{"id":"https://openalex.org/W2972589613","doi":"https://doi.org/10.21437/interspeech.2019-2626","title":"On the Suitability of the Riesz Spectro-Temporal Envelope for WaveNet Based Speech Synthesis","display_name":"On the Suitability of the Riesz Spectro-Temporal Envelope for WaveNet Based Speech Synthesis","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972589613","doi":"https://doi.org/10.21437/interspeech.2019-2626","mag":"2972589613"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2626","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5003670015","display_name":"Jitendra Kumar Dhiman","orcid":"https://orcid.org/0000-0001-8537-6573"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jitendra Kumar Dhiman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015353805","display_name":"Nagaraj Adiga","orcid":"https://orcid.org/0000-0002-3438-567X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nagaraj Adiga","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005652970","display_name":"Chandra Sekhar Seelamantula","orcid":"https://orcid.org/0000-0001-9049-1912"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chandra Sekhar Seelamantula","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10512872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"944","last_page":"948"},"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":0.9998000264167786,"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":0.9983000159263611,"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/envelope","display_name":"Envelope (radar)","score":0.6458612084388733},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4838751554489136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4805067777633667},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42618560791015625},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4063003361225128},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1813959777355194},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07304930686950684}],"concepts":[{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.6458612084388733},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4838751554489136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4805067777633667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42618560791015625},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4063003361225128},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1813959777355194},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07304930686950684},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-2626","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai::78252","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W1510007267","https://openalex.org/W1542873368","https://openalex.org/W2026275791","https://openalex.org/W2030351702","https://openalex.org/W2049686551","https://openalex.org/W2056639312","https://openalex.org/W2069501481","https://openalex.org/W2075769341","https://openalex.org/W2131774270","https://openalex.org/W2135269154","https://openalex.org/W2141998673","https://openalex.org/W2143458888","https://openalex.org/W2395578248","https://openalex.org/W2402287333","https://openalex.org/W2471520273","https://openalex.org/W2519648275","https://openalex.org/W2747070883","https://openalex.org/W2749651610","https://openalex.org/W2803714261"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"We":[0,42,85],"address":[1],"the":[2,6,20,49,58,69,77,83,87,104,109,117,122,131,135,145,150,160,167,175],"problem":[3],"of":[4,10,111,116,152],"estimating":[5],"time-varying":[7],"spectral":[8],"envelope":[9,124,132,169],"a":[11,15,25,30,44],"speech":[12,112,119],"signal":[13],"using":[14,33,130,159],"spectro-temporal":[16,31],"demodulation":[17,45],"technique.":[18],"Unlike":[19],"conventional":[21],"spectrogram,":[22],"we":[23,53],"consider":[24,86],"pitch-adaptive":[26],"spectrogram":[27],"and":[28,36,60,76,89,140],"model":[29],"patch":[32],"an":[34,97,171],"amplitude-":[35],"frequency-modulated":[37],"two-dimensional":[38],"(2-D)":[39],"cosine":[40],"signal.":[41],"employ":[43],"technique":[46],"based":[47],"on":[48,144],"Riesz":[50,123,168],"transform":[51],"that":[52,128,149,157],"proposed":[54],"recently":[55],"to":[56,68,82,156,174],"estimate":[57],"amplitude":[59,64],"frequency":[61,78],"modulations.":[62],"The":[63,114],"modulation":[65,79],"(AM)":[66],"corresponds":[67,81],"vocal-tract":[70],"filter":[71],"magnitude":[72],"response":[73],"(or":[74],"envelope)":[75],"(FM)":[80],"excitation.":[84],"AM":[88],"demonstrate":[90],"its":[91],"effectiveness":[92],"by":[93,134],"incorporating":[94],"it":[95],"as":[96,170],"acoustic":[98],"feature":[99],"for":[100,108],"local":[101],"conditioning":[102],"in":[103],"statistical":[105],"WaveNet":[106],"vocoder":[107],"task":[110],"synthesis.":[113],"quality":[115,151],"synthesized":[118],"obtained":[120,129,158],"with":[121,127],"is":[125,154],"compared":[126],"estimated":[133],"WORLD":[136,161,176],"vocoder.":[137],"Objective":[138],"measures":[139],"subjective":[141],"listening":[142],"tests":[143],"CMU-Arctic":[146],"database":[147],"show":[148],"synthesis":[153],"superior":[155],"envelope.":[162,177],"This":[163],"study":[164],"thus":[165],"establishes":[166],"efficient":[172],"alternative":[173]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
