{"id":"https://openalex.org/W132712915","doi":"https://doi.org/10.21437/interspeech.2004-353","title":"DWT-based classification of acoustic-phonetic classes and phonetic units","display_name":"DWT-based classification of acoustic-phonetic classes and phonetic units","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W132712915","doi":"https://doi.org/10.21437/interspeech.2004-353","mag":"132712915"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-353","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-353","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/A5071861893","display_name":"Gernot Kubin","orcid":"https://orcid.org/0000-0002-8420-6051"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gernot Kubin","raw_affiliation_strings":["Institute of Electrical and Electronics Engineers"],"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Electronics Engineers","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047079852","display_name":"Van Tuan Pham","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Van Tuan Pham","raw_affiliation_strings":["Institute of Electrical and Electronics Engineers"],"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Electronics Engineers","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071861893"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6398,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83953742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"985","last_page":"988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.996999979019165,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7656289339065552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7001779675483704},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5567775964736938},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5546987056732178},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5336502194404602},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5215549468994141},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49024254083633423},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4841214120388031},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.4392302930355072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36558517813682556},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35274094343185425},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14339140057563782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656289339065552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7001779675483704},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5567775964736938},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5546987056732178},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5336502194404602},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5215549468994141},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49024254083633423},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4841214120388031},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.4392302930355072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36558517813682556},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35274094343185425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14339140057563782},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-353","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-353","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1561480741","https://openalex.org/W1660921708","https://openalex.org/W1907720640","https://openalex.org/W1959596450","https://openalex.org/W1985836220","https://openalex.org/W2019661654","https://openalex.org/W2154138336","https://openalex.org/W2162759570"],"related_works":["https://openalex.org/W193702574","https://openalex.org/W1842536210","https://openalex.org/W1967664370","https://openalex.org/W2155010696","https://openalex.org/W1979693044","https://openalex.org/W2154415461","https://openalex.org/W1999835922","https://openalex.org/W2063862874","https://openalex.org/W1541372708","https://openalex.org/W1923241916"],"abstract_inverted_index":{"Abstract":[0],"In":[1,226],"this":[2,268],"paper,":[3],"we":[4],"describe":[5],"a":[6,18,50,221,261],"new":[7],"algorithm":[8,96,108],"based":[9,238],"on":[10,31,66,239],"the":[11,40,58,74,90,93,100,106,160,181,190,248],"discrete":[12],"wavelet":[13,229,255],"transform":[14],"(DWT)":[15],"which":[16],"uses":[17],"multi-threshold":[19],"decision":[20],"model":[21,41,60],"(MTD":[22],"model)":[23],"to":[24,61,88,112,158,203,244,263,273],"detect":[25],"acoustic":[26],"and":[27,78,103,109,132],"phonetic":[28,63,156,249,282],"classes":[29,173],"(based":[30,65],"10ms":[32,69],"speech":[33,120,129,141,152,166,172,191,234,246],"signal":[34,192],"segments).":[35,70],"The":[36,71,95,119,168,252],"best":[37],"thresholds":[38],"of":[39,68,73,92,139,170,184,189,224,254,281],"are":[42,76],"found":[43],"by":[44,81,143],"using":[45,220],"experimental":[46],"pattern":[47],"classification.":[48],"Then":[49],"unit":[51],"level":[52,250],"interpolation":[53],"technique":[54],"is":[55,97],"combined":[56],"with":[57,99,105,257],"MTD":[59],"classify":[62,245],"units":[64,283],"sequences":[67],"results":[72],"classifiers":[75],"compared":[77,104],"jointly":[79],"adjusted":[80],"an":[82,124],"interactive":[83],"scheme":[84],"(IS)":[85],"in":[86,127,177,233],"order":[87],"improve":[89,137],"performance":[91,138],"algorithm.":[94],"tested":[98],"TIMIT":[101],"database":[102],"SUB-CRA-based":[107],"other":[110],"algorithms":[111,131,237],"demonstrate":[113],"its":[114],"effectiveness.":[115],"1":[116],"{(":[117],")}Introduction":[118],"classification":[121,157,280],"problem":[122],"plays":[123],"important":[125],"role":[126],"many":[128,178],"processing":[130],"applications.":[133,235],"Its":[134],"solution":[135],"can":[136,270],"concatenative":[140],"synthesis":[142],"selecting":[144],"proper":[145],"smoothing":[146],"strategies":[147],"at":[148,247],"concatenation":[149],"points.":[150],"Some":[151,236],"coding":[153],"systems":[154],"use":[155],"determine":[159],"optimal":[161],"bit":[162],"allocation":[163],"for":[164],"each":[165],"segment.":[167],"discrimination":[169],"different":[171],"has":[174],"been":[175,242],"studied":[176],"articles":[179],"since":[180],"1980\u2019s.":[182],"Most":[183],"them":[185],"exploit":[186],"statistical":[187,258],"features":[188],"[1]\u2013[2]":[193],"such":[194,278],"as":[195,279],"relative":[196],"energy":[197],"level,":[198],"zero":[199],"crossing":[200],"rate,":[201],"etc.,":[202],"decide":[204],"about":[205],"voiced,":[206],"unvoiced,":[207],"silence":[208],"or":[209],"mixed":[210],"excitation.":[211],"However,":[212],"these":[213],"approaches":[214],"only":[215],"achieve":[216],"good":[217],"accuracy":[218],"if":[219],"large":[222],"number":[223],"parameters.":[225],"recent":[227],"years,":[228],"analysis":[230],"attracted":[231],"researchers":[232],"DWT":[240],"have":[241],"developed":[243],"[4]-[7].":[251],"combination":[253,269],"parameters":[256,259],"opens":[260],"way":[262],"increase":[264],"classifier":[265],"performance.":[266],"Especially,":[267],"be":[271],"exploited":[272],"solve":[274],"more":[275],"difficult":[276],"tasks":[277],"[3],[8].":[284]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}