{"id":"https://openalex.org/W7128239512","doi":"https://doi.org/10.1007/978-981-96-6603-4_12","title":"STD: Using Self-attention Discriminators to\u00a0Improve Speech Synthesis","display_name":"STD: Using Self-attention Discriminators to\u00a0Improve Speech Synthesis","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W7128239512","doi":"https://doi.org/10.1007/978-981-96-6603-4_12"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-96-6603-4_12","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-96-6603-4_12","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5113262378","display_name":"Kuan Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuan Guo","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0008-2611-2234","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125298152","display_name":"Xingyuan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingyuan Chen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0006-6331-6928","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101302336","display_name":"Yicui Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yicui Peng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0007-4295-0038","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125305260","display_name":"Bing Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bing Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0007-0820-2204","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113262379","display_name":"Weishan Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weishan Feng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0008-5145-0681","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109736858","display_name":"Chunhao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunhao Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0005-8292-1077","affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Peng Jin","orcid":"https://orcid.org/0000-0002-4835-0312"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Jin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4835-0312","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"165","last_page":"179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6128000020980835,"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":0.6128000020980835,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.07880000025033951,"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"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.04580000042915344,"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/speech-synthesis","display_name":"Speech synthesis","score":0.5515999794006348},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37560001015663147},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.31630000472068787},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.30250000953674316},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.28349998593330383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500000238418579},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6259999871253967},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5515999794006348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42879998683929443},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36820000410079956},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.27720001339912415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-96-6603-4_12","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-96-6603-4_12","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7839703559875488,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1552314771","https://openalex.org/W2102372511","https://openalex.org/W2107860279","https://openalex.org/W2593414223","https://openalex.org/W2972359262","https://openalex.org/W3015338123","https://openalex.org/W3212744045"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-08T00:00:00"}
