{"id":"https://openalex.org/W2104653033","doi":"https://doi.org/10.1109/icassp.2009.4960451","title":"Optimizing segment label boundaries for statistical speech synthesis","display_name":"Optimizing segment label boundaries for statistical speech synthesis","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2104653033","doi":"https://doi.org/10.1109/icassp.2009.4960451","mag":"2104653033"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan W. Black","raw_affiliation_strings":["Language Technologies, Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technologies Institute; Carnegie Mellon University; Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies, Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute; Carnegie Mellon University; Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013132605","display_name":"John Kominek","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Kominek","raw_affiliation_strings":["Language Technologies, Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technologies Institute; Carnegie Mellon University; Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies, Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute; Carnegie Mellon University; Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":3.1711,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92266173,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3785","last_page":"3788"},"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":0.9990000128746033,"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":0.9965000152587891,"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/phone","display_name":"Phone","score":0.7560468912124634},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7446053624153137},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6821582317352295},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6720475554466248},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6486895680427551},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6450624465942383},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.4434766173362732},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.43986859917640686},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41507411003112793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3137773871421814},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13516166806221008},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11101275682449341}],"concepts":[{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7560468912124634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7446053624153137},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6821582317352295},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6720475554466248},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6486895680427551},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6450624465942383},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.4434766173362732},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.43986859917640686},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41507411003112793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3137773871421814},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13516166806221008},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11101275682449341},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W202879582","https://openalex.org/W1538607601","https://openalex.org/W2013196554","https://openalex.org/W2096980176","https://openalex.org/W2104499423","https://openalex.org/W2125279775","https://openalex.org/W2134756243","https://openalex.org/W2150612204","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2163246542","https://openalex.org/W2169847499","https://openalex.org/W2396366106","https://openalex.org/W2400063444","https://openalex.org/W6632366324","https://openalex.org/W6678688679"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W2350702655","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W2319685803","https://openalex.org/W2026012944","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3],"new":[4],"optimization":[5],"technique":[6],"for":[7],"moving":[8],"segment":[9],"labels":[10],"(phone":[11],"and":[12,29],"subphonetic)":[13],"to":[14,35,45],"optimize":[15],"statistical":[16],"parametric":[17],"speech":[18,43],"synthesis":[19],"models.":[20],"The":[21],"choice":[22],"of":[23,40],"objective":[24],"measures":[25],"is":[26],"investigated":[27],"thoroughly":[28],"listening":[30],"tests":[31],"show":[32],"the":[33,38,41,47],"results":[34],"significantly":[36],"improve":[37],"quality":[39],"generated":[42],"equivalent":[44],"increasing":[46],"database":[48],"size":[49],"by":[50],"3":[51],"fold.":[52]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}