{"id":"https://openalex.org/W2079678531","doi":"https://doi.org/10.1587/transinf.e95.d.2351","title":"Outlier Detection and Removal for HMM-Based Speech Synthesis with an Insufficient Speech Database","display_name":"Outlier Detection and Removal for HMM-Based Speech Synthesis with an Insufficient Speech Database","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2079678531","doi":"https://doi.org/10.1587/transinf.e95.d.2351","mag":"2079678531"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.e95.d.2351","pdf_url":null,"source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1587/transinf.e95.d.2351","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054169859","display_name":"Doo Hwa Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"funder","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Doo Hwa HONG","raw_affiliation_strings":["School of Electrical Engineering and the Institute of New Media and Communications, Seoul National University"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and the Institute of New Media and Communications, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110947099","display_name":"June Sig Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"funder","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"June Sig SUNG","raw_affiliation_strings":["School of Electrical Engineering and the Institute of New Media and Communications, Seoul National University"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and the Institute of New Media and Communications, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048720977","display_name":"Kyung Hwan Oh","orcid":"https://orcid.org/0000-0002-4232-2003"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"funder","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyung Hwan OH","raw_affiliation_strings":["School of Electrical Engineering and the Institute of New Media and Communications, Seoul National University"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and the Institute of New Media and Communications, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"funder","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo KIM","raw_affiliation_strings":["School of Electrical Engineering and the Institute of New Media and Communications, Seoul National University"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and the Institute of New Media and Communications, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.361,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":1,"citation_normalized_percentile":{"value":0.544683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":64,"max":72},"biblio":{"volume":"E95.D","issue":"9","first_page":"2351","last_page":"2354"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998,"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":0.9998,"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":0.9978,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9673,"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"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85759187},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.76025486},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.74515885},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.57872903},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5540136},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5425362},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.47217673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44446445},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40440455}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.e95.d.2351","pdf_url":null,"source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.e95.d.2351","pdf_url":null,"source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"score":0.81,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":12,"referenced_works":["https://openalex.org/W102093577","https://openalex.org/W153997859","https://openalex.org/W1540596182","https://openalex.org/W1600722501","https://openalex.org/W1926768285","https://openalex.org/W1980262437","https://openalex.org/W2106792148","https://openalex.org/W2154920538","https://openalex.org/W2158069733","https://openalex.org/W2228674556","https://openalex.org/W2407087858","https://openalex.org/W4239873714"],"related_works":["https://openalex.org/W3145575561","https://openalex.org/W2995886640","https://openalex.org/W2904846757","https://openalex.org/W2688184458","https://openalex.org/W2364370872","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W2053269318","https://openalex.org/W2038801705","https://openalex.org/W2025614924"],"abstract_inverted_index":{"Decision":[0],"tree-based":[1],"clustering":[2],"and":[3,67],"parameter":[4],"estimation":[5],"are":[6,22],"essential":[7],"steps":[8,21],"in":[9,51],"the":[10,27,35,38,55,78,83,88],"training":[11,90],"part":[12],"of":[13,34,37,54],"an":[14,63],"HMM-based":[15,71],"speech":[16,72,91],"synthesis":[17],"system.":[18],"These":[19],"two":[20],"usually":[23,49],"performed":[24],"based":[25],"on":[26],"maximum":[28],"likelihood":[29],"(ML)":[30],"criterion.":[31],"However,":[32],"one":[33],"drawbacks":[36],"ML":[39],"criterion":[40],"is":[41,44,93],"that":[42,77],"it":[43],"sensitive":[45],"to":[46,65],"outliers":[47,69],"which":[48],"result":[50],"quality":[52],"degradation":[53],"synthesized":[56],"speech.":[57],"In":[58],"this":[59],"letter,":[60],"we":[61],"propose":[62],"approach":[64,80],"detect":[66],"remove":[68],"for":[70],"synthesis.":[73],"Experimental":[74],"results":[75],"show":[76],"proposed":[79],"can":[81],"improve":[82],"synthetic":[84],"speech,":[85],"particularly":[86],"when":[87],"available":[89],"database":[92],"insufficient.":[94]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2079678531","counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-04-22T05:04:19.139899","created_date":"2016-06-24"}