{"id":"https://openalex.org/W2398947221","doi":"https://doi.org/10.1109/icassp.2016.7472748","title":"Modulation spectrum compensation for HMM-based speech synthesis using line spectral pairs","display_name":"Modulation spectrum compensation for HMM-based speech synthesis using line spectral pairs","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2398947221","doi":"https://doi.org/10.1109/icassp.2016.7472748","mag":"2398947221"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101613242","display_name":"Xiaohui Sun","orcid":"https://orcid.org/0000-0002-5079-8685"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Hui Sun","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101816319","display_name":"Yu Hu","orcid":"https://orcid.org/0000-0002-6302-3539"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Hu","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059767940"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.857,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.832257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"20","issue":null,"first_page":"5595","last_page":"5599"},"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":0.9991000294685364,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7779378890991211},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6871725916862488},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5965362191200256},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5709234476089478},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5592383146286011},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5173293948173523},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5107216835021973},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4783446490764618},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.46707087755203247},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4170878529548645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3725428879261017},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3338688015937805},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2172272503376007},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.16035163402557373},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14496269822120667},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13047829270362854}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7779378890991211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6871725916862488},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5965362191200256},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5709234476089478},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5592383146286011},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5173293948173523},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5107216835021973},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4783446490764618},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.46707087755203247},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4170878529548645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3725428879261017},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3338688015937805},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2172272503376007},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.16035163402557373},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14496269822120667},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13047829270362854},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W157817982","https://openalex.org/W200094172","https://openalex.org/W1546472312","https://openalex.org/W1568585903","https://openalex.org/W1600722501","https://openalex.org/W1789888671","https://openalex.org/W1907246751","https://openalex.org/W1987992317","https://openalex.org/W2000513720","https://openalex.org/W2030637102","https://openalex.org/W2042691334","https://openalex.org/W2049036695","https://openalex.org/W2049686551","https://openalex.org/W2054139811","https://openalex.org/W2108674328","https://openalex.org/W2154920538","https://openalex.org/W2292984643","https://openalex.org/W2376932199","https://openalex.org/W2403847736","https://openalex.org/W6603838645","https://openalex.org/W6632724131","https://openalex.org/W6676044216","https://openalex.org/W6713560387","https://openalex.org/W7056901721"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W1914543332","https://openalex.org/W2373675101","https://openalex.org/W2946856121","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2108985546"],"abstract_inverted_index":{"In":[0],"previous":[1],"work,":[2],"a":[3,178],"method":[4,31,56],"to":[5,64,180],"compensate":[6],"the":[7,10,34,53,104,130,188,197],"divergence":[8],"between":[9],"distributions":[11],"of":[12,37,106,126,132,190],"natural":[13],"and":[14,71,93,152,193],"generated":[15],"modulation":[16],"spectra":[17,84],"(MS)":[18],"has":[19],"been":[20],"proposed":[21],"for":[22,57,121,135,146],"hidden":[23],"Markov":[24],"model":[25],"(HMM)":[26],"based":[27],"speech":[28,97,108,162],"synthesis.":[29],"This":[30,49,168],"can":[32,173],"alleviate":[33],"over-smoothing":[35],"effect":[36],"parameter":[38],"generation":[39],"when":[40,114],"Mel-cepstral":[41],"coefficients":[42],"(MCC)":[43],"are":[44,69,116,143],"used":[45,117],"as":[46,118,177],"spectral":[47,59,119,133,191],"features.":[48],"paper":[50],"further":[51],"investigates":[52],"MS":[54,66,76,112,136,147,171],"compensation":[55,113,148,172],"line":[58],"pairs":[60],"(LSP).":[61],"Four":[62],"approaches":[63,74],"extract":[65],"from":[67,87,91,96,141,155,161],"LSPs":[68,115,142,151],"implemented":[70,176],"compared.":[72],"These":[73],"calculate":[75],"vectors":[77],"using":[78,158],"original":[79,150],"LSP":[80],"sequences,":[81],"log":[82],"power":[83],"(LPS)":[85],"derived":[86,90,95,140,154,160],"LSPs,":[88,92],"MCCs":[89,94,139,159],"waveforms,":[98],"respectively.":[99],"Experimental":[100],"results":[101],"show":[102],"that":[103,170],"naturalness":[105],"synthetic":[107,181],"gets":[109],"improved":[110],"after":[111],"features":[120,134,192],"HMM":[122],"modeling.":[123],"The":[124],"degree":[125],"improvement":[127],"depends":[128],"on":[129,187],"type":[131,189],"calculation":[137],"significantly.":[138],"more":[144],"suitable":[145],"than":[149],"LPS":[153],"LSPs.":[156],"Besides,":[157],"waveforms":[163,182],"also":[164,174],"achieves":[165],"satisfactory":[166],"performance.":[167],"means":[169],"be":[175],"post-filter":[179],"which":[183],"does":[184],"not":[185],"rely":[186],"vocoders":[194],"adopted":[195],"in":[196],"synthesis":[198],"system.":[199]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}