{"id":"https://openalex.org/W2408081206","doi":"https://doi.org/10.1109/icassp.2016.7472750","title":"Template based techniques for automatic segmentation of TTS unit database","display_name":"Template based techniques for automatic segmentation of TTS unit database","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2408081206","doi":"https://doi.org/10.1109/icassp.2016.7472750","mag":"2408081206"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472750","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/A5112357933","display_name":"S. Adithya","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]},{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"S. Adithya","raw_affiliation_strings":["PESIT-BSC, Bangalore as Research Associates in the TTS-Consortium project","University of California, San Diego"],"affiliations":[{"raw_affiliation_string":"PESIT-BSC, Bangalore as Research Associates in the TTS-Consortium project","institution_ids":["https://openalex.org/I196608512"]},{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072177587","display_name":"S. P. V. Subba Rao","orcid":"https://orcid.org/0000-0001-8912-4103"},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]},{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Sunil Rao","raw_affiliation_strings":["Arizona State University, Tempe, Arizona","PESIT-BSC, Bangalore as Research Associates in the TTS-Consortium project"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, Arizona","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"PESIT-BSC, Bangalore as Research Associates in the TTS-Consortium project","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018741678","display_name":"C Mahima","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. Mahima","raw_affiliation_strings":["PES Institute of Technology - Bangalore South Campus (PESIT-BSC), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"PES Institute of Technology - Bangalore South Campus (PESIT-BSC), Bangalore, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111276536","display_name":"S. Vishnu","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]},{"id":"https://openalex.org/I26538001","display_name":"San Diego State University","ror":"https://ror.org/0264fdx42","country_code":"US","type":"education","lineage":["https://openalex.org/I26538001"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"S. Vishnu","raw_affiliation_strings":["PESIT-BSC, Bangalore as Research Associates in the TTS-Consortium project","San Diego State University, San Diego"],"affiliations":[{"raw_affiliation_string":"PESIT-BSC, Bangalore as Research Associates in the TTS-Consortium project","institution_ids":["https://openalex.org/I196608512"]},{"raw_affiliation_string":"San Diego State University, San Diego","institution_ids":["https://openalex.org/I26538001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025921856","display_name":"Mythri Thippareddy","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mythri Thippareddy","raw_affiliation_strings":["PES Institute of Technology - Bangalore South Campus (PESIT-BSC), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"PES Institute of Technology - Bangalore South Campus (PESIT-BSC), Bangalore, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036811576","display_name":"V. Ramasubramanian","orcid":"https://orcid.org/0000-0002-0676-9174"},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"V. Ramasubramanian","raw_affiliation_strings":["PES Institute of Technology - Bangalore South Campus (PESIT-BSC), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"PES Institute of Technology - Bangalore South Campus (PESIT-BSC), Bangalore, India","institution_ids":["https://openalex.org/I196608512"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112357933"],"corresponding_institution_ids":["https://openalex.org/I196608512","https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.02678797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"assp 23","issue":null,"first_page":"5605","last_page":"5609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9954000115394592,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/segmentation","display_name":"Segmentation","score":0.827424168586731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8157890439033508},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6324136257171631},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5619985461235046},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5565782189369202},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.5475030541419983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5415201187133789},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5304583311080933},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5274398922920227},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47190433740615845},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.42180415987968445},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4212067723274231}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.827424168586731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8157890439033508},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6324136257171631},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5619985461235046},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5565782189369202},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.5475030541419983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5415201187133789},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5304583311080933},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5274398922920227},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47190433740615845},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.42180415987968445},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4212067723274231},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472750","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":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W168484277","https://openalex.org/W192085530","https://openalex.org/W1496801689","https://openalex.org/W1826405859","https://openalex.org/W1945490744","https://openalex.org/W1950396994","https://openalex.org/W1988378063","https://openalex.org/W1997240284","https://openalex.org/W2079337129","https://openalex.org/W2097207027","https://openalex.org/W2104653033","https://openalex.org/W2113601991","https://openalex.org/W2116059692","https://openalex.org/W2122304690","https://openalex.org/W2122420664","https://openalex.org/W2126939586","https://openalex.org/W2155368638","https://openalex.org/W2165199619","https://openalex.org/W2170160235","https://openalex.org/W2244366121","https://openalex.org/W2405896898","https://openalex.org/W2495104180","https://openalex.org/W2575483272","https://openalex.org/W4395958260","https://openalex.org/W6606916877","https://openalex.org/W6732323387"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W3144569342","https://openalex.org/W2340308015"],"abstract_inverted_index":{"We":[0,88,114],"address":[1],"the":[2,8,23,65,91,94,105,117,130,155,170,190],"problem":[3],"of":[4,7,57,64,93,107,189],"automatic":[5],"segmentation":[6,21,96,103,121,132,152,188],"unit":[9],"database":[10,100],"in":[11,22,86,112],"unit-selection":[12],"based":[13,18,72,120,136,158,173],"TTS":[14,83],"and":[15,43,74,128,146,165,167,177],"propose":[16],"template":[17,119,172],"forced":[19],"alignment":[20],"one-pass":[24],"dynamic":[25],"programming":[26],"(DP)":[27],"framework":[28,97],"with":[29,54,149],"several":[30],"variants:":[31],"i)":[32],"multi-template":[33,48],"representation":[34],"derived":[35],"by":[36],"modified":[37],"K-means":[38,52],"(MKM)":[39],"algorithm,":[40],"ii)":[41],"context-independent":[42],"context-dependent":[44],"templates":[45],"for":[46,70,79,82,101,123],"reduced":[47],"representation,":[49],"iii)":[50],"segmental":[51],"algorithm":[53],"MKM":[55],"modeling":[56,73],"phone":[58],"classes,":[59],"as":[60],"a":[61],"template-based":[62],"equivalent":[63],"conventional":[66],"embedded":[67],"re-estimation":[68],"procedure":[69],"HMM":[71,164],"segmentation,":[75],"that":[76,169],"is":[77],"typical":[78],"deriving":[80],"unit-databases":[81],"(e.g.":[84],"EHMM":[85],"Festival).":[87],"first":[89],"benchmark":[90,129],"performance":[92],"proposed":[95,118,131,171],"on":[98,137,142],"TIMIT":[99],"phonetic":[102,108],"given":[104],"availability":[106],"labeling":[109],"ground":[110],"truth":[111],"TIMIT.":[113],"then":[115],"apply":[116],"algorithms":[122],"syllabic":[124],"Indian":[125],"language":[126],"TTS,":[127],"using":[133],"objective":[134],"measures":[135],"spectral":[138,179],"distortions":[139],"(SD)":[140],"obtained":[141],"time-aligned":[143],"speech":[144],"utterances":[145],"compare":[147],"it":[148],"other":[150],"recent":[151],"approaches,":[153],"namely":[154],"group-delay":[156],"(GD)":[157],"semiautomatic":[159],"method,":[160,162],"Hybrid":[161],"EHMM,":[163],"SKM-HMM":[166],"show":[168],"approaches":[174],"offer":[175],"comparable":[176],"better":[178],"distortions,":[180],"validating":[181],"their":[182],"ability":[183],"to":[184],"provide":[185],"accurate":[186],"high-resolution":[187],"unit-database.":[191]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}