{"id":"https://openalex.org/W1488156205","doi":"https://doi.org/10.21437/interspeech.2005-110","title":"On variable-scale piecewise stationary spectral analysis of speech signals for ASR","display_name":"On variable-scale piecewise stationary spectral analysis of speech signals for ASR","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W1488156205","doi":"https://doi.org/10.21437/interspeech.2005-110","mag":"1488156205"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-110","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/83279","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062805147","display_name":"Vivek Tyagi","orcid":"https://orcid.org/0000-0002-3067-0801"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vivek Tyagi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108525230","display_name":"C. Wellekens","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Wellekens","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bourlard","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062805147"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9728,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73728429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"209","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9894000291824341,"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/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9765999913215637,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.6431469917297363},{"id":"https://openalex.org/keywords/spectral-analysis","display_name":"Spectral analysis","score":0.5879417061805725},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5753200650215149},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5655379891395569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5624947547912598},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4962001442909241},{"id":"https://openalex.org/keywords/scale-analysis","display_name":"Scale analysis (mathematics)","score":0.44315770268440247},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2655176520347595},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1589253544807434},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.06687670946121216}],"concepts":[{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.6431469917297363},{"id":"https://openalex.org/C2983668108","wikidata":"https://www.wikidata.org/wiki/Q280453","display_name":"Spectral analysis","level":3,"score":0.5879417061805725},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5753200650215149},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5655379891395569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5624947547912598},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4962001442909241},{"id":"https://openalex.org/C2775879016","wikidata":"https://www.wikidata.org/wiki/Q2845204","display_name":"Scale analysis (mathematics)","level":2,"score":0.44315770268440247},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2655176520347595},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1589253544807434},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.06687670946121216},{"id":"https://openalex.org/C32891209","wikidata":"https://www.wikidata.org/wiki/Q483666","display_name":"Spectroscopy","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2005-110","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:83279","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83279","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:83279","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83279","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W49883889","https://openalex.org/W68437168","https://openalex.org/W87496662","https://openalex.org/W1560013842","https://openalex.org/W1966264494","https://openalex.org/W2090861223","https://openalex.org/W2107964963","https://openalex.org/W2112446559","https://openalex.org/W2128780426","https://openalex.org/W2142183264","https://openalex.org/W2156447271","https://openalex.org/W2158358098","https://openalex.org/W2171700247","https://openalex.org/W4242662141"],"related_works":["https://openalex.org/W2385263368","https://openalex.org/W2347422947","https://openalex.org/W2061292372","https://openalex.org/W2353392568","https://openalex.org/W2377341410","https://openalex.org/W1454600515","https://openalex.org/W328874995","https://openalex.org/W25079857","https://openalex.org/W2005126053","https://openalex.org/W2172084624"],"abstract_inverted_index":{"It":[0],"is":[1,71,153,167],"often":[2],"acknowledged":[3],"that":[4,13,115,141,200,220],"speech":[5,87,107,117,135],"signals":[6],"contain":[7],"short-term":[8],"and":[9,18,42,78],"long-term":[10],"temporal":[11],"properties":[12],"are":[14,53,178],"difficult":[15],"to":[16,239],"capture":[17],"model":[19],"by":[20,122,146],"using":[21,99],"the":[22,86,90,95,112,116,131,139,147,156,193,201,206,215,221],"usual":[23,113],"fixed":[24,68,253],"scale":[25,69,187,254],"(typically":[26],"20ms)":[27],"short":[28],"time":[29,188],"spectral":[30,176,189,226,255],"analysis":[31,63,70,102,172,196,227],"used":[32,169],"in":[33,85,185,235],"hidden":[34],"Markov":[35],"models":[36],"(HMMs),":[37],"based":[38,137,228,241,251],"on":[39,111,138,214,242,252],"piecewise":[40,133,224],"stationarity":[41],"state":[43],"conditional":[44],"independence":[45],"assumptions":[46],"of":[47,80,98,163],"acoustic":[48],"vectors.":[49],"For":[50],"example,":[51],"vowels":[52],"typically":[54,61],"quasi-stationary":[55,134,165],"over":[56],"40-80ms":[57],"segments,":[58,136],"while":[59],"plosives":[60],"require":[62],"below":[64],"20ms":[65],"segments.":[66],"Thus,":[67],"clearly":[72],"sub-optimal":[73],"for":[74],"``optimal''":[75],"time-frequency":[76],"resolution":[77,209],"modeling":[79],"different":[81],"stationary":[82,225],"phones":[83],"found":[84],"signal.":[88],"In":[89],"present":[91],"paper,":[92],"we":[93,129],"investigate":[94],"potential":[96],"advantages":[97],"variable":[100,186],"size":[101,198],"windows":[103],"towards":[104],"improving":[105],"state-of-the-art":[106],"recognition":[108,212,233],"systems.":[109],"Based":[110],"assumption":[114],"signal":[118,202],"can":[119],"be":[120],"modeled":[121],"a":[123,142],"varying":[124],"autoregressive":[125],"(AR)":[126],"Gaussian":[127],"process,":[128],"estimate":[130],"largest":[132,194],"likelihood":[140,152],"segment":[143],"was":[144],"generated":[145],"same":[148],"AR":[149],"process.":[150],"This":[151],"estimated":[154],"from":[155,174],"Linear":[157],"Prediction":[158],"(LP)":[159],"residual":[160],"error.":[161],"Each":[162],"these":[164],"segments":[166],"then":[168],"as":[170,247,249],"an":[171,181],"window":[173,197],"which":[175],"features":[177,229,240],"extracted.":[179],"Such":[180],"approach":[182],"thus":[183,205],"results":[184],"analysis,":[190],"adaptively":[191],"estimating":[192],"possible":[195],"such":[199],"remains":[203],"quasi-stationary,":[204],"best":[207],"temporal/frequency":[208],"tradeoff.":[210],"Speech":[211],"experiments":[213],"OGI":[216],"Numbers95":[217],"database":[218],"show":[219],"proposed":[222],"multi-scale":[223],"indeed":[230],"yield":[231],"improved":[232],"accuracy":[234],"clean":[236],"conditions,":[237],"compared":[238],"minimum":[243],"cross":[244],"entropy":[245],"spectrum":[246],"well":[248],"those":[250],"analysis.":[256]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}