{"id":"https://openalex.org/W3193700177","doi":"https://doi.org/10.21437/ssw.2021-12","title":"Acquiring conversational speaking style from multi-speaker spontaneous dialog corpus for prosody-controllable sequence-to-sequence speech synthesis","display_name":"Acquiring conversational speaking style from multi-speaker spontaneous dialog corpus for prosody-controllable sequence-to-sequence speech synthesis","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3193700177","doi":"https://doi.org/10.21437/ssw.2021-12","mag":"3193700177"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2021-12","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-12","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","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/A5035109881","display_name":"Slava Shechtman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Slava Shechtman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069651955","display_name":"Avrech Ben-David","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Avrech Ben-David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6997,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76378915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9851999878883362,"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/T12031","display_name":"Speech and dialogue systems","score":0.9851999878883362,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9567999839782715,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9462000131607056,"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/prosody","display_name":"Prosody","score":0.7918698191642761},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.75770103931427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7239571809768677},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6871525049209595},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.6187331676483154},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6049638390541077},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5690965056419373},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5319801568984985},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.4959448277950287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45354974269866943},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.4228464961051941},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.399095356464386},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.06629836559295654},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.05622595548629761}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7918698191642761},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.75770103931427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7239571809768677},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6871525049209595},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.6187331676483154},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6049638390541077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5690965056419373},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5319801568984985},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.4959448277950287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45354974269866943},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.4228464961051941},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.399095356464386},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.06629836559295654},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.05622595548629761},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/ssw.2021-12","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-12","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","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/W3149582125","https://openalex.org/W2349468610","https://openalex.org/W2465421051","https://openalex.org/W2161314515","https://openalex.org/W2181715843","https://openalex.org/W652196294","https://openalex.org/W2395605663","https://openalex.org/W1984347656","https://openalex.org/W2772686614","https://openalex.org/W4200068392"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}