{"id":"https://openalex.org/W4415433492","doi":"https://doi.org/10.21437/interspeech.2025-908","title":"GTA: Towards Generative Text-To-Audio Retrieval via Multi-Scale Tokenizer","display_name":"GTA: Towards Generative Text-To-Audio Retrieval via Multi-Scale Tokenizer","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433492","doi":"https://doi.org/10.21437/interspeech.2025-908"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-908","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-908","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/A5113747251","display_name":"Minghui Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Minghui Fang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102904447","display_name":"Shengpeng Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengpeng Ji","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101230918","display_name":"Jialong Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jialong Zuo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009897266","display_name":"Xize Cheng","orcid":"https://orcid.org/0000-0001-9708-3225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xize Cheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081447891","display_name":"Wenrui Liu","orcid":"https://orcid.org/0000-0002-9501-7053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenrui Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040461965","display_name":"Xiaoda Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoda Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100586774","display_name":"Ruofan Hu","orcid":"https://orcid.org/0009-0005-1723-6778"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruofan Hu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100552790","display_name":"Jieming Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jieming Zhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5113747251"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40203642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2650","last_page":"2654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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":0.9973000288009644,"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":0.9919999837875366,"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":0.9894999861717224,"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/generative-grammar","display_name":"Generative grammar","score":0.5340999960899353},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3294000029563904},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2888999879360199},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.288100004196167},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2524000108242035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6399000287055969},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5340999960899353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5174999833106995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3817000091075897},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3294000029563904},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.23499999940395355},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.22660000622272491}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-908","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-908","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}
