{"id":"https://openalex.org/W2533495","doi":"https://doi.org/10.21437/interspeech.2007-546","title":"Automatic building of synthetic voices from large multi-paragraph speech databases","display_name":"Automatic building of synthetic voices from large multi-paragraph speech databases","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W2533495","doi":"https://doi.org/10.21437/interspeech.2007-546","mag":"2533495"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-546","doi":"https://doi.org/10.21437/interspeech.2007-546","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-546","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},"volume":null,"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/A5113522207","display_name":"Kishore Sunkeswari Prahallad","orcid":null,"observed_orcids":[]},"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":"Kishore Prahallad","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069337237","display_name":"Arthur R. Toth","orcid":null,"observed_orcids":[]},"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":"Arthur R. Toth","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831","observed_orcids":["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":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","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":1.2583,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.78098066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2901","last_page":"2904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00039999998989515007,"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":9.999999747378752e-05,"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/forced-alignment","display_name":"forced alignment","score":0.7870000004768372},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"speech segmentation","score":0.9139999747276306},{"id":"https://openalex.org/keywords/prosody","display_name":"prosody","score":0.7540000081062317},{"id":"https://openalex.org/keywords/contextual-information","display_name":"contextual information","score":0.7400000095367432},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"speech synthesis","score":0.5799999833106995}],"concepts":[{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.910363495349884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348463773727417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6163287162780762},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5671592950820923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5483036637306213},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4816245436668396},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.47976478934288025},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43054479360580444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4231649339199066},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4068882167339325},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34748780727386475},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32536375522613525},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19883477687835693}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2007-546","doi":"https://doi.org/10.21437/interspeech.2007-546","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-546","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.66.7285","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.7285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~awb/papers/is2007/IS071088.PDF","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W121216320","https://openalex.org/W202879582","https://openalex.org/W1577300430","https://openalex.org/W1585826837","https://openalex.org/W2100873065","https://openalex.org/W2139795704","https://openalex.org/W2150612204","https://openalex.org/W2159290663","https://openalex.org/W2407137326"],"related_works":["https://openalex.org/W2407137326","https://openalex.org/W7096417681","https://openalex.org/W2330075180","https://openalex.org/W114226241","https://openalex.org/W48727633","https://openalex.org/W2145880678","https://openalex.org/W3082699039","https://openalex.org/W1517747606","https://openalex.org/W2559071631","https://openalex.org/W4205154972"],"abstract_inverted_index":{"Large":[0],"multi":[1],"paragraph":[2],"speech":[3,37,49,97,101],"databases":[4],"encapsulate":[5],"prosodic":[6],"and":[7,59],"contextual":[8],"information":[9],"beyond":[10],"the":[11,42,61,67,70],"sentence":[12],"level":[13],"which":[14],"could":[15,51,79],"be":[16,52,80],"exploited":[17],"to":[18,56,82],"build":[19,83],"natural":[20],"sounding":[21],"voices.":[22],"This":[23],"paper":[24],"discusses":[25],"our":[26],"efforts":[27],"on":[28],"automatic":[29],"building":[30],"of":[31,45,47,66,69,87],"synthetic":[32],"voices":[33,88],"from":[34,89],"large":[35,48,85,92,99],"multi-paragraph":[36,93,100],"databases.":[38],"We":[39,73],"show":[40],"that":[41,60],"primary":[43],"issue":[44],"segmentation":[46],"file":[50],"addressed":[53],"with":[54],"modifications":[55],"forced-alignment":[57],"technique":[58,63],"proposed":[62],"is":[64],"independent":[65],"duration":[68],"audio":[71],"file.":[72],"also":[74],"discuss":[75],"how":[76],"this":[77],"framework":[78],"extended":[81],"a":[84],"number":[86],"public":[90,104],"domain":[91,105],"recordings.":[94],"Index":[95],"Terms:":[96],"synthesis,":[98],"databases,":[102],"forced-alignment,":[103],"recordings":[106]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":6}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}