{"id":"https://openalex.org/W1585831907","doi":"https://doi.org/10.1109/icassp.1987.1169742","title":"Modeling spectral speech transitions using temporal decomposition techniques","display_name":"Modeling spectral speech transitions using temporal decomposition techniques","publication_year":2005,"publication_date":"2005-03-24","ids":{"openalex":"https://openalex.org/W1585831907","doi":"https://doi.org/10.1109/icassp.1987.1169742","mag":"1585831907"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1987.1169742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1987.1169742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5063624133","display_name":"G. Ahlbom","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G. Ahlbom","raw_affiliation_strings":["ENST Department, SYC, CNRS UA-820, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ENST Department, SYC, CNRS UA-820, Paris, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111908492","display_name":"Fr\u00e9d\u00e9ric Bimbot","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"F. Bimbot","raw_affiliation_strings":["ENST Department, SYC, CNRS UA-820, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ENST Department, SYC, CNRS UA-820, Paris, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054175637","display_name":"G\u00e9rard Chollet","orcid":"https://orcid.org/0000-0003-4245-146X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G. Chollet","raw_affiliation_strings":["ENST Department, SYC, CNRS UA-820, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ENST Department, SYC, CNRS UA-820, Paris, France","institution_ids":["https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1294671590"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"13","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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":0.9955999851226807,"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":0.9901000261306763,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9872000217437744,"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/coarticulation","display_name":"Coarticulation","score":0.7766709327697754},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6482419967651367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.624786376953125},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5684223771095276},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5186251997947693},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.515677809715271},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5135610103607178},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.4985642433166504},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.49339500069618225},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4557187259197235},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4477616548538208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3194708824157715},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.11774685978889465}],"concepts":[{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.7766709327697754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6482419967651367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.624786376953125},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5684223771095276},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5186251997947693},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.515677809715271},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5135610103607178},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.4985642433166504},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.49339500069618225},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4557187259197235},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4477616548538208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3194708824157715},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.11774685978889465},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1987.1169742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1987.1169742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2018708513","https://openalex.org/W2155098255","https://openalex.org/W2158358098","https://openalex.org/W2162293237","https://openalex.org/W2566756653"],"related_works":["https://openalex.org/W1890221585","https://openalex.org/W2020989338","https://openalex.org/W2147126679","https://openalex.org/W1823617068","https://openalex.org/W4300049944","https://openalex.org/W2040310682","https://openalex.org/W2115984063","https://openalex.org/W2115039802","https://openalex.org/W2091321647","https://openalex.org/W2160220319"],"abstract_inverted_index":{"ATAL":[0],"[1]":[1],"introduced":[2],"a":[3,80],"technique":[4,27],"for":[5,150],"decomposing":[6],"speech":[7,93,155],"into":[8],"phone-length":[9],"temporal":[10],"events":[11],"in":[12,40,147,153],"terms":[13],"of":[14,25,44,83,92,124],"overlapping":[15],"and":[16,106,134],"interacting":[17],"articulatory":[18,84],"gestures.":[19],"This":[20],"paper":[21],"reports":[22],"on":[23],"simplifications":[24],"this":[26,100],"with":[28,74],"applications":[29],"to":[30,79,112],"acoustic-phonetic":[31],"synthesis.":[32,156],"Spectral":[33],"evolution":[34],"is":[35,137],"represented":[36],"by":[37],"time-indexed":[38],"trajectories":[39],"the":[41,58,121],"p-dimensional":[42],"space":[43],"Log-Area":[45],"Ratios":[46],"<tex":[47],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[48,55],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">{y_{i}=":[49],"\\Ln":[50],"((1+k_{i})/(1-k_{i}))}</tex>":[51],"where":[52],"k":[53],"<inf":[54],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i</inf>":[56],"are":[57,110,131],"reflection":[59],"coefficients":[60],"obtained":[61],"from":[62],"short-time":[63],"stationary":[64],"LPC":[65],"analysis.":[66],"The":[67],"vocal":[68],"tract":[69],"configuration":[70],"(spectral":[71],"vector)":[72],"associated":[73],"each":[75],"interpolation":[76],"function":[77],"belongs":[78],"finite":[81],"set":[82,91],"targets":[85],"(vector":[86],"quantization":[87],"code":[88],"book).":[89],"A":[90],"segments":[94],"(\"polysons\")":[95],"has":[96],"been":[97],"encoded":[98],"using":[99,116],"technique.":[101],"It":[102,136],"includes":[103],"diphones,":[104],"demi-syllables,":[105],"other":[107],"units":[108],"that":[109,139],"difficult":[111],"segment.":[113],"Temporal":[114],"decomposition":[115],"target":[117],"spectra":[118],"can":[119],"break":[120],"complex":[122],"encoding":[123],"these":[125,140],"segments.":[126],"In":[127],"particular,":[128],"coarticulation":[129],"effects":[130],"analyticaiy":[132],"explained":[133],"modeled.":[135],"demonstrated":[138],"new":[141],"tools":[142],"provide":[143],"an":[144],"adequate":[145],"environment":[146],"our":[148],"search":[149],"better":[151],"rules":[152],"acoustic":[154]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}