{"id":"https://openalex.org/W4385895691","doi":"https://doi.org/10.21437/interspeech.2023-2574","title":"SALTTS: Leveraging Self-Supervised Speech Representations for improved Text-to-Speech Synthesis","display_name":"SALTTS: Leveraging Self-Supervised Speech Representations for improved Text-to-Speech Synthesis","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385895691","doi":"https://doi.org/10.21437/interspeech.2023-2574"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2574","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5092653231","display_name":"R Sivaguru","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ramanan Sivaguru","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075877984","display_name":"Vasista Sai Lodagala","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasista Sai Lodagala","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000684485","display_name":"S Umesh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S Umesh","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092653231"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6952,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75799095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3033","last_page":"3037"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9961000084877014,"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":0.9961000084877014,"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":0.979200005531311,"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/T12031","display_name":"Speech and dialogue systems","score":0.958899974822998,"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/computer-science","display_name":"Computer science","score":0.7995021343231201},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6742270588874817},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6603631973266602},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.574398934841156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4708889126777649},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4549134075641632},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4359420835971832},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4302268326282501},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4131980538368225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995021343231201},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6742270588874817},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6603631973266602},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.574398934841156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4708889126777649},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4549134075641632},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4359420835971832},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4302268326282501},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4131980538368225}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-2574","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/W642007152","https://openalex.org/W2537969829","https://openalex.org/W2153664791","https://openalex.org/W2389353568","https://openalex.org/W2971563979","https://openalex.org/W2184127972","https://openalex.org/W2147998355","https://openalex.org/W2889413431","https://openalex.org/W25845660","https://openalex.org/W2567084565"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}