{"id":"https://openalex.org/W4415433415","doi":"https://doi.org/10.21437/interspeech.2025-1137","title":"EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer","display_name":"EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433415","doi":"https://doi.org/10.21437/interspeech.2025-1137"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-1137","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","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/A5048171604","display_name":"Jiarui Hai","orcid":"https://orcid.org/0000-0001-9968-7372"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiarui Hai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006545495","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0002-9933-024X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692070","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-8472-6137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101744663","display_name":"Chenxing Li","orcid":"https://orcid.org/0009-0001-4226-7825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenxing Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101664824","display_name":"Helin Wang","orcid":"https://orcid.org/0000-0001-6088-0378"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helin Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038788686","display_name":"Mounya Elhilali","orcid":"https://orcid.org/0000-0003-2597-738X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mounya Elhilali","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100894532","display_name":"Dong Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5048171604"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.0306,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.9822684,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4233","last_page":"4237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9872999787330627,"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/transformer","display_name":"Transformer","score":0.3483999967575073},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.2395000010728836},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.22509999573230743},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.22290000319480896}],"concepts":[{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.48399999737739563},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3483999967575073},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2994999885559082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2563999891281128},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24899999797344208},{"id":"https://openalex.org/C49040817","wikidata":"https://www.wikidata.org/wiki/Q193091","display_name":"Optoelectronics","level":1,"score":0.2425999939441681},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.2395000010728836},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.22509999573230743},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.22290000319480896}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-1137","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-24T00:00:00"}
