{"id":"https://openalex.org/W4402112475","doi":"https://doi.org/10.21437/interspeech.2024-1056","title":"Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model","display_name":"Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112475","doi":"https://doi.org/10.21437/interspeech.2024-1056"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1056","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-1056","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":"conference-paper","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/A5033565985","display_name":"Jinlong Xue","orcid":"https://orcid.org/0009-0000-0442-0932"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinlong Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008597430","display_name":"Yayue Deng","orcid":"https://orcid.org/0009-0003-7642-4942"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yayue Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102684506","display_name":"Yicheng Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yicheng Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033063238","display_name":"Yingming Gao","orcid":"https://orcid.org/0000-0001-5881-3723"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingming Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343662","display_name":"Ya Li","orcid":"https://orcid.org/0000-0002-6284-5039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"682","last_page":"686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9771999716758728,"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":0.9771999716758728,"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":0.8181147575378418},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6385634541511536},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.6303296685218811},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6117646098136902},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5949305295944214},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5187563896179199},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4905223250389099},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4287441670894623},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3281552791595459},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.23634973168373108},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.22318404912948608},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.10125142335891724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8181147575378418},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6385634541511536},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.6303296685218811},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6117646098136902},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5949305295944214},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5187563896179199},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4905223250389099},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4287441670894623},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3281552791595459},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.23634973168373108},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.22318404912948608},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.10125142335891724},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1056","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-1056","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":[{"score":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4252424250","https://openalex.org/W2370747337","https://openalex.org/W1890500690","https://openalex.org/W2157819213","https://openalex.org/W2374470469","https://openalex.org/W2899318368","https://openalex.org/W2363660481","https://openalex.org/W2352448339","https://openalex.org/W2159899134","https://openalex.org/W2787189739"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}