{"id":"https://openalex.org/W2164534744","doi":"https://doi.org/10.1109/icassp.2009.4960508","title":"Minimum generation error training by using original spectrum as reference for log spectral distortion measure","display_name":"Minimum generation error training by using original spectrum as reference for log spectral distortion measure","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2164534744","doi":"https://doi.org/10.1109/icassp.2009.4960508","mag":"2164534744"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nitech.repo.nii.ac.jp/records/3405","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039492028","display_name":"Yi-Jian Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi-Jian Wu","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7178,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.91459314,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"5","issue":null,"first_page":"4013","last_page":"4016"},"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":0.9988999962806702,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9915000200271606,"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/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.722878098487854},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5872972011566162},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5155148506164551},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5024158954620361},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.47213464975357056},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.4640369415283203},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4443172812461853},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.43647894263267517},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.42410892248153687},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4231882095336914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.39105409383773804},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.3031458258628845},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.24233868718147278},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.22587734460830688}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.722878098487854},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5872972011566162},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5155148506164551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5024158954620361},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.47213464975357056},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.4640369415283203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4443172812461853},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.43647894263267517},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.42410892248153687},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4231882095336914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39105409383773804},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.3031458258628845},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.24233868718147278},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.22587734460830688},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01154:0001435272","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/3405","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2009. IEEE International Conference on Acoustics, Speech and Signal Processing, 2009.","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01154:0001435272","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/3405","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2009. IEEE International Conference on Acoustics, Speech and Signal Processing, 2009.","raw_type":"conference paper"},"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W233059834","https://openalex.org/W234770729","https://openalex.org/W1600722501","https://openalex.org/W1935012542","https://openalex.org/W2009674825","https://openalex.org/W2010581677","https://openalex.org/W2049686551","https://openalex.org/W2111194146","https://openalex.org/W2133035145","https://openalex.org/W2144139079","https://openalex.org/W2165856656","https://openalex.org/W2166823384","https://openalex.org/W3036802551","https://openalex.org/W6609136615","https://openalex.org/W6676358011","https://openalex.org/W6679574054","https://openalex.org/W6684311649","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2370517014","https://openalex.org/W2039242888","https://openalex.org/W2515867587","https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W2176409448","https://openalex.org/W1838021708","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W2056136368"],"abstract_inverted_index":{"This":[0],"paper":[1],"improves":[2],"a":[3,99],"minimum":[4],"generation":[5],"error":[6],"(MGE)":[7],"based":[8],"HMM":[9],"training":[10,117],"technique":[11],"for":[12,31,43],"HMM-based":[13],"speech":[14,53,64],"synthesis":[15],"by":[16,55,92],"directly":[17],"using":[18,118],"the":[19,49,58,68,71,77,81,95,106,112,115,119,126],"original":[20,40,87],"spectrum":[21,30,50,61,73,89,121,124],"instead":[22],"of":[23,39,70],"line":[24],"spectral":[25,33,79],"pairs":[26],"(LSPs)":[27],"as":[28,122],"reference":[29,41,123],"log":[32],"distortion":[34],"(LSD)":[35],"measure.":[36],"Two":[37],"types":[38],"spectra":[42],"LSD":[44,82],"calculation":[45],"are":[46,74],"investigated,":[47],"including":[48],"extracted":[51],"from":[52,63],"waveform":[54],"STRAIGHT,":[56],"and":[57,86,98],"short-time":[59],"FFT":[60,72,88,120],"calculated":[62,91],"waveforms.":[65],"Since":[66],"only":[67],"harmonics":[69],"coincident":[75],"with":[76],"underlying":[78],"envelope,":[80],"between":[83],"generated":[84],"LSPs":[85],"is":[90,102],"sampling":[93,107],"at":[94],"harmonic":[96],"frequencies,":[97],"weighting":[100],"function":[101],"designed":[103],"to":[104],"simulate":[105],"strategy":[108],"on":[109],"LSPs.":[110],"From":[111],"experimental":[113],"results,":[114],"MGE-LSD":[116],"achieved":[125],"best":[127],"performance.":[128]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}