{"id":"https://openalex.org/W2408267635","doi":"https://doi.org/10.21437/interspeech.2012-365","title":"Amplitude spectrum based excitation model for HMM-based speech synthesis","display_name":"Amplitude spectrum based excitation model for HMM-based speech synthesis","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2408267635","doi":"https://doi.org/10.21437/interspeech.2012-365","mag":"2408267635"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-365","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Institute of Automation. Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation. Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1428","last_page":"1431"},"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":0.9991000294685364,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9854999780654907,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.6767728328704834},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.611555278301239},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6028943061828613},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5905115008354187},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.5450525283813477},{"id":"https://openalex.org/keywords/aperiodic-graph","display_name":"Aperiodic graph","score":0.5313998460769653},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5149551033973694},{"id":"https://openalex.org/keywords/excitation","display_name":"Excitation","score":0.47644808888435364},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4507347643375397},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.42752066254615784},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37420472502708435},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2769755721092224},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.21166068315505981},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.0820946991443634}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6767728328704834},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.611555278301239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6028943061828613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5905115008354187},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.5450525283813477},{"id":"https://openalex.org/C104247578","wikidata":"https://www.wikidata.org/wiki/Q4779368","display_name":"Aperiodic graph","level":2,"score":0.5313998460769653},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5149551033973694},{"id":"https://openalex.org/C83581075","wikidata":"https://www.wikidata.org/wiki/Q1361503","display_name":"Excitation","level":2,"score":0.47644808888435364},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4507347643375397},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.42752066254615784},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37420472502708435},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2769755721092224},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.21166068315505981},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0820946991443634},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2012-365","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W169745891","https://openalex.org/W1600722501","https://openalex.org/W2000513720","https://openalex.org/W2042691334","https://openalex.org/W2049686551","https://openalex.org/W2097634052","https://openalex.org/W2107449214","https://openalex.org/W2129142580","https://openalex.org/W2134383396","https://openalex.org/W2141605952","https://openalex.org/W2149572519","https://openalex.org/W2155295839","https://openalex.org/W2158972663","https://openalex.org/W2164764235","https://openalex.org/W2168523336"],"related_works":["https://openalex.org/W2037661079","https://openalex.org/W2339191433","https://openalex.org/W4287817191","https://openalex.org/W4298800952","https://openalex.org/W2039582600","https://openalex.org/W1992569127","https://openalex.org/W172284633","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3],"excitation":[4,70,102,132],"model":[5,13,71,133],"based":[6,129],"on":[7,130],"amplitude":[8],"spectrum":[9,36],"for":[10,88,120],"hidden":[11],"Markov":[12],"(HMM)-based":[14],"speech":[15,149],"synthesis":[16,48],"system":[17],"(HTS).":[18],"Residual":[19],"signal":[20],"obtained":[21],"from":[22,95],"inverse":[23],"filtering":[24],"is":[25,42,83,134,150],"decomposed":[26],"into":[27,72,106,143],"periodic":[28,45,75],"and":[29,50,53,79,113,140],"aperiodic":[30,114],"spectrums":[31,76],"in":[32,47],"frequency":[33],"domain.":[34],"Amplitude":[35],"of":[37,126,138,147],"half":[38],"pitch":[39,54],"period":[40],"length":[41],"reserved":[43],"as":[44,101],"component":[46],"stage":[49],"zero-phase":[51],"criterion":[52],"synchronous":[55],"overlap":[56],"add":[57],"method":[58],"(PSOLA)":[59],"are":[60,77,99,104],"adopted":[61,84],"to":[62,85],"reconstruct":[63],"the":[64,123,127,145],"residual":[65],"signal.":[66],"Before":[67],"integrating":[68,142],"this":[69],"HTS,":[73,144],"these":[74,96],"normalized":[78],"Linde-Buzo-Gray":[80],"(LBG)":[81],"algorithm":[82],"construct":[86],"codebooks":[87,97],"every":[89],"Mandarin":[90],"final1.":[91],"Then":[92],"index":[93],"parameters":[94],"which":[98],"indicated":[100],"information":[103],"taken":[105],"HTS":[107],"training":[108],"together":[109],"with":[110,136],"spectral,":[111],"F0":[112],"parameters.":[115],"Listening":[116],"test":[117],"showed":[118],"that":[119,137],"female":[121],"voice":[122],"analysis-synthesis":[124],"result":[125],"vocoder":[128],"proposed":[131],"comparable":[135],"STRAIGHT":[139],"when":[141],"quality":[146],"generated":[148],"also":[151],"improved.":[152]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}