{"id":"https://openalex.org/W2394630935","doi":"https://doi.org/10.21437/interspeech.2007-244","title":"A flexible spectral modification method based on temporal decomposition and Gaussian mixture model","display_name":"A flexible spectral modification method based on temporal decomposition and Gaussian mixture model","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W2394630935","doi":"https://doi.org/10.21437/interspeech.2007-244","mag":"2394630935"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-244","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5091142923","display_name":"Binh P. Nguyen","orcid":"https://orcid.org/0000-0001-6203-6664"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Binh Phu Nguyen","raw_affiliation_strings":["School of Information Science,  Japan Advanced Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"School of Information Science,  Japan Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":["School of Information Science,  Japan Advanced Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"School of Information Science,  Japan Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091142923"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.3165,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6392663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"538","last_page":"541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.994700014591217,"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":0.994700014591217,"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":0.9919999837875366,"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":0.9054999947547913,"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/mixture-model","display_name":"Mixture model","score":0.7687371969223022},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6637313365936279},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.6145880818367004},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.5483180284500122},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5480684041976929},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5324476957321167},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5254004597663879},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4678925573825836},{"id":"https://openalex.org/keywords/spectral-shape-analysis","display_name":"Spectral shape analysis","score":0.46453553438186646},{"id":"https://openalex.org/keywords/spectral-line","display_name":"Spectral line","score":0.41898268461227417},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.41441160440444946},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3789318799972534},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3621164858341217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3605908751487732},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24523910880088806},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09055101871490479},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08421191573143005}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7687371969223022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6637313365936279},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.6145880818367004},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.5483180284500122},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5480684041976929},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5324476957321167},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5254004597663879},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4678925573825836},{"id":"https://openalex.org/C152822103","wikidata":"https://www.wikidata.org/wiki/Q7575207","display_name":"Spectral shape analysis","level":3,"score":0.46453553438186646},{"id":"https://openalex.org/C4839761","wikidata":"https://www.wikidata.org/wiki/Q212111","display_name":"Spectral line","level":2,"score":0.41898268461227417},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.41441160440444946},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3789318799972534},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3621164858341217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3605908751487732},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24523910880088806},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09055101871490479},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08421191573143005},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2007-244","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1578916557","https://openalex.org/W4243908963","https://openalex.org/W2140014531","https://openalex.org/W2008537336","https://openalex.org/W2021369389","https://openalex.org/W2158216108","https://openalex.org/W2928432034","https://openalex.org/W2083716025","https://openalex.org/W2402055149","https://openalex.org/W2092844234"],"abstract_inverted_index":{"Manipulating":[0],"spectral":[1,25,32,75,123,136,181,206],"structure":[2],"often":[3],"leads":[4,99],"to":[5,14,35,72,90,100,133,173],"degradation":[6],"of":[7,17,39,79,103,110,118,138,162,180,196],"speech":[8,54,63,82,105,112,184],"quality,":[9],"which":[10,61,176],"is":[11,70,113,200],"mainly":[12],"due":[13],"insufficient":[15],"smoothness":[16,109],"the":[18,37,74,81,104,108,116,135,160,194],"modified":[19,40,111],"spectra":[20,83,167,203],"between":[21],"frames,":[22],"and":[23,67,94,107,142,169,186,205],"ineffective":[24],"modification.":[26,207],"This":[27,97],"paper":[28],"presents":[29],"a":[30,53,144],"new":[31,145],"modification":[33,102],"method":[34,165,199],"improve":[36,122],"quality":[38],"speech.":[41],"If":[42],"frames":[43],"are":[44],"processed":[45],"independently,":[46],"discontinuous":[47],"features":[48],"may":[49],"be":[50],"generated.":[51],"Therefore,":[52],"analysis":[55],"technique":[56],"called":[57],"temporal":[58],"decomposition":[59],"(TD),":[60],"decomposes":[62],"into":[64],"event":[65,68,92,95,119,140],"targets":[66,93],"functions,":[69],"used":[71],"model":[73,129,134],"evolution":[76],"effectively.":[77],"Instead":[78],"modifying":[80,148],"frame":[84],"by":[85,115],"frame,":[86],"we":[87,125],"only":[88],"need":[89],"modify":[91],"functions.":[96,120],"feature":[98],"easy":[101],"spectra,":[106],"ensured":[114],"shape":[117],"To":[121],"modification,":[124,182],"explore":[126],"Gaussian":[127],"mixture":[128],"parameters":[130,150],"(spectral-GMM":[131],"parameters)":[132],"envelope":[137],"each":[139],"target,":[141],"develop":[143],"algorithm":[146],"for":[147,202],"spectral-GMM":[149],"in":[151,166],"accordance":[152],"with":[153],"formant":[154],"scaling":[155],"factors.":[156],"We":[157],"first":[158],"evaluate":[159],"effectiveness":[161,195],"our":[163,197],"proposed":[164,198],"modeling,":[168],"then":[170],"apply":[171],"it":[172],"two":[174],"areas":[175],"require":[177],"different":[178],"amounts":[179],"emotional":[183],"synthesis":[185],"voice":[187],"gender":[188],"conversion.":[189],"Experimental":[190],"results":[191],"show":[192],"that":[193],"verified":[201],"modeling":[204]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}