{"id":"https://openalex.org/W2395889896","doi":"https://doi.org/10.21437/interspeech.2012-136","title":"Pitch-scaled analysis based residual reconstruction for speech analysis and synthesis","display_name":"Pitch-scaled analysis based residual reconstruction for speech analysis and synthesis","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2395889896","doi":"https://doi.org/10.21437/interspeech.2012-136","mag":"2395889896"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-136","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072749858","display_name":"Hideki Kawahara","orcid":"https://orcid.org/0000-0001-9360-5700"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hideki Kawahara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"374","last_page":"377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9980999827384949,"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/T10901","display_name":"Advanced Data Compression Techniques","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/speech-recognition","display_name":"Speech recognition","score":0.5996637344360352},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5702544450759888},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.540873646736145},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.43545883893966675},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.43325281143188477},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.42430973052978516},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.41372787952423096},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4131161868572235},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.34268879890441895},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34026893973350525},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24597367644309998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1892293393611908},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.17812198400497437},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09729158878326416}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5996637344360352},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5702544450759888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.540873646736145},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.43545883893966675},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.43325281143188477},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.42430973052978516},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.41372787952423096},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4131161868572235},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34268879890441895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34026893973350525},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24597367644309998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1892293393611908},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.17812198400497437},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09729158878326416},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2012-136","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W349984566","https://openalex.org/W795690926","https://openalex.org/W1571401318","https://openalex.org/W2042691334","https://openalex.org/W2049686551","https://openalex.org/W2108688353","https://openalex.org/W2129082420","https://openalex.org/W2132496293","https://openalex.org/W2152820192","https://openalex.org/W2155295839","https://openalex.org/W2158972663"],"related_works":["https://openalex.org/W1975632186","https://openalex.org/W3027745756","https://openalex.org/W3205213561","https://openalex.org/W2531880140","https://openalex.org/W2126145365","https://openalex.org/W2036609560","https://openalex.org/W346861917","https://openalex.org/W3024018414","https://openalex.org/W2560215812","https://openalex.org/W1542592062"],"abstract_inverted_index":{"The":[0],"typical":[1],"problem":[2],"in":[3,49,91,121],"LPC-like":[4],"vocoder":[5,132],"is":[6,10,27,47,54,85,100],"buzzing":[7],"sound":[8],"which":[9],"mainly":[11],"due":[12],"to":[13,24,28,56,79,102],"the":[14,30,58,88,92,104,122,151],"simple":[15],"pulse":[16],"train":[17],"or":[18],"noise":[19],"excitation":[20,119],"model.":[21],"One":[22],"way":[23],"improve":[25],"it":[26],"reconstruct":[29],"residual":[31,62],"obtained":[32],"from":[33],"inverse":[34],"filtering.":[35],"So":[36],"a":[37,135,143],"new":[38],"parametric":[39],"representation":[40],"of":[41,61,106,140],"speech":[42],"based":[43],"on":[44],"pitch-scaled":[45],"analysis":[46,53,77],"proposed":[48,123,131],"this":[50,130],"paper.":[51],"Pitch-scaled":[52],"used":[55,101],"extract":[57],"periodic":[59,70],"spectrum":[60,109],"with":[63,114],"half":[64],"pitch":[65],"period":[66],"length.":[67],"Then":[68],"these":[69],"spectrums":[71],"are":[72,116],"de-correlated":[73],"by":[74],"principal":[75],"component":[76],"(PCA)":[78],"reduce":[80],"their":[81],"dimension.":[82],"Aperiodic":[83],"measure":[84,112],"defined":[86],"as":[87,118],"harmonic-to-noise":[89],"ratio":[90],"frequency":[93,98],"domain":[94],"where":[95],"voicing":[96],"cut-off":[97],"(VCO)":[99],"control":[103],"smoothness":[105],"aperiodicity.":[107],"Periodic":[108],"and":[110,149],"aperiodic":[111],"together":[113],"F0":[115],"indicated":[117],"parameters":[120],"LPC":[124],"vocoder.":[125],"Experimental":[126],"results":[127],"show":[128],"that":[129],"can":[133],"get":[134],"mean":[136],"opinion":[137],"score":[138],"(MOS)":[139],"4.1":[141],"for":[142],"female":[144],"voice":[145],"before":[146],"dimensionality":[147],"reduction":[148],"keep":[150],"high-quality":[152],"property":[153],"after":[154],"parameter":[155],"compression.":[156]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}