{"id":"https://openalex.org/W2118566939","doi":"https://doi.org/10.1109/icassp.2014.6853600","title":"Effectiveness of PLP-based phonetic segmentation for speech synthesis","display_name":"Effectiveness of PLP-based phonetic segmentation for speech synthesis","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2118566939","doi":"https://doi.org/10.1109/icassp.2014.6853600","mag":"2118566939"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5091143209","display_name":"Nirmesh J. Shah","orcid":"https://orcid.org/0000-0002-7294-6757"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nirmesh J. 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]"],"raw_orcid":null,"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/A5082723451","display_name":"Bhavik Vachhani","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bhavik B. Vachhani","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]"],"raw_orcid":null,"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/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hardik B. Sailor","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]"],"raw_orcid":null,"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 University","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]"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":2.8948,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92830815,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"270","last_page":"274"},"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":0.9998000264167786,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9976999759674072,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8320729732513428},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7958561778068542},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7129645943641663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6799860596656799},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.5631600022315979},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.557392418384552},{"id":"https://openalex.org/keywords/gujarati","display_name":"Gujarati","score":0.5489311218261719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5358705520629883},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.47084495425224304},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46410664916038513},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.4427202641963959},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.33917003870010376}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8320729732513428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7958561778068542},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7129645943641663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6799860596656799},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.5631600022315979},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.557392418384552},{"id":"https://openalex.org/C2779296024","wikidata":"https://www.wikidata.org/wiki/Q5137","display_name":"Gujarati","level":2,"score":0.5489311218261719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5358705520629883},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.47084495425224304},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46410664916038513},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.4427202641963959},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33917003870010376},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W170586818","https://openalex.org/W344150399","https://openalex.org/W1560013842","https://openalex.org/W1600722501","https://openalex.org/W1997240284","https://openalex.org/W2001496355","https://openalex.org/W2008161911","https://openalex.org/W2022226126","https://openalex.org/W2026858810","https://openalex.org/W2057635330","https://openalex.org/W2082330413","https://openalex.org/W2083904075","https://openalex.org/W2084609288","https://openalex.org/W2090861223","https://openalex.org/W2098363562","https://openalex.org/W2107860279","https://openalex.org/W2125838338","https://openalex.org/W2128160875","https://openalex.org/W2137075158","https://openalex.org/W2145892079","https://openalex.org/W2171752983","https://openalex.org/W2171903461","https://openalex.org/W2575483272","https://openalex.org/W4301420498","https://openalex.org/W6607038894","https://openalex.org/W6611766843","https://openalex.org/W6674795352","https://openalex.org/W6684765037","https://openalex.org/W6732323387"],"related_works":["https://openalex.org/W2789575942","https://openalex.org/W2018086531","https://openalex.org/W2477092114","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948"],"abstract_inverted_index":{"In":[0,23,98],"this":[1],"paper,":[2],"use":[3,29],"of":[4,16,30,69,92,96,103],"Viterbi-based":[5,127],"algorithm":[6,12],"and":[7,49,120,128],"spectral":[8,32],"transition":[9],"measure":[10,101],"(STM)-based":[11],"for":[13,62,84,112],"the":[14,24,93,118],"task":[15],"speech":[17,108],"data":[18,79],"labeling":[19],"is":[20,81,124],"being":[21],"attempted.":[22],"STM":[25,129],"framework,":[26],"we":[27,73],"propose":[28],"several":[31],"features":[33],"such":[34,88],"as":[35,89],"recently":[36],"proposed":[37],"cochlear":[38],"filter":[39],"cepstral":[40,46,59],"coefficients":[41,47,60],"(CFCC),":[42],"perceptual":[43],"linear":[44],"prediction":[45],"(PLPCC)":[48],"RelAtive":[50],"SpecTrAl":[51],"(RASTA)-based":[52],"PLPCC":[53],"in":[54],"addition":[55],"to":[56,100],"Mel":[57],"frequency":[58],"(MFCC)":[61],"phonetic":[63],"segmentation":[64,71,105,132],"task.":[65],"To":[66],"evaluate":[67],"effectiveness":[68,102],"these":[70],"algorithms,":[72,106],"require":[74],"manual":[75],"accurate":[76],"phoneme-level":[77],"labeled":[78],"which":[80],"not":[82],"available":[83],"low":[85],"resourced":[86],"languages":[87,95],"Gujarati":[90,113],"(one":[91],"official":[94],"India).":[97],"order":[99],"various":[104],"HMM-based":[107],"synthesis":[109],"system":[110],"(HTS)":[111],"has":[114],"been":[115],"built.":[116],"From":[117],"subjective":[119],"objective":[121],"evaluations,":[122],"it":[123],"observed":[125],"that":[126],"with":[130],"PLPCC-based":[131],"algorithms":[133],"work":[134],"better":[135],"than":[136],"other":[137],"algorithms.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}