{"id":"https://openalex.org/W4391021699","doi":"https://doi.org/10.1109/asru57964.2023.10389630","title":"Towards Developing State-of-The-Art TTS Synthesisers for 13 Indian Languages with Signal Processing Aided Alignments","display_name":"Towards Developing State-of-The-Art TTS Synthesisers for 13 Indian Languages with Signal Processing Aided Alignments","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021699","doi":"https://doi.org/10.1109/asru57964.2023.10389630"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389630","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5091337351","display_name":"Anusha Prakash","orcid":"https://orcid.org/0000-0001-7913-9336"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anusha Prakash","raw_affiliation_strings":["Indian Institute of Technology Madras,India","Indian Institute of Technology Madras, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras,India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S Umesh","raw_affiliation_strings":["Indian Institute of Technology Madras,India","Indian Institute of Technology Madras, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras,India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032418366","display_name":"Hema A. Murthy","orcid":"https://orcid.org/0000-0003-3611-6550"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hema A Murthy","raw_affiliation_strings":["Indian Institute of Technology Madras,India","Indian Institute of Technology Madras, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras,India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091337351"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.1746,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59607452,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9939000010490417,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.982699990272522,"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/computer-science","display_name":"Computer science","score":0.7943880558013916},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6574836373329163},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6328365206718445},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.6054425239562988},{"id":"https://openalex.org/keywords/computer-aided","display_name":"Computer-aided","score":0.55497807264328},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5413550734519958},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5037204623222351},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.49847888946533203},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.48038536310195923},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.4582890272140503},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44482100009918213},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4346426725387573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42867547273635864},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3432348966598511},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.18937349319458008},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18880945444107056},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.15746691823005676},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07353869080543518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943880558013916},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6574836373329163},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6328365206718445},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.6054425239562988},{"id":"https://openalex.org/C2780727963","wikidata":"https://www.wikidata.org/wiki/Q5157368","display_name":"Computer-aided","level":2,"score":0.55497807264328},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5413550734519958},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5037204623222351},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.49847888946533203},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.48038536310195923},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.4582890272140503},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44482100009918213},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4346426725387573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42867547273635864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3432348966598511},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.18937349319458008},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18880945444107056},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.15746691823005676},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07353869080543518},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389630","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"systems":[2,84,95,106,113],"synthesise":[3],"high-quality":[4],"speech,":[5],"but":[6],"this":[7],"typically":[8],"requires":[9],"a":[10,42,71],"large":[11],"amount":[12],"of":[13,39,73],"data.":[14,69],"As":[15,70],"E2E":[16],"synthesis":[17],"progressed":[18],"from":[19],"Tacotron":[20],"to":[21,61],"FastSpeech2,":[22],"it":[23],"became":[24],"evident":[25],"that":[26,83],"features":[27],"representing":[28],"prosody,":[29],"particularly":[30],"subword":[31],"durations,":[32],"are":[33,79,92],"important":[34],"for":[35,48,66,115],"error-free":[36],"synthesis.":[37],"Variants":[38],"FastSpeech":[40],"use":[41],"teacher":[43],"model":[44],"or":[45],"forced":[46,59],"alignments":[47],"training.":[49],"This":[50],"paper":[51],"uses":[52],"signal":[53,89],"processing":[54],"cues":[55],"in":[56,102],"tandem":[57],"with":[58],"alignment":[60,99],"produce":[62],"accurate":[63],"phone":[64],"boundaries":[65],"the":[67,87,109],"training":[68],"result":[72],"better":[74,93],"duration":[75],"modelling,":[76],"good-quality":[77],"synthesisers":[78],"developed.":[80],"Evaluations":[81],"indicate":[82],"developed":[85,96],"using":[86,97],"proposed":[88],"processing-aided":[90],"approach":[91],"than":[94],"other":[98],"approaches,":[100],"especially":[101],"low-resource":[103],"scenarios.":[104],"Our":[105],"also":[107],"outperform":[108],"existing":[110],"best":[111],"TTS":[112],"available":[114],"13":[116],"Indian":[117],"languages.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}
