{"id":"https://openalex.org/W4402112120","doi":"https://doi.org/10.21437/interspeech.2024-1327","title":"Total-Duration-Aware Duration Modeling for Text-to-Speech Systems","display_name":"Total-Duration-Aware Duration Modeling for Text-to-Speech Systems","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112120","doi":"https://doi.org/10.21437/interspeech.2024-1327"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1327","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1327","pdf_url":"https://www.isca-archive.org/interspeech_2024/eskimez24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/eskimez24_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026088950","display_name":"\u015eefik Emre Eskimez","orcid":"https://orcid.org/0000-0001-6259-5925"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sefik Emre Eskimez","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005333910","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0002-8482-6138"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028363114","display_name":"Manthan Thakker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manthan Thakker","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101375070","display_name":"Chung-Hsien Tsai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chung-Hsien Tsai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112416737","display_name":"Canrun Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Canrun Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033383677","display_name":"Zhen Xiao","orcid":"https://orcid.org/0000-0003-3832-3916"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Xiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023001621","display_name":"Hemin Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hemin Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046470928","display_name":"Zirun Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zirun Zhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106627865","display_name":"Min Tang","orcid":"https://orcid.org/0009-0006-3428-9967"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Tang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329353","display_name":"Sheng Zhao","orcid":"https://orcid.org/0000-0002-9624-5381"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5026088950"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3603,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66335884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2290","last_page":"2294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.92330002784729,"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":0.92330002784729,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.957282304763794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6670322418212891},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48693788051605225},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33491671085357666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32225140929222107},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0641503632068634}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.957282304763794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6670322418212891},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48693788051605225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33491671085357666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32225140929222107},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0641503632068634},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1327","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1327","pdf_url":"https://www.isca-archive.org/interspeech_2024/eskimez24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-1327","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1327","pdf_url":"https://www.isca-archive.org/interspeech_2024/eskimez24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4402112120.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2348837382","https://openalex.org/W746329893","https://openalex.org/W4205872570","https://openalex.org/W4245971243","https://openalex.org/W1922805944","https://openalex.org/W4253588120","https://openalex.org/W2383732295","https://openalex.org/W3204019825"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}
