{"id":"https://openalex.org/W824914942","doi":"https://doi.org/10.21437/interspeech.2012-30","title":"A study of mutual information for GMM-based spectral conversion","display_name":"A study of mutual information for GMM-based spectral conversion","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W824914942","doi":"https://doi.org/10.21437/interspeech.2012-30","mag":"824914942"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-30","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-30","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":"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/A5111385896","display_name":"Hsin-Te Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Hsin-Te Hwang","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica,Research Center for Information Technology Innovation"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Research Center for Information Technology Innovation","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["[Academia Sinica, Institute of Information Science]"],"affiliations":[{"raw_affiliation_string":"[Academia Sinica, Institute of Information Science]","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071941088","display_name":"Yih\u2010Ru Wang","orcid":"https://orcid.org/0000-0002-4483-1418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yih-Ru Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015529786","display_name":"Sin\u2010Horng Chen","orcid":"https://orcid.org/0000-0002-9820-2318"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sin-Horng Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111385896"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":3.4252,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.92192028,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"78","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9832000136375427,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.6870073080062866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6628307700157166},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6275066137313843},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.6233441829681396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5650045871734619},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5161812901496887},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46284955739974976},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.439340204000473},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4137468636035919},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3829079866409302},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3526666760444641},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07336476445198059}],"concepts":[{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6870073080062866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6628307700157166},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6275066137313843},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6233441829681396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5650045871734619},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5161812901496887},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46284955739974976},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.439340204000473},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4137468636035919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3829079866409302},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3526666760444641},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07336476445198059},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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":1,"locations":[{"id":"doi:10.21437/interspeech.2012-30","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-30","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/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W33533989","https://openalex.org/W2049686551","https://openalex.org/W2099111195","https://openalex.org/W2116257577","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2156142001","https://openalex.org/W2408732577"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W2366328218"],"abstract_inverted_index":{"The":[0],"Gaussian":[1],"mixture":[2],"model":[3],"(GMM)-based":[4],"method":[5,104,110],"has":[6],"dominated":[7],"the":[8,18,35,40,43,62,67,95,101,108],"field":[9],"of":[10,97,113],"voice":[11],"conversion":[12],"(VC)":[13],"for":[14,85],"last":[15],"decade.":[16],"However,":[17],"converted":[19,28,48,63,98],"spectra":[20],"are":[21],"excessively":[22],"smoothed":[23],"and":[24,47,80],"thus":[25],"produce":[26],"muffled":[27],"sound.":[29,69],"In":[30],"this":[31,58,71],"study,":[32],"we":[33,73],"improve":[34],"speech":[36,99],"quality":[37,96],"by":[38,100,107],"enhancing":[39,57],"dependency":[41,59],"between":[42],"source":[44],"(natural":[45],"sound)":[46],"feature":[49],"vectors":[50],"(converted":[51],"sound).":[52],"It":[53],"is":[54],"believed":[55],"that":[56,94,106],"can":[60],"make":[61],"sound":[64],"closer":[65],"to":[66],"natural":[68],"To":[70],"end,":[72],"propose":[74],"an":[75],"integrated":[76],"maximum":[77],"a":[78],"posteriori":[79],"mutual":[81],"information":[82],"(MAPMI)":[83],"criterion":[84],"parameter":[86],"generation":[87],"on":[88],"spectral":[89],"conversion.":[90],"Experimental":[91],"results":[92],"demonstrate":[93],"proposed":[102],"MAPMI":[103],"outperforms":[105],"conventional":[109],"in":[111],"terms":[112],"formal":[114],"listening":[115],"test.":[116]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
