{"id":"https://openalex.org/W3175498341","doi":"https://doi.org/10.21437/ssw.2021-31","title":"Multi-Scale Spectrogram Modelling for Neural Text-to-Speech","display_name":"Multi-Scale Spectrogram Modelling for Neural Text-to-Speech","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3175498341","doi":"https://doi.org/10.21437/ssw.2021-31","mag":"3175498341"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2021-31","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-31","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.15649","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035308242","display_name":"Ammar N. Abbas","orcid":"https://orcid.org/0000-0002-2578-5137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ammar Abbas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064828339","display_name":"Bajibabu Bollepalli","orcid":"https://orcid.org/0000-0003-1268-0579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bajibabu Bollepalli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014483986","display_name":"Alexis Moinet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexis Moinet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083043476","display_name":"Arnaud Joly","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arnaud Joly","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006537074","display_name":"Penny Karanasou","orcid":"https://orcid.org/0000-0003-1939-4161"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Penny Karanasou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089340248","display_name":"Peter Makarov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Makarov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016847906","display_name":"Simon Slangens","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon Slangens","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066855316","display_name":"Sri Karlapati","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sri Karlapati","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"177","last_page":"182"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9975000023841858,"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":0.9973999857902527,"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/spectrogram","display_name":"Spectrogram","score":0.977977991104126},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6734165549278259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6404529213905334},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6272310018539429},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6035074591636658},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5426490902900696},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5326088666915894},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4710540473461151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4435121715068817},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19644039869308472}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.977977991104126},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6734165549278259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6404529213905334},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6272310018539429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6035074591636658},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5426490902900696},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5326088666915894},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4710540473461151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4435121715068817},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19644039869308472},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/ssw.2021-31","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-31","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.15649","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.15649","pdf_url":"https://arxiv.org/pdf/2106.15649","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3175498341","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.15649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2106.15649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.15649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.15649","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.15649","pdf_url":"https://arxiv.org/pdf/2106.15649","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3175498341.pdf","grobid_xml":"https://content.openalex.org/works/W3175498341.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1563963229","https://openalex.org/W2129142580","https://openalex.org/W2608207374","https://openalex.org/W2615666954","https://openalex.org/W2624871570","https://openalex.org/W2897548994","https://openalex.org/W2945544731","https://openalex.org/W2948211236","https://openalex.org/W2949175740","https://openalex.org/W2949382160","https://openalex.org/W2952269766","https://openalex.org/W2962691331","https://openalex.org/W2963927338","https://openalex.org/W2964243274","https://openalex.org/W2971753973","https://openalex.org/W2976159681","https://openalex.org/W2990883660","https://openalex.org/W3015440759","https://openalex.org/W3016136182","https://openalex.org/W3086296097","https://openalex.org/W3096634037","https://openalex.org/W3097320728","https://openalex.org/W3104580832","https://openalex.org/W3130016944"],"related_works":["https://openalex.org/W1936312352","https://openalex.org/W3211165121","https://openalex.org/W2101011209","https://openalex.org/W1605605950","https://openalex.org/W2162295204","https://openalex.org/W3202098869","https://openalex.org/W2294995564","https://openalex.org/W2127589467","https://openalex.org/W1969930246","https://openalex.org/W3163003432","https://openalex.org/W2735977374","https://openalex.org/W2365963885","https://openalex.org/W2166994723","https://openalex.org/W3133012673","https://openalex.org/W2166128510","https://openalex.org/W3082521910","https://openalex.org/W2144294430","https://openalex.org/W2152807729","https://openalex.org/W2299809954","https://openalex.org/W2111741938"],"abstract_inverted_index":{"We":[0,19,57],"propose":[1],"a":[2,21],"novel":[3],"Multi-Scale":[4],"Spectrogram":[5],"(MSS)":[6],"modelling":[7],"approach":[8],"to":[9,49,112],"synthesise":[10],"speech":[11],"with":[12],"an":[13],"improved":[14],"coarse":[15],"and":[16,42,69,90],"fine-grained":[17,55],"prosody.":[18,56],"present":[20,58],"generic":[22],"multi-scale":[23],"spectrogram":[24,98],"prediction":[25],"mechanism":[26],"where":[27,72],"the":[28,37,73,81,113],"system":[29,77],"first":[30],"predicts":[31],"coarser":[32,46],"scale":[33,47,52],"mel-spectrograms":[34,48,53],"that":[35,104],"capture":[36],"suprasegmental":[38],"information":[39],"in":[40,75,99],"speech,":[41],"later":[43],"uses":[44],"these":[45],"predict":[50],"finer":[51],"capturing":[54],"details":[59],"for":[60],"two":[61,116],"specific":[62],"versions":[63],"of":[64],"MSS":[65,68,71,86,95,106],"called":[66],"Word-level":[67,85,105],"Sentence-level":[70,94],"scales":[74],"our":[76],"are":[78],"motivated":[79],"by":[80],"linguistic":[82],"units.":[83],"The":[84],"models":[87,96],"word,":[88],"phoneme,":[89],"frame-level":[91],"spectrograms":[92],"while":[93],"sentence-level":[97],"addition.":[100],"Subjective":[101],"evaluations":[102],"show":[103],"performs":[107],"statistically":[108],"significantly":[109],"better":[110],"compared":[111],"baseline":[114],"on":[115],"voices.":[117]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}