{"id":"https://openalex.org/W2399979888","doi":"https://doi.org/10.1109/icassp.2016.7472753","title":"Significance of Pseudo-syllables in building better acoustic models for Indian English TTS","display_name":"Significance of Pseudo-syllables in building better acoustic models for Indian English TTS","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2399979888","doi":"https://doi.org/10.1109/icassp.2016.7472753","mag":"2399979888"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472753","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/A5107865681","display_name":"S. Vignesh","orcid":null},"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":"S. Rupak Vignesh","raw_affiliation_strings":["Indian Institute of Technology Madras"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112135760","display_name":"S. Aswin Shanmugam","orcid":"https://orcid.org/0009-0001-3792-4659"},"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. Aswin Shanmugam","raw_affiliation_strings":["Indian Institute of Technology Madras"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras","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"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107865681"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":1.2854,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.86496014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5620","last_page":"5624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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/syllabification","display_name":"Syllabification","score":0.9399185180664062},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.7304353713989258},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7247188091278076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7063318490982056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5033099055290222},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46094000339508057},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.41868138313293457}],"concepts":[{"id":"https://openalex.org/C2779211743","wikidata":"https://www.wikidata.org/wiki/Q11994045","display_name":"Syllabification","level":3,"score":0.9399185180664062},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7304353713989258},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7247188091278076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063318490982056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5033099055290222},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46094000339508057},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.41868138313293457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472753","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":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W58497106","https://openalex.org/W95152782","https://openalex.org/W1491238342","https://openalex.org/W1690307316","https://openalex.org/W1779680350","https://openalex.org/W1911232923","https://openalex.org/W2015876361","https://openalex.org/W2020577846","https://openalex.org/W2044682042","https://openalex.org/W2048684118","https://openalex.org/W2108060348","https://openalex.org/W2124878473","https://openalex.org/W2147749835","https://openalex.org/W2163632146","https://openalex.org/W2405896898","https://openalex.org/W2506554303","https://openalex.org/W3173177459","https://openalex.org/W6603838645"],"related_works":["https://openalex.org/W4205258283","https://openalex.org/W2947041878","https://openalex.org/W2222951281","https://openalex.org/W2162409476","https://openalex.org/W1574591767","https://openalex.org/W2809588103","https://openalex.org/W642320556","https://openalex.org/W1972536245","https://openalex.org/W2935873809","https://openalex.org/W4232746212"],"abstract_inverted_index":{"Signal":[0],"processing":[1],"based":[2,10,50],"landmark":[3,18],"detection":[4],"is":[5,19,49,58,76,96,104,164],"precise":[6],"compared":[7],"to":[8,78,98,114],"HMM":[9],"alignment,":[11],"primarily":[12],"because":[13],"the":[14,17,23,37,47,62,65,80,100,110,134,139,144,171],"location":[15],"of":[16,25,41,46],"not":[20],"factored":[21],"in":[22,143,170],"estimation":[24],"parameters.":[26],"Acoustic":[27],"cues":[28,88],"for":[29,68,83,148],"syllable":[30,91,112],"boundaries":[31],"are":[32,124],"usually":[33],"obtained":[34,89,128],"by":[35,156],"exploiting":[36],"inherent":[38],"sonority":[39],"characteristics":[40],"a":[42,59,165],"syllable.":[43],"As":[44],"syllabification":[45,81],"text":[48],"on":[51],"generalized":[52],"rules":[53,82],"or":[54],"lexicon":[55],"definitions,":[56],"there":[57,163],"mismatch":[60],"between":[61],"acoustical":[63],"and":[64,137,152,158],"lexical":[66],"segments":[67],"non-native":[69],"syllabification.":[70],"In":[71],"this":[72],"paper,":[73],"an":[74],"attempt":[75],"made":[77],"modify":[79],"Indian":[84,119],"English":[85,120],"using":[86,106,126],"acoustic":[87],"from":[90],"boundaries.":[92,118],"The":[93],"modified":[94,111],"syllabifier":[95],"used":[97],"syllabify":[99],"text.":[101],"Embedded":[102],"re-estimation":[103,132],"performed":[105],"forced":[107],"alignment":[108],"at":[109,133],"level":[113,136],"obtain":[115],"refined":[116],"phoneme":[117],"Text-to-Speech":[121],"(TTS)":[122],"systems":[123],"built":[125],"labels":[127],"after":[129],"(i)":[130],"embedded":[131],"sentence":[135],"(ii)":[138],"aforementioned":[140],"procedure.":[141],"Reduction":[142],"word":[145],"error":[146],"rates":[147],"both":[149],"native":[150],"Aryan":[151],"Dravidian":[153],"speakers":[154],"(relatively":[155],"54.1%":[157],"52.4%":[159],"respectively),":[160],"suggests":[161],"that":[162],"significant":[166],"synthesis":[167],"quality":[168],"improvement":[169],"proposed":[172],"system.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}