{"id":"https://openalex.org/W1994259430","doi":"https://doi.org/10.1109/iscslp.2012.6423477","title":"Exploring mutual information for GMM-based spectral conversion","display_name":"Exploring mutual information for GMM-based spectral conversion","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W1994259430","doi":"https://doi.org/10.1109/iscslp.2012.6423477","mag":"1994259430"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","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/A5101061014","display_name":"Hsin-Te Hwang","orcid":null},"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"]},{"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":["Department of Electrical and Computer Engineering, National Chiao-Tung University, Hsinchu, Taiwan","Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao-Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"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":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","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":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","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":[{"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":false,"raw_author_name":"Yih-Ru Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao-Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao-Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015529786","display_name":"Sin\u2010Horng Chen","orcid":"https://orcid.org/0000-0002-9820-2318"},"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":false,"raw_author_name":"Sin-Horng Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao-Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao-Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101061014"],"corresponding_institution_ids":["https://openalex.org/I148366613","https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":1.4691,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84758293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9954000115394592,"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":0.6945623159408569},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6874996423721313},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.6696241497993469},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.609172523021698},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5829232931137085},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5670499205589294},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5444515943527222},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5372341275215149},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5338807106018066},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5286436676979065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5240480899810791},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4625048041343689},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4603556990623474},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.45452865958213806},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.099327951669693},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08970049023628235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6945623159408569},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6874996423721313},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6696241497993469},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.609172523021698},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5829232931137085},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5670499205589294},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5444515943527222},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5372341275215149},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5338807106018066},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5286436676979065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5240480899810791},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4625048041343689},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4603556990623474},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.45452865958213806},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.099327951669693},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08970049023628235},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2012.6423477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W33533989","https://openalex.org/W824914942","https://openalex.org/W2049686551","https://openalex.org/W2099111195","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2156142001","https://openalex.org/W2158289097","https://openalex.org/W6601370681","https://openalex.org/W6623273663"],"related_works":["https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2033669961","https://openalex.org/W1972167985","https://openalex.org/W2971899271","https://openalex.org/W2350644419","https://openalex.org/W2014385108"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,42],"maximum":[6,34],"mutual":[7],"information":[8],"(MMI)":[9],"training":[10,59,121,129],"criterion":[11,37],"to":[12,23,40,72,89,95],"refine":[13],"the":[14,17,25,33,47,51,62,66,69,78,81,91,96,105,110,114,127],"parameters":[15,67],"of":[16,50,68,109],"joint":[18,48],"density":[19],"GMM":[20],"(JDGMM)":[21],"set":[22,71],"tackle":[24],"over-smoothing":[26],"issue":[27],"in":[28],"voice":[29],"conversion":[30],"(VC).":[31],"Conventionally,":[32],"likelihood":[35],"(ML)":[36],"is":[38,123],"used":[39],"train":[41],"JDGMM":[43,70],"set,":[44],"which":[45],"characterizes":[46],"property":[49],"source":[52,82],"and":[53,83,87,107],"target":[54,84],"feature":[55,85],"vectors.":[56],"The":[57,99],"MMI":[58,119],"criterion,":[60],"on":[61,76],"other":[63],"hand,":[64],"updates":[65],"increase":[73],"its":[74],"capability":[75],"modeling":[77],"dependency":[79],"between":[80],"vectors,":[86],"thus":[88],"make":[90],"converted":[92,111],"sounds":[93],"closer":[94],"natural":[97],"ones.":[98],"subjective":[100],"listening":[101],"test":[102],"demonstrates":[103],"that":[104,125],"quality":[106],"individuality":[108],"speech":[112],"by":[113,118,126],"proposed":[115],"ML":[116,128],"followed":[117],"(ML+MMI)":[120],"method":[122],"better":[124],"method.":[130]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
