{"id":"https://openalex.org/W4402111981","doi":"https://doi.org/10.21437/interspeech.2024-771","title":"Pre-training Neural Transducer-based Streaming Voice Conversion for Faster Convergence and Alignment-free Training","display_name":"Pre-training Neural Transducer-based Streaming Voice Conversion for Faster Convergence and Alignment-free Training","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111981","doi":"https://doi.org/10.21437/interspeech.2024-771"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-771","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","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/A5076754533","display_name":"Hiroki Kanagawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hiroki Kanagawa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuke Ijima","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076754533"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12180644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2755","last_page":"2759"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9593999981880188,"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":0.9593999981880188,"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/training","display_name":"Training (meteorology)","score":0.8405261039733887},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7383016347885132},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6598911881446838},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.5255081653594971},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.501218318939209},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44811612367630005},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41591137647628784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33741116523742676},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.221576988697052}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.8405261039733887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383016347885132},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6598911881446838},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.5255081653594971},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.501218318939209},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44811612367630005},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41591137647628784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33741116523742676},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.221576988697052},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-771","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","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/W2012283803","https://openalex.org/W4384820447","https://openalex.org/W2072454424","https://openalex.org/W2117438306","https://openalex.org/W2185942010","https://openalex.org/W2260725127","https://openalex.org/W230091440","https://openalex.org/W2004297762","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
