{"id":"https://openalex.org/W4296068816","doi":"https://doi.org/10.21437/interspeech.2022-621","title":"Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech","display_name":"Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068816","doi":"https://doi.org/10.21437/interspeech.2022-621"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-621","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-621","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5102854878","display_name":"Guangyan Zhang","orcid":"https://orcid.org/0000-0002-3480-5902"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guangyan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028035527","display_name":"Kaitao Song","orcid":"https://orcid.org/0000-0002-4046-8594"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaitao Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385893","display_name":"Xu Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006527442","display_name":"Daxin Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daxin Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010122282","display_name":"Yuzi Yan","orcid":"https://orcid.org/0000-0002-3117-3305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuzi Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360935","display_name":"Yanqing Liu","orcid":"https://orcid.org/0000-0003-0412-8805"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanqing Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107031356","display_name":"Gang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636970","display_name":"Wei Zhou","orcid":"https://orcid.org/0009-0006-3754-8872"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020025718","display_name":"Tao Qin","orcid":"https://orcid.org/0000-0002-9095-0776"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Qin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","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":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2839,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90172277,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"456","last_page":"460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.995199978351593,"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":0.995199978351593,"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":0.9656999707221985,"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":0.9621999859809875,"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":0.7502803802490234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6604675650596619},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4772722125053406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4032166302204132}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7502803802490234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6604675650596619},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4772722125053406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4032166302204132}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-621","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-621","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W1551406738","https://openalex.org/W2610387714","https://openalex.org/W2369308426","https://openalex.org/W1569841287","https://openalex.org/W1512718085","https://openalex.org/W2359001871","https://openalex.org/W2167662847","https://openalex.org/W1560657467"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
