{"id":"https://openalex.org/W1968869378","doi":"https://doi.org/10.1109/ialp.2014.6973508","title":"Effectiveness of multiscale fractal dimension-based phonetic segmentation in speech synthesis for low resource language","display_name":"Effectiveness of multiscale fractal dimension-based phonetic segmentation in speech synthesis for low resource language","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W1968869378","doi":"https://doi.org/10.1109/ialp.2014.6973508","mag":"1968869378"},"language":"en","primary_location":{"id":"doi:10.1109/ialp.2014.6973508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2014.6973508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Asian Language Processing (IALP)","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/A5022610118","display_name":"Mohammadi Zaki","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Mohammadi Zaki","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India","[Dhirubhai Ambani, Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India]"],"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]},{"raw_affiliation_string":"[Dhirubhai Ambani, Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India]","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109612079","display_name":"J. Nirmesh Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"J. Nirmesh Shah","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India","[Dhirubhai Ambani, Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India]"],"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]},{"raw_affiliation_string":"[Dhirubhai Ambani, Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India]","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India","[Dhirubhai Ambani, Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India]"],"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]},{"raw_affiliation_string":"[Dhirubhai Ambani, Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India]","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022610118"],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":1.44894316,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84537397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"106"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9987000226974487,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8404443860054016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8126873970031738},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6476032137870789},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6217645406723022},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.613693356513977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5009686946868896},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.48871755599975586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47070786356925964},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.43205520510673523},{"id":"https://openalex.org/keywords/fractal-dimension","display_name":"Fractal dimension","score":0.43094420433044434},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3733823597431183},{"id":"https://openalex.org/keywords/fractal","display_name":"Fractal","score":0.26977381110191345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10238102078437805}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8404443860054016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126873970031738},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6476032137870789},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6217645406723022},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.613693356513977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5009686946868896},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.48871755599975586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47070786356925964},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.43205520510673523},{"id":"https://openalex.org/C26546657","wikidata":"https://www.wikidata.org/wiki/Q1412452","display_name":"Fractal dimension","level":3,"score":0.43094420433044434},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3733823597431183},{"id":"https://openalex.org/C40636538","wikidata":"https://www.wikidata.org/wiki/Q81392","display_name":"Fractal","level":2,"score":0.26977381110191345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10238102078437805},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp.2014.6973508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2014.6973508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W133758878","https://openalex.org/W344150399","https://openalex.org/W1023278555","https://openalex.org/W1536822605","https://openalex.org/W1557133539","https://openalex.org/W1600722501","https://openalex.org/W1629445802","https://openalex.org/W1898667524","https://openalex.org/W1990513930","https://openalex.org/W1997240284","https://openalex.org/W2013004558","https://openalex.org/W2022226126","https://openalex.org/W2033728633","https://openalex.org/W2038729262","https://openalex.org/W2073955790","https://openalex.org/W2078206416","https://openalex.org/W2084609288","https://openalex.org/W2090861223","https://openalex.org/W2104833242","https://openalex.org/W2107860279","https://openalex.org/W2117095944","https://openalex.org/W2118566939","https://openalex.org/W2125838338","https://openalex.org/W2137075158","https://openalex.org/W2145892079","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2171903461","https://openalex.org/W2282341633","https://openalex.org/W3111455066","https://openalex.org/W4301420498","https://openalex.org/W6611766843","https://openalex.org/W6631991466","https://openalex.org/W6770626368"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W2057635330"],"abstract_inverted_index":{"Phonetic":[0],"segmentation":[1,23,66,74,113,138],"plays":[2],"a":[3],"key":[4],"role":[5],"in":[6,57],"developing":[7],"various":[8,18,112],"speech":[9,58,116],"applications.":[10],"In":[11,106],"this":[12],"work,":[13],"we":[14,76],"propose":[15,34],"to":[16,35,53,69,108,194],"use":[17,36],"features":[19,41,50,136,145,187],"for":[20,25,87,120,137],"automatic":[21],"phonetic":[22],"task":[24],"forced":[26],"Viterbi":[27],"alignment":[28],"and":[29,98,128,160,170],"compare":[30],"their":[31],"effectiveness.":[32],"We":[33],"novel":[37,49],"multiscale":[38],"fractal":[39],"dimension-based":[40],"concatenated":[42],"with":[43,184],"Mel-Frequency":[44],"Cepstral":[45,152,157],"Coefficients":[46,153,158],"(MFCC).":[47],"The":[48,165],"are":[51,174],"expected":[52],"capture":[54],"additional":[55],"nonlinearities":[56],"production":[59],"which":[60,83,173],"should":[61],"improve":[62],"the":[63,101,126,171,175,185,189,196,199],"performance":[64],"of":[65,72,100,104,111,177,182],"task.":[67],"However,":[68],"evaluate":[70],"effectiveness":[71,110],"these":[73],"algorithms,":[75,114],"require":[77],"manual":[78],"accurate":[79],"phoneme-level":[80],"labeled":[81],"data":[82],"is":[84,132,192],"not":[85],"available":[86],"low":[88,95],"resource":[89,96],"languages":[90,103],"such":[91,146],"as":[92,147],"Gujarati":[93,121],"(a":[94],"language":[97],"one":[99],"official":[102],"India).":[105],"order":[107],"measure":[109],"HMM-based":[115],"synthesis":[117],"system":[118],"(HTS)":[119],"have":[122],"been":[123],"built.":[124],"From":[125],"subjective":[127],"objective":[129],"evaluations,":[130],"it":[131],"observed":[133],"that":[134],"FD-based":[135],"work":[139],"moderately":[140],"better":[141],"than":[142],"other":[143,200],"state-of-the-art":[144],"MFCC,":[148],"Perceptual":[149],"Linear":[150],"Prediction":[151],"(PLP-CC),":[154],"Cochlear":[155],"Filter":[156],"(CFCC),":[159],"RelAtive":[161],"SpecTrAl":[162],"(RASTA)-based":[163],"PLP-CC.":[164],"Mean":[166],"Opinion":[167],"Score":[168],"(MOS)":[169],"Degraded-MOS,":[172],"measures":[176],"naturalness":[178],"indicate":[179],"an":[180],"improvement":[181],"9.69%":[183],"proposed":[186],"from":[188],"MFCC":[190],"(which":[191],"found":[193],"be":[195],"best":[197],"among":[198],"features)":[201],"based":[202],"features.":[203]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}