{"id":"https://openalex.org/W233059834","doi":"https://doi.org/10.21437/interspeech.2008-170","title":"Minimum generation error training with direct log spectral distortion on LSPs for HMM-based speech synthesis","display_name":"Minimum generation error training with direct log spectral distortion on LSPs for HMM-based speech synthesis","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W233059834","doi":"https://doi.org/10.21437/interspeech.2008-170","mag":"233059834"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-170","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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/3399","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 Inst. of Technol.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Inst. of Technol.#TAB#","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 Inst. of Technol.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Inst. of Technol.#TAB#","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":3.5265,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.92316298,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"577","last_page":"580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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":0.9811000227928162,"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/euclidean-distance","display_name":"Euclidean distance","score":0.715962290763855},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6743052005767822},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6672715544700623},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6671936511993408},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5652380585670471},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.48619335889816284},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43908417224884033},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42292100191116333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3724554777145386},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3710881173610687},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13718047738075256},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07016444206237793}],"concepts":[{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.715962290763855},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6743052005767822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6672715544700623},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6671936511993408},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5652380585670471},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48619335889816284},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43908417224884033},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42292100191116333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3724554777145386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3710881173610687},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13718047738075256},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07016444206237793},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2008-170","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01154:0001435266","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/3399","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":"INTERSPEECH 2008 9th Annual Conference of the International Speech Communication Association","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01154:0001435266","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/3399","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":"INTERSPEECH 2008 9th Annual Conference of the International Speech Communication Association","raw_type":"conference paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1563645159","https://openalex.org/W1600722501","https://openalex.org/W1935012542","https://openalex.org/W1993523973","https://openalex.org/W2010581677","https://openalex.org/W2049686551","https://openalex.org/W2108674328","https://openalex.org/W2111194146","https://openalex.org/W2165856656","https://openalex.org/W2166823384","https://openalex.org/W3036802551"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"A":[0],"minimum":[1],"generation":[2],"error":[3,44],"(MGE)":[4],"criterion":[5,29],"had":[6],"been":[7],"proposedto":[8],"solve":[9],"the":[10,27,38,46,57,64,70,74,81,84,90,95],"issues":[11],"related":[12],"to":[13,41,62],"maximum":[14],"likelihood":[15],"(ML)based":[16],"HMM":[17],"training":[18],"in":[19],"HMM-based":[20],"speech":[21,88],"synthesis.":[22],"In":[23],"thispaper,":[24],"we":[25,55],"improve":[26],"MGE":[28,97],"by":[30,76],"imposing":[31],"a":[32],"log":[33],"spectraldistortion":[34],"(LSD)":[35],"instead":[36],"of":[37,66,86],"Euclidean":[39],"distance":[40],"define":[42],"thegeneration":[43],"between":[45],"original":[47,96],"and":[48],"generated":[49],"line":[50],"spectralpair":[51],"(LSP)":[52],"coefficients.":[53],"Moreover,":[54],"investigate":[56],"effect":[58],"ofdifferent":[59],"sampling":[60,77],"strategies":[61],"calculate":[63],"integration":[65],"theLSD":[67],"function.":[68],"From":[69],"experimental":[71],"results,":[72],"using":[73],"LSDscalculated":[75],"at":[78],"LSPs":[79],"achieved":[80],"best":[82],"performance,and":[83],"quality":[85],"synthesized":[87],"after":[89],"MGE-LSD":[91],"trainingwas":[92],"improved":[93],"over":[94],"training.":[98]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}