{"id":"https://openalex.org/W174019601","doi":"https://doi.org/10.21437/interspeech.2006-628","title":"An investigation of manifold learning for speech analysis","display_name":"An investigation of manifold learning for speech analysis","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W174019601","doi":"https://doi.org/10.21437/interspeech.2006-628","mag":"174019601"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-628","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5054033450","display_name":"Andrew Errity","orcid":"https://orcid.org/0000-0002-4041-1408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Errity","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057356529","display_name":"John McKenna","orcid":null},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"John McKenna","raw_affiliation_strings":["Dublin City University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dublin City University#TAB#","institution_ids":["https://openalex.org/I42934936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 1667","last_page":"Thu2BuP.8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9929999709129333,"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":0.991599977016449,"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/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.6820335388183594},{"id":"https://openalex.org/keywords/nonlinear-dimensionality-reduction","display_name":"Nonlinear dimensionality reduction","score":0.6752772927284241},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6619647145271301},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6182912588119507},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5624297261238098},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.5562807321548462},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.48090171813964844},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4717443883419037},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4700055718421936},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42641955614089966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4013710916042328},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3305583596229553}],"concepts":[{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6820335388183594},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.6752772927284241},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6619647145271301},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6182912588119507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5624297261238098},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.5562807321548462},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.48090171813964844},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4717443883419037},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4700055718421936},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42641955614089966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4013710916042328},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3305583596229553},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2006-628","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1966949944","https://openalex.org/W2001141328","https://openalex.org/W2053186076","https://openalex.org/W2057781541","https://openalex.org/W2135346934","https://openalex.org/W2153754278","https://openalex.org/W2153934661","https://openalex.org/W2155970279","https://openalex.org/W2156718197","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2375574759","https://openalex.org/W2383239174","https://openalex.org/W3088634662","https://openalex.org/W117517268","https://openalex.org/W3162910294","https://openalex.org/W2539700568","https://openalex.org/W1995622179","https://openalex.org/W4391160746","https://openalex.org/W2931531042","https://openalex.org/W2166963679"],"abstract_inverted_index":{"Abstract":[0],"Due":[1],"to":[2,53,59,77,88,149,219,228,236,240,250,267,272,311,376,417,480,489,512,538,565,580,624],"the":[3,36,65,126,152,178,187,198,221,224,242,253,259,275,314,328,331,378,389,457,502,642,656,683,691],"physiological":[4],"constraints":[5,151],"of":[6,14,20,27,35,48,72,107,159,166,171,223,258,301,319,322,330,344,349,380,388,420,504,515,569,621,641,680,682],"articulatory":[7],"motion":[8],"thespeech":[9],"apparatus":[10,155],"has":[11,156,203,557],"limited":[12,169,375],"degrees":[13,158],"freedom.":[15,160],"As":[16],"a":[17,23,31,46,80,168,175,194,339,385,451,471,483,513,542,586,678],"result,":[18],"therange":[19],"speech":[21,54,68,112,115,124,127,153,188,207,225,237,276,302,421,429,436,447,540,553,583,618,629],"sounds":[22,172,448],"human":[24],"is":[25,84,129,217,248,263,631,649],"capable":[26,106,165],"producing":[28],"may":[29,469,530],"lieon":[30],"low":[32,81,212,316,341,452,463,543,587,626],"dimensional":[33,38,62,67,82,135,213,317,342,391,453,459,588,627],"submanifold":[34,465],"high":[37,66,134,199,345,390,458],"spaceof":[39],"all":[40],"possible":[41],"sounds.":[42],"In":[43,123,181,653],"this":[44,182,468,563,597],"study":[45],"number":[47,321,514,568,679],"manifold":[49,74,96,117,195,214,454,485,517,574,602],"learningalgorithms":[50],"are":[51,105,163,295,374,671],"applied":[52,235,416,511],"data":[55,354,381,433,584,630],"in":[56,79,111,197,238,456,523,534,552,585,688],"an":[57],"effort":[58],"extract":[60,338,548],"usefullow":[61],"structure":[63,318,379],"from":[64],"sig-nal.":[69],"The":[70,666],"ability":[71],"these":[73,350,622],"learning":[75,97,486,528,575,603,658,685],"algorithms":[76,98,493,529,576,623,659],"separatevowels":[78],"space":[83,589],"evaluated":[85,632],"and":[86,104,255,291,299,304,359,408,435,438,593,614,633,662,669],"compared":[87],"aclassical":[89],"linear":[90,143,285,368,386,397,476,505,605],"dimensionality":[91,222,324,351,398],"reduction":[92,325,363,399],"method.":[93],"Results":[94],"indicatethat":[95],"outperform":[99],"classical":[100],"methods":[101,400,413,477,508],"inlow":[102],"dimensions":[103],"discovering":[108,377],"useful":[109,522,533],"manifoldstructure":[110],"data.Index":[113],"Terms:":[114],"analysis,":[116],"learning,":[118],"dimensionalityreduction,":[119],"classi\ufb01cation.":[120],"1.":[121],"Introduction":[122],"processing,":[125],"signal":[128,231],"often":[130,264],"modeled":[131],"by":[132,244,327],"rela-tively":[133],"features":[136,549],"such":[137,211,307,466],"as":[138,306,367,467,490,651],"discrete":[139],"Fourier":[140],"transform(DFT)":[141],"or":[142,192,369,547],"prediction":[144,286],"(LP)":[145],"coef\ufb01cients.":[146],"However":[147,555],"due":[148],"phys-iological":[150],"production":[154,303],"relativelyfew":[157],"Thus,":[161],"humans":[162],"only":[164],"gen-erating":[167],"range":[170,419],"which":[173,500],"occupy":[174],"con\ufb01ned":[176],"regionof":[177],"acoustic":[179,460],"space.":[180,201,393,461],"case,":[183],"we":[184,599],"can":[185,577],"imagine":[186],"dataas":[189],"lying":[190,382],"on":[191,297,383,450],"near":[193],"embedded":[196],"dimensionalacoustic":[200],"It":[202],"been":[204,234,334,415,495,558],"proposed":[205,335,496],"that":[206,247,336,444,475,640],"intrinsically":[208],"lieson":[209],"some":[210,268],"[1,":[215],"2].It":[216],"desirable":[218],"reduce":[220,241],"sig-nal":[226],"prior":[227],"processing.":[229],"Traditionally,":[230],"processing":[232,422,526],"techniqueshave":[233],"order":[239],"dimensional-ity":[243],"extracting":[245],"information":[246,262],"judged":[249],"capture":[251],"informationabout":[252],"energy":[254],"spectral":[256],"characteristics":[257],"signal.":[260],"Theextracted":[261],"transformed":[265],"according":[266],"per-ceptually":[269],"motivated":[270,293],"scheme":[271],"better":[273],"model":[274],"auditorypath;":[277],"for":[278,427,536,545,550],"example,":[279,537],"Mel-frequency":[280],"cepstral":[281],"coef\ufb01cients":[282],"(MFCC)and":[283],"perceptual":[284],"(PLP)":[287],"parameters.":[288],"These":[289,412,507],"acousti-cally":[290],"perceptually":[292],"representations":[294],"based":[296],"ourknowledge":[298],"assumptions":[300],"perception,and":[305],"do":[308],"not":[309],"attempt":[310],"automatically":[312],"discover":[313,625],"underly-ing":[315],"speech.A":[320],"automatic":[323],"algorithms,driven":[326],"statistics":[329],"data,":[332],"have":[333,414,441,470,494,509,519,572],"aimto":[337],"meaningful":[340],"representation":[343],"di-mensional":[346],"data.":[347,619],"Applications":[348],"reductionalgorithms":[352],"include":[353],"compression,":[355],"visualisation,":[356],"noise":[357],"reduc-tion,":[358],"feature":[360,425,611],"extraction.":[361],"Dimensionality":[362],"methodscan":[364],"be":[365,532,578],"categorised":[366],"nonlinear":[370,473,491],"methods.":[371,506],"Linear":[372],"meth-ods":[373],"ornear":[384],"subspace":[387],"input":[392],"Themost":[394],"widely":[395],"used":[396,579],"includethe":[401],"classic":[402],"principal":[403],"component":[404],"analysis":[405],"(PCA)":[406],"[3]":[407],"multidi-mensional":[409],"scaling":[410],"(MDS).":[411],"awide":[418],"problems":[423],"including,":[424],"trans-formation":[426],"improved":[428],"recognition":[430],"performance,":[431],"speakeradaptation,":[432],"compaction,":[434],"analysis.Jansen":[437],"Niyogi":[439],"[2]":[440],"recently":[442],"shown":[443],"certain":[445],"classesof":[446],"lie":[449],"nonlinearlyembedded":[455],"A":[462,567],"dimen-sional":[464],"highly":[472],"struc-ture":[474],"would":[478],"fail":[479],"discover.":[481],"Recently,":[482],"numberof":[484],"(also":[487],"referred":[488],"dimensionalityreduction)":[492],"[4,":[497,608],"5,":[498,690],"6]":[499],"over-come":[501],"limitations":[503,681],"beensuccessfully":[510],"benchmark":[516],"problemsand":[518],"also":[520,531,637],"proved":[521],"several":[524,601],"image":[525],"applica-tions.Manifold":[527],"speechanalysis;":[535],"project":[539],"into":[541],"dimensionalspace":[544],"visualisation":[546],"use":[551],"recog-nition.":[554],"there":[556],"relatively":[559],"little":[560],"research":[561],"conductedin":[562],"area":[564],"date.":[566],"exploratory":[570],"studies":[571],"shownthat":[573],"successfully":[581],"vi-sualise":[582],"[7,":[590],"6,":[591],"8]":[592],"forphone":[594],"classi\ufb01cation":[595],"[9].In":[596],"paper,":[598],"apply":[600],"algorithms\u2014locally":[604],"embedding":[606],"(LLE)":[607],"10],":[609],"isometric":[610],"mapping(Isomap)":[612],"[5],":[613],"Laplacian":[615,663],"eigenmaps":[616],"[6]\u2014to":[617],"Theability":[620],"structurewithin":[628],"compared.":[634],"Their":[635],"performanceis":[636],"contrasted":[638],"with":[639],"classical,":[643],"linear,":[644],"PCA":[645],"method[3].":[646],"This":[647],"paper":[648],"structured":[650],"follows.":[652],"Section":[654,675,689],"2,":[655],"man-ifold":[657],"LLE,":[660],"Isomap":[661],"eigenmapsare":[664],"described.":[665],"corpus,":[667],"experiments":[668],"results":[670],"detailed":[672],"inSection":[673],"3.":[674],"4":[676],"discusses":[677],"mani-fold":[684],"algorithms.":[686],"Finally,":[687],"conclusions":[692],"arepresented.":[693]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}