{"id":"https://openalex.org/W306135325","doi":"https://doi.org/10.21437/interspeech.2004-381","title":"Use of neural network mapping and extended kalman filter to recover vocal tract resonances from the MFCC parameters of speech","display_name":"Use of neural network mapping and extended kalman filter to recover vocal tract resonances from the MFCC parameters of speech","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W306135325","doi":"https://doi.org/10.21437/interspeech.2004-381","mag":"306135325"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-381","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5100671326","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-7140-0701"},"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":true,"raw_author_name":"Li Deng","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","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":false,"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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100671326"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.03192752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1097","last_page":"1100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9976000189781189,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.8886687755584717},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.8854110240936279},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6955579519271851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6328227519989014},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.6203020215034485},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.6144281029701233},{"id":"https://openalex.org/keywords/consonant","display_name":"Consonant","score":0.6065936088562012},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5010056495666504},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4330219328403473},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.32470595836639404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3235153555870056},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.18919408321380615},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.12535050511360168},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07314950227737427}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8886687755584717},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8854110240936279},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6955579519271851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6328227519989014},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.6203020215034485},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.6144281029701233},{"id":"https://openalex.org/C2778203577","wikidata":"https://www.wikidata.org/wiki/Q38035","display_name":"Consonant","level":3,"score":0.6065936088562012},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5010056495666504},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4330219328403473},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.32470595836639404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3235153555870056},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.18919408321380615},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.12535050511360168},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07314950227737427}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-381","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1269046860","https://openalex.org/W1704572586","https://openalex.org/W1999885698","https://openalex.org/W2092684968","https://openalex.org/W2107093743","https://openalex.org/W2124776405","https://openalex.org/W2125956490","https://openalex.org/W2161748486","https://openalex.org/W2171371585","https://openalex.org/W2988208854"],"related_works":["https://openalex.org/W2046073792","https://openalex.org/W4254341835","https://openalex.org/W1748856376","https://openalex.org/W2086580720","https://openalex.org/W1909584822","https://openalex.org/W2001425423","https://openalex.org/W2061217898","https://openalex.org/W2894697037","https://openalex.org/W2131046383","https://openalex.org/W2050311283"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,9],"state-space":[6],"formulation":[7],"of":[8,14,29,32,60,75,111],"neuralnetwork-based":[10],"hidden":[11],"dynamic":[12],"model":[13],"speech":[15,76],"whose":[16],"parameters":[17],"are":[18],"trained":[19,57],"using":[20],"an":[21,33],"approximate":[22],"EM":[23,54],"algorithm.":[24,55],"The":[25,56,106],"training":[26],"makes":[27],"use":[28],"the":[30,38,43,52,61,65,82,88,98,112,127,138],"results":[31,107],"off-the-shelf":[34],"formant":[35],"tracker":[36],"(during":[37],"vowel":[39],"segments)":[40],"to":[41,90,96,136],"simplify":[42],"complex":[44],"sufficient":[45],"statistics":[46],"that":[47],"would":[48],"be":[49],"required":[50],"in":[51],"exact":[53],"model,":[58],"consisting":[59],"state":[62],"equation":[63,84],"for":[64,85],"target-directed":[66],"vocal":[67],"tract":[68],"resonance":[69],"(VTR)":[70],"dynamics":[71],"on":[72,102],"all":[73],"classes":[74],"sounds":[77],"(including":[78],"consonant":[79,124],"closure)":[80],"and":[81,122],"observation":[83],"mapping":[86],"from":[87],"VTR":[89,100,139],"acoustic":[91,128],"measurement,":[92],"is":[93],"then":[94],"used":[95],"recover":[97],"unobserved":[99],"based":[101],"Extended":[103],"Kalman":[104],"Filter.":[105],"demonstrate":[108],"accurate":[109],"estimation":[110],"VTRs,":[113],"especially":[114],"those":[115],"during":[116,123],"rapic":[117],"consonant-vowel":[118],"or":[119,133],"vowel-consonant":[120],"transitions":[121],"closure":[125],"when":[126],"measurement":[129],"alone":[130],"provides":[131],"weak":[132],"no":[134],"information":[135],"infer":[137],"values.":[140]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}