{"id":"https://openalex.org/W2052282967","doi":"https://doi.org/10.1109/icapr.2015.7050668","title":"Optimal residual frame based source modeling for HMM-based speech synthesis","display_name":"Optimal residual frame based source modeling for HMM-based speech synthesis","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2052282967","doi":"https://doi.org/10.1109/icapr.2015.7050668","mag":"2052282967"},"language":"en","primary_location":{"id":"doi:10.1109/icapr.2015.7050668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icapr.2015.7050668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Eighth International Conference on Advances in Pattern Recognition (ICAPR)","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/A5006858710","display_name":"N. P. Narendra","orcid":null},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"N. P. Narendra","raw_affiliation_strings":["School of Information Technology, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India","School of Information Technology, Indian Institute of Technology Kharagpur - 721302, West Bengal, India"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"School of Information Technology, Indian Institute of Technology Kharagpur - 721302, West Bengal, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111514705","display_name":"Kanishka Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K. Sreenivasa Rao","raw_affiliation_strings":["School of Information Technology, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India","School of Information Technology, Indian Institute of Technology Kharagpur - 721302, West Bengal, India"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"School of Information Technology, Indian Institute of Technology Kharagpur - 721302, West Bengal, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006858710"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":1.2943,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.85667912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976999759674072,"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":0.9872999787330627,"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/residual","display_name":"Residual","score":0.8687798976898193},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7801651954650879},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.7289940714836121},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6503898501396179},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.6347458362579346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6115466952323914},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5983848571777344},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.49349653720855713},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46152442693710327},{"id":"https://openalex.org/keywords/residual-frame","display_name":"Residual frame","score":0.43816953897476196},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4273906648159027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42651355266571045},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36849623918533325},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22189673781394958},{"id":"https://openalex.org/keywords/reference-frame","display_name":"Reference frame","score":0.20733347535133362},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07200878858566284}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.8687798976898193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7801651954650879},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.7289940714836121},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6503898501396179},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.6347458362579346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6115466952323914},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5983848571777344},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.49349653720855713},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46152442693710327},{"id":"https://openalex.org/C204641915","wikidata":"https://www.wikidata.org/wiki/Q7315509","display_name":"Residual frame","level":4,"score":0.43816953897476196},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4273906648159027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42651355266571045},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36849623918533325},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22189673781394958},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.20733347535133362},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07200878858566284},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icapr.2015.7050668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icapr.2015.7050668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Eighth International Conference on Advances in Pattern Recognition (ICAPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W200094172","https://openalex.org/W1594031697","https://openalex.org/W2042691334","https://openalex.org/W2049686551","https://openalex.org/W2060855080","https://openalex.org/W2097634052","https://openalex.org/W2108532241","https://openalex.org/W2112844139","https://openalex.org/W2145575463","https://openalex.org/W2154920538","https://openalex.org/W2286166914","https://openalex.org/W2296704011","https://openalex.org/W2406579473","https://openalex.org/W6696156092","https://openalex.org/W6697285287"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2153098279","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,65],"method":[4],"for":[5],"modeling":[6],"the":[7,12,36,41,51,79,94,100,118,125],"excitation":[8,120],"signal":[9,39,97],"to":[10,27,34,63,99,130],"improve":[11,124],"quality":[13,126],"of":[14,30,40,46,68,81,127],"HMM-based":[15],"speech":[16,52],"synthesis":[17],"system":[18],"(HTS).":[19],"Single":[20],"optimal":[21,91],"residual":[22,38,44,73,92,96],"frame":[23],"which":[24],"closely":[25],"relates":[26],"all":[28,47],"frames":[29,45,74],"phone":[31,101],"is":[32,102],"chosen":[33],"represent":[35],"entire":[37,95],"phone.":[42],"Optimal":[43],"phones":[48],"present":[49],"in":[50],"corpus":[53],"are":[54,75],"efficiently":[55],"grouped":[56],"based":[57,84,104],"on":[58,85,105],"positional":[59],"and":[60,107],"contextual":[61],"features":[62],"form":[64],"decision":[66,82],"tree":[67,83],"clusters.":[69],"During":[70],"synthesis,":[71],"suitable":[72],"picked":[76],"up":[77],"from":[78,111],"leaf":[80],"certain":[86],"selection":[87],"criteria.":[88],"From":[89],"each":[90],"frame,":[93],"corresponding":[98],"generated":[103],"pitch":[106],"intensity":[108],"contours":[109],"obtained":[110],"HMMs.":[112],"Subjective":[113],"evaluation":[114],"results":[115],"show":[116],"that":[117],"proposed":[119],"model":[121],"can":[122],"significantly":[123],"HTS":[128],"compared":[129],"traditional":[131],"pulse":[132],"excitation.":[133]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}