{"id":"https://openalex.org/W41853125","doi":"https://doi.org/10.21437/interspeech.2007-326","title":"A structured speech model parameterized by recursive dynamics and neural networks","display_name":"A structured speech model parameterized by recursive dynamics and neural networks","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W41853125","doi":"https://doi.org/10.21437/interspeech.2007-326","mag":"41853125"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-326","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},"type":"article","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/A5017213156","display_name":"Roberto Togneri","orcid":"https://orcid.org/0000-0002-3778-4633"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Roberto Togneri","raw_affiliation_strings":["University of Western  Australia"],"affiliations":[{"raw_affiliation_string":"University of Western  Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067818713","display_name":"Li Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Li Deng","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017213156"],"corresponding_institution_ids":["https://openalex.org/I177877127"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00380446,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"894","last_page":"897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9980000257492065,"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":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.7403991222381592},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6784033179283142},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.6402715444564819},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5610436201095581},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5451504588127136},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5381942391395569},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.531019389629364},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.5183066725730896},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4926009774208069},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47591572999954224},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.460854709148407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.442704975605011},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27450141310691833},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15574228763580322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7403991222381592},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6784033179283142},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.6402715444564819},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5610436201095581},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5451504588127136},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5381942391395569},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.531019389629364},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.5183066725730896},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4926009774208069},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47591572999954224},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.460854709148407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.442704975605011},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27450141310691833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15574228763580322},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2007-326","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/a153d844-4f6f-4c93-a212-f110c06ab8fa","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/a153d844-4f6f-4c93-a212-f110c06ab8fa","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Togneri, R & Deng, L 2007, A Structured Speech Model Parameterized by Recursive Dynamics and Neural Networks. in Proceedings of Interspeech 2007. Antwerp, Belgium edn, vol. CD Rom, International Speech Recognition Association, Universitat Bonn, Bonn, Germany, pp. 894-897.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.589.7405","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.589.7405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/um/redmond/groups/srg/papers/2007-deng-interspeech.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.624.8850","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.624.8850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.uwa.edu.au/~roberto/research/papers/IS2007_2.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1855533549","https://openalex.org/W1984002593","https://openalex.org/W2027915610","https://openalex.org/W2045785976","https://openalex.org/W2056731339","https://openalex.org/W2092684968","https://openalex.org/W2118587967","https://openalex.org/W2118825896","https://openalex.org/W2122994642","https://openalex.org/W2123487311","https://openalex.org/W2139648927","https://openalex.org/W2148622792","https://openalex.org/W2148812765","https://openalex.org/W2151323943"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2053269318","https://openalex.org/W2546021431","https://openalex.org/W2581127593","https://openalex.org/W2049352309","https://openalex.org/W4249887698"],"abstract_inverted_index":{"We":[0,28,86,111],"present":[1,88],"in":[2,73,128],"this":[3,97],"paper":[4],"an":[5],"overview":[6],"of":[7,17,33,65,68,75,96,99,125,143,154],"the":[8,34,43,53,57,69,94,116,122,126,131,144],"Hidden":[9],"Dynamic":[10],"Model":[11],"(HDM)":[12],"paradigm,":[13],"exemplifying":[14],"parametric":[15],"construction":[16],"structure-based":[18],"speech":[19,45,61],"models":[20],"that":[21,36],"can":[22],"be":[23],"used":[24],"for":[25,101,105],"recog-nition":[26],"purposes.":[27],"explore":[29],"a":[30,78,83],"general":[31],"class":[32],"HDM":[35,70,127,145],"uses":[37,48],"recursive,":[38],"autoregression":[39],"functions":[40],"to":[41,51,140],"represent":[42,52],"hid-den":[44],"dynamics,":[46],"and":[47,59,82,104,121],"neural":[49,156],"networks":[50],"functional":[54],"relationship":[55],"between":[56],"hidden":[58,149],"observed":[60],"vectors.":[62],"This":[63],"type":[64,98],"state-space":[66],"formulation":[67],"is":[71],"re-viewed":[72],"terms":[74],"model":[76],"construction,":[77],"parameter":[79,123],"estimation":[80],"technique,":[81],"decoding":[84],"method.":[85],"also":[87],"some":[89],"typ-ical":[90],"experimental":[91],"results":[92],"on":[93,115],"use":[95],"HDMs":[100],"phonetic":[102],"recognition":[103,163],"automatic":[106],"vocal":[107],"tract":[108],"resonance":[109],"tracking.":[110],"further":[112],"provide":[113],"analyses":[114],"computational":[117],"complexity":[118],"(for":[119],"decoding)":[120],"size":[124],"comparison":[129],"with":[130],"HMM.":[132],"Finally,":[133],"we":[134],"discuss":[135],"several":[136],"key":[137],"issues":[138],"related":[139],"future":[141],"exploration":[142],"paradigm.":[146],"Index":[147],"Terms:":[148],"dynamic":[150],"model,":[151],"recursive":[152],"form":[153],"dynam-ics,":[155],"network,":[157],"nonlinear":[158],"mapping,":[159],"formant":[160],"tracking,":[161],"pho-netic":[162]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}