{"id":"https://openalex.org/W4372269499","doi":"https://doi.org/10.1109/icassp49357.2023.10096643","title":"Diverse and Vivid Sound Generation from Text Descriptions","display_name":"Diverse and Vivid Sound Generation from Text Descriptions","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372269499","doi":"https://doi.org/10.1109/icassp49357.2023.10096643"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096643","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5002348751","display_name":"Guangwei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwei Li","raw_affiliation_strings":["Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025827045","display_name":"Xuenan Xu","orcid":"https://orcid.org/0000-0001-8718-1278"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuenan Xu","raw_affiliation_strings":["Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033635690","display_name":"Lingfeng Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingfeng Dai","raw_affiliation_strings":["Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081865665","display_name":"Mengyue Wu","orcid":"https://orcid.org/0000-0002-5599-8707"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyue Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074843536","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0003-2436-5162"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-Lance Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.6959,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66576663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991999864578247,"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":0.9979000091552734,"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/spectrogram","display_name":"Spectrogram","score":0.886943519115448},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.8375962376594543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7271287441253662},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.6791926026344299},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5839298963546753},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4975183308124542},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.468387633562088},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.45926275849342346},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4145759344100952},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4051443934440613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3522268235683441},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18745329976081848},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07897034287452698}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.886943519115448},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8375962376594543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271287441253662},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.6791926026344299},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5839298963546753},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4975183308124542},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.468387633562088},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.45926275849342346},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4145759344100952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4051443934440613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3522268235683441},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18745329976081848},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07897034287452698},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096643","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1519855838","https://openalex.org/W1956340063","https://openalex.org/W2242818861","https://openalex.org/W2331128040","https://openalex.org/W2506483933","https://openalex.org/W2746068898","https://openalex.org/W2752796333","https://openalex.org/W2772474126","https://openalex.org/W2892140764","https://openalex.org/W2896457183","https://openalex.org/W2899724567","https://openalex.org/W2963073614","https://openalex.org/W2963799213","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W3015584015","https://openalex.org/W3015591594","https://openalex.org/W3033411150","https://openalex.org/W3037391061","https://openalex.org/W3127705815","https://openalex.org/W3166396011","https://openalex.org/W3180355996","https://openalex.org/W3207498282","https://openalex.org/W4226125322","https://openalex.org/W4281485151","https://openalex.org/W4300980117","https://openalex.org/W4301206121","https://openalex.org/W4367359628","https://openalex.org/W6690026940","https://openalex.org/W6702130928","https://openalex.org/W6725318829","https://openalex.org/W6729966448","https://openalex.org/W6743002019","https://openalex.org/W6754925833","https://openalex.org/W6755207826","https://openalex.org/W6765779288","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6780316881","https://openalex.org/W6790023719","https://openalex.org/W6791353385","https://openalex.org/W6802805937","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6839857308","https://openalex.org/W6845479124"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2135608140","https://openalex.org/W2347409177","https://openalex.org/W2895525995","https://openalex.org/W2319626700","https://openalex.org/W4319589573","https://openalex.org/W1997070615"],"abstract_inverted_index":{"Previous":[0],"audio":[1,28,68],"generation":[2,29],"mainly":[3],"focuses":[4],"on":[5,66],"specified":[6],"sound":[7],"classes":[8],"such":[9],"as":[10,35],"speech":[11],"or":[12],"music,":[13],"whose":[14],"form":[15],"and":[16,64,123,148],"content":[17],"are":[18],"greatly":[19],"restricted.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"go":[25],"beyond":[26],"specific":[27],"by":[30,50,113],"using":[31],"natural":[32],"language":[33],"description":[34,47],"a":[36,45,61,79,87,97,105,114],"clue":[37],"to":[38,69,77,96,99,103,107,128],"generate":[39],"broad":[40],"sounds.":[41],"Unlike":[42],"visual":[43],"information,":[44],"text":[46,89],"is":[48,75,94,138],"concise":[49],"its":[51,91],"nature":[52],"but":[53],"has":[54,120],"rich":[55],"hidden":[56],"meanings":[57],"beneath,":[58],"which":[59],"poses":[60],"higher":[62],"possibility":[63],"complexity":[65],"the":[67,129],"be":[70,108],"generated.":[71],"A":[72],"Variation-Quantized":[73],"GAN":[74],"used":[76],"train":[78],"codebook":[80,101],"learning":[81],"discrete":[82],"representations":[83],"of":[84,140],"spectrograms.":[85],"For":[86],"given":[88,130],"description,":[90],"pre-trained":[92],"embedding":[93],"fed":[95],"Transformer":[98],"sample":[100],"indices":[102],"decode":[104],"spectrogram":[106],"further":[109],"transformed":[110],"into":[111],"waveform":[112,119],"melgan":[115],"vocoder.":[116],"The":[117],"generated":[118],"high":[121],"quality":[122],"fidelity":[124],"while":[125],"excellently":[126],"corresponding":[127],"text.":[131],"Experiments":[132],"show":[133],"that":[134],"our":[135],"proposed":[136],"method":[137],"capable":[139],"generating":[141],"natural,":[142],"vivid":[143],"audios,":[144],"achieving":[145],"superb":[146],"quantitative":[147],"qualitative":[149],"results.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}