[42],"be":[43],"<br/>advantageous":[44],"replace":[46],"this":[47,61],"DNN":[49],"with":[50,75,181],"several":[51],"phone":[52,79,93,169],"class":[53,94,146],"dependent":[54,96],"DNNs.":[55],"The":[56,81,86,155,178],"appropriate":[57],"mathematical":[58],"formalism":[59],"for":[60,78],"is":[62,103],"manifold.":[64],"This":[65],"paper":[66,179],"assesses":[67],"nonlinear":[72],"manifold":[73],"structure":[74],"multiple":[76],"DNNs":[77,162,192],"classification.":[80],"system":[82],"has":[83],"two":[84],"levels.":[85],"first":[87],"comprises":[88],"set":[90],"broad":[92,145],"(BPC)":[95],"DNN-based":[97],"mappings":[98],"second":[101],"level":[102],"fusion":[105,139],"network.":[106],"Various":[107],"ways":[108],"designing":[110],"training":[112],"networks":[114],"in":[115,168],"both":[116],"levels":[117],"assessed,":[119],"including":[120],"varying":[121],"size":[123],"hidden":[125],"layers,":[126],"bottleneck":[131],"or":[132],"softmax":[133],"outputs":[134],"as":[135],"input":[136],"network,":[140],"use<br/>of":[143],"definitions.":[147],"Phone":[148],"classification":[149,170],"experiments":[150],"performed":[152],"on":[153],"TIMIT.":[154],"results":[156],"show":[157],"that":[158],"using":[159],"BPC-dependent":[161],"provides":[163],"small":[164],"but":[165],"significant":[166],"improvements":[167],"accuracy":[171],"relative":[172],"global":[176,191],"DNN.":[177],"concludes":[180],"visualisations":[182],"structures":[185],"learned":[186],"local":[189],"discussion":[194],"their<br/>interpretations.":[196]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}