{"id":"https://openalex.org/W4385993905","doi":"https://doi.org/10.21437/ssw.2023-22","title":"Audiobook synthesis with long-form neural text-to-speech","display_name":"Audiobook synthesis with long-form neural text-to-speech","publication_year":2023,"publication_date":"2023-08-18","ids":{"openalex":"https://openalex.org/W4385993905","doi":"https://doi.org/10.21437/ssw.2023-22"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2023-22","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2023-22","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"12th ISCA Speech Synthesis Workshop (SSW2023)","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/A5107912452","display_name":"Weicheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Weicheng Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074874599","display_name":"Cheng-chieh Yeh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng-Chieh Yeh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092664372","display_name":"Will Beckman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Will Beckman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000571465","display_name":"Tuomo Raitio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuomo Raitio","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015798689","display_name":"Ramya Rasipuram","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramya Rasipuram","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010570444","display_name":"Ladan Golipour","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ladan Golipour","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064317196","display_name":"David Winarsky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Winarsky","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5107912452"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.049,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81235688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"139","last_page":"143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9782000184059143,"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":0.9782000184059143,"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/T11309","display_name":"Music and Audio Processing","score":0.9708999991416931,"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/computer-science","display_name":"Computer science","score":0.6412966251373291},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6005572080612183},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5460113286972046},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.373227059841156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34923988580703735}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6412966251373291},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6005572080612183},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5460113286972046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.373227059841156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34923988580703735}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/ssw.2023-22","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2023-22","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"12th ISCA Speech Synthesis Workshop (SSW2023)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W3192589309"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}