{"id":"https://openalex.org/W2397149834","doi":"https://doi.org/10.21437/interspeech.2015-208","title":"Analysis of a low-dimensional bottleneck neural network representation of speech for modelling speech dynamics","display_name":"Analysis of a low-dimensional bottleneck neural network representation of speech for modelling speech dynamics","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2397149834","doi":"https://doi.org/10.21437/interspeech.2015-208","mag":"2397149834"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-208","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109403866","display_name":"Linxue Bai","orcid":"https://orcid.org/0009-0008-0538-2307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linxue Bai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079477816","display_name":"Martin Russell","orcid":"https://orcid.org/0000-0002-8324-4961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Russell","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102937478","display_name":"Philip Weber","orcid":"https://orcid.org/0000-0002-3121-9625"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philip Weber","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4691,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91449396,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"583","last_page":"587"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9958000183105469,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.870524525642395},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8450160026550293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7471249103546143},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6244000196456909},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6160474419593811},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5912962555885315},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5663633346557617},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4960380494594574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4426586329936981},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4333392381668091},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.43283769488334656},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.42605969309806824},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41727009415626526},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41164663434028625}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.870524525642395},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8450160026550293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7471249103546143},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6244000196456909},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6160474419593811},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5912962555885315},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5663633346557617},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4960380494594574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4426586329936981},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4333392381668091},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.43283769488334656},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.42605969309806824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41727009415626526},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41164663434028625},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2015-208","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/7b1b56e2-0af0-4785-ab74-fa5fb6a98da3","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/7b1b56e2-0af0-4785-ab74-fa5fb6a98da3","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":"Bai , L , Jancovic , P , Russell , M & Weber , P 2015 , ' Analysis of a low-dimensional bottleneck neural network representation of speech for modelling speech dynamics ' , Paper presented at Interspeech 2015 , Dresden , Germany , 6/09/15 - 10/09/15 pp. 583-587 . https://doi.org/10.21437/Interspeech.2015-208","raw_type":"conferenceObject"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/d53079af-0845-47e2-a8c3-1e9da3b541dc","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/d53079af-0845-47e2-a8c3-1e9da3b541dc","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":"Bai, L, Jancovic, P, Russell, M & Weber, P 2015, Analysis of a Low-Dimensional Bottleneck Neural Network Representation of Speech for Modelling Speech Dynamics. in Proceedings of Interspeech. ISCA, pp. 583-587, Interspeech 2015, Dresden, Germany, 6/09/15.","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:publications/7b1b56e2-0af0-4785-ab74-fa5fb6a98da3","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/portal/en/publications/analysis-of-a-lowdimensional-bottleneck-neural-network-representation-of-speech-for-modelling-speech-dynamics(7b1b56e2-0af0-4785-ab74-fa5fb6a98da3).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":"Bai , L , Jancovic , P , Russell , M & Weber , P 2015 , ' Analysis of a low-dimensional bottleneck neural network representation of speech for modelling speech dynamics ' , Paper presented at Interspeech 2015 , Dresden , Germany , 6/09/15 - 10/09/15 pp. 583-587 . https://doi.org/10.21437/Interspeech.2015-208","raw_type":"conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W79929747","https://openalex.org/W88081813","https://openalex.org/W227955348","https://openalex.org/W1500026161","https://openalex.org/W1606347560","https://openalex.org/W1998362482","https://openalex.org/W2012897754","https://openalex.org/W2026862302","https://openalex.org/W2075925017","https://openalex.org/W2077804127","https://openalex.org/W2083393647","https://openalex.org/W2086754356","https://openalex.org/W2090764203","https://openalex.org/W2092684968","https://openalex.org/W2109915598","https://openalex.org/W2118825896","https://openalex.org/W2133129980","https://openalex.org/W2161964681","https://openalex.org/W2165712214","https://openalex.org/W2546373232","https://openalex.org/W2619993508","https://openalex.org/W3082371797","https://openalex.org/W3127686677","https://openalex.org/W3209383001","https://openalex.org/W3216401400","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W1524112065","https://openalex.org/W2573596907","https://openalex.org/W3102785448"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"analysis":[4],"of":[5,9,29,37,42,50,57,93,114,117,134],"a":[6,27,84,132,155],"low-dimensional":[7],"representation":[8,157],"speech":[10,13,130],"for":[11,158],"modelling":[12],"dynamics,":[14],"extracted":[15],"using":[16,65,100],"bottleneck":[17,59,79,109,143],"neural":[18,24],"networks.":[19],"The":[20,78],"input":[21,54,66],"to":[22],"the":[23,35,43,48,53,58,96,108,112,122,142,147],"network":[25],"is":[26],"set":[28],"spectral":[30],"feature":[31],"vectors.":[32],"We":[33,104,139],"explore":[34],"effect":[36],"various":[38],"designs":[39],"and":[40,60,64,136,152],"training":[41],"network,":[44],"such":[45],"as":[46,71,131],"varying":[47],"size":[49,56],"context":[51],"in":[52,83],"layer,":[55],"other":[61],"hidden":[62,124],"layers,":[63],"reconstruction":[67],"or":[68],"phone":[69],"posteriors":[70],"targets.":[72],"Experiments":[73],"are":[74,81],"performed":[75],"on":[76,95],"TIMIT.":[77],"features":[80,110,144],"employed":[82],"conventional":[85],"HMM-based":[86],"phoneme":[87],"recognition":[88,91],"system,":[89],"with":[90],"accuracy":[92],"70.6%":[94],"core":[97],"test":[98],"achieved":[99],"only":[101],"9-dimensional":[102],"features.":[103],"also":[105],"analyse":[106],"how":[107],"fit":[111],"assumptions":[113],"dynamic":[115],"models":[116],"speech.":[118],"Specifically,":[119],"we":[120],"employ":[121],"continuous-state":[123],"Markov":[125],"model":[126],"(CS-HMM),":[127],"which":[128],"considers":[129],"sequence":[133],"dwell":[135],"transition":[137],"regions.":[138],"demonstrate":[140],"that":[141],"preserve":[145],"well":[146],"trajectory":[148],"continuity":[149],"over":[150],"time":[151],"can":[153],"provide":[154],"suitable":[156],"CS-HMM.":[159]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}