{"id":"https://openalex.org/W2889445910","doi":"https://doi.org/10.21437/interspeech.2018-1376","title":"Phone Recognition Using a Non-Linear Manifold with Broad Phone Class Dependent DNNs","display_name":"Phone Recognition Using a Non-Linear Manifold with Broad Phone Class Dependent DNNs","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889445910","doi":"https://doi.org/10.21437/interspeech.2018-1376","mag":"2889445910"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1376","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1376","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.birmingham.ac.uk/en/publications/065430a2-66f1-49fd-b509-90d920ea11bd","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027476226","display_name":"Mengjie Qian","orcid":"https://orcid.org/0000-0003-2614-5411"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengjie Qian","raw_affiliation_strings":["Electronic, Electrical and Systems Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic, Electrical and Systems Engineering","institution_ids":[]}]},{"author_position":"middle","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":false,"raw_author_name":"Linxue Bai","raw_affiliation_strings":["Department of Electronic, Electrical & Systems Engineering, The University of Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic, Electrical & Systems Engineering, The University of Birmingham, 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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Jan\u010dovi\u010d","raw_affiliation_strings":["Electronic, Electrical and Systems Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic, Electrical and Systems Engineering","institution_ids":[]}]},{"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":["Department of Electronic, Electrical & Systems Engineering, The University of Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic, Electrical & Systems Engineering, The University of Birmingham, UK","institution_ids":["https://openalex.org/I79619799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3608,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.51109401,"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":"3753","last_page":"3757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T13289","display_name":"Infant Health and Development","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7305659055709839},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.584073543548584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5812786817550659},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4898395240306854},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.4856759309768677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28127312660217285},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11293527483940125},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07763552665710449}],"concepts":[{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7305659055709839},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.584073543548584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5812786817550659},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4898395240306854},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.4856759309768677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28127312660217285},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11293527483940125},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07763552665710449},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2018-1376","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1376","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/065430a2-66f1-49fd-b509-90d920ea11bd","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/065430a2-66f1-49fd-b509-90d920ea11bd","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/065430a2-66f1-49fd-b509-90d920ea11bd","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":"Qian, M, Bai, L, Jancovic, P & Russell, M 2018, Phone recognition using a non-linear manifold with broad phone class dependent DNNs. in Proceedings of Interspeech 2018. Interspeech, vol. 2018, ISCA, Hyderabad, India, pp. 3753-3757, Interspeech 2018, Hyderabad , India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-1376","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/065430a2-66f1-49fd-b509-90d920ea11bd","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/065430a2-66f1-49fd-b509-90d920ea11bd","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":"Qian, M, Bai, L, Jancovic, P & Russell, M 2018, Phone recognition using a non-linear manifold with broad phone class dependent DNNs. in Proceedings of Interspeech 2018. Interspeech, vol. 2018, ISCA, Hyderabad, India, pp. 3753-3757, Interspeech 2018, Hyderabad , India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-1376","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1512581325","https://openalex.org/W1524333225","https://openalex.org/W1567690964","https://openalex.org/W1980076831","https://openalex.org/W1980399492","https://openalex.org/W1998523266","https://openalex.org/W2032625358","https://openalex.org/W2077804127","https://openalex.org/W2078279533","https://openalex.org/W2102898380","https://openalex.org/W2125879978","https://openalex.org/W2132085065","https://openalex.org/W2238198527","https://openalex.org/W2402340204","https://openalex.org/W2405455920","https://openalex.org/W2747774782"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W2114089658","https://openalex.org/W2061937230"],"abstract_inverted_index":{"Although":[0],"it":[1],"is":[2,141],"generally":[3],"accepted":[4],"that":[5,144,157],"different":[6,12,20,76],"broad":[7,77],"phone":[8,111,150,178],"classes":[9,79],"(BPCs)":[10],"have":[11],"production":[13],"mechanisms":[14],"and":[15,34,80,172,177],"are":[16,73,90],"better":[17],"described":[18],"by":[19,41,57],"types":[21],"of":[22,60,87,137,170],"features,":[23],"most":[24,153],"automatic":[25],"speech":[26],"recognition":[27],"(ASR)":[28],"systems":[29],"use":[30],"the":[31,58,65,82,85,127,138,158],"same":[32],"features":[33],"decision":[35],"criteria":[36],"for":[37,101,110,174],"all":[38],"phones.":[39],"Motivated":[40],"this":[42,44,118,145],"observation,":[43],"paper":[45,116,140],"proposes":[46],"a":[47,54,61,114,132,167],"two-level":[48],"DNN":[49,169],"structure,":[50],"referred":[51],"to":[52,75,92,142,148,166],"as":[53],"BPC-DNN,":[55],"inspired":[56],"notion":[59],"topological":[62],"manifold.":[63],"In":[64,113],"first":[66],"level,":[67],"several":[68],"small":[69],"separate":[70],"BPC-dependent":[71],"DNNs":[72,89],"applied":[74],"phonetic":[78],"in":[81,162],"second":[83],"level":[84,103],"outputs":[86],"these":[88],"fused":[91],"obtain":[93],"senone-dependent":[94],"posterior":[95],"probabilities,":[96],"which":[97],"can":[98],"be":[99],"used":[100],"frame":[102,123,175],"classification":[104,124,176],"or":[105],"integrated":[106],"into":[107],"Viterbi":[108],"decoding":[109],"recognition.":[112,151],"previous":[115],"using":[117],"approach":[119],"we":[120],"reported":[121],"improved":[122],"accuracy":[125],"on":[126],"TIMIT":[128],"corpus":[129],"compared":[130],"with":[131],"conventional":[133,168],"DNN.":[134],"The":[135],"contribution":[136],"present":[139],"demonstrate":[143],"advantage":[146],"extends":[147],"full":[149],"Our":[152],"recent":[154],"results":[155],"show":[156],"BPC-DNN":[159],"achieves":[160],"reductions":[161],"error":[163],"rate":[164],"relative":[165],"16%":[171],"8%":[173],"recognition,":[179],"respectively.":[180]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}