{"id":"https://openalex.org/W4392903535","doi":"https://doi.org/10.1109/icassp48485.2024.10446349","title":"SoundLoCD: An Efficient Conditional Discrete Contrastive Latent Diffusion Model for Text-to-Sound Generation","display_name":"SoundLoCD: An Efficient Conditional Discrete Contrastive Latent Diffusion Model for Text-to-Sound Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903535","doi":"https://doi.org/10.1109/icassp48485.2024.10446349"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446349","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5036522347","display_name":"Xinlei Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Xinlei Niu","raw_affiliation_strings":["Australian National University,Canberra,Australia","Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University,Canberra,Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630815","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-8516-0913"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Australian National University,Canberra,Australia","Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University,Canberra,Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063357214","display_name":"Christian Walder","orcid":"https://orcid.org/0000-0002-2411-3523"},"institutions":[{"id":"https://openalex.org/I4210148186","display_name":"Google (Canada)","ror":"https://ror.org/04d06q394","country_code":"CA","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969","https://openalex.org/I4210148186"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Christian Walder","raw_affiliation_strings":["Google DeepMind,Montreal,Canada","Google DeepMind, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Google DeepMind,Montreal,Canada","institution_ids":["https://openalex.org/I4210148186"]},{"raw_affiliation_string":"Google DeepMind, Montreal, Canada","institution_ids":["https://openalex.org/I4210148186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065674172","display_name":"Charles Mart\u00edn","orcid":"https://orcid.org/0000-0001-5683-7529"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Charles Patrick Martin","raw_affiliation_strings":["Australian National University,Canberra,Australia","Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University,Canberra,Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036522347"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":0.724,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64671386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.986299991607666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6880436539649963},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5497885942459106},{"id":"https://openalex.org/keywords/connection","display_name":"Connection (principal bundle)","score":0.4617602527141571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43995529413223267},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4348932206630707},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4326859712600708},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34648582339286804},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33632296323776245},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32505926489830017},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16083014011383057},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.073017418384552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6880436539649963},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5497885942459106},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.4617602527141571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43995529413223267},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4348932206630707},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4326859712600708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34648582339286804},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33632296323776245},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32505926489830017},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16083014011383057},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.073017418384552},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446349","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/733806737","is_oa":false,"landing_page_url":"https://hdl.handle.net/1885/733806737","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2747329762","https://openalex.org/W2752796333","https://openalex.org/W2963799213","https://openalex.org/W2970006822","https://openalex.org/W3036167779","https://openalex.org/W3121370741","https://openalex.org/W3162926177","https://openalex.org/W3163243746","https://openalex.org/W3166396011","https://openalex.org/W3215615641","https://openalex.org/W4283074862","https://openalex.org/W4288089799","https://openalex.org/W4300980117","https://openalex.org/W4312388283","https://openalex.org/W4318752004","https://openalex.org/W4367359628","https://openalex.org/W4372260310","https://openalex.org/W4378942405","https://openalex.org/W4381551698","https://openalex.org/W4387969125","https://openalex.org/W6767111847","https://openalex.org/W6769627184","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6796581206","https://openalex.org/W6838582276","https://openalex.org/W6845479124","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6852971826","https://openalex.org/W6854083324"],"related_works":["https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W587735977","https://openalex.org/W3125091513","https://openalex.org/W1978142926","https://openalex.org/W4318832338","https://openalex.org/W3157395178","https://openalex.org/W4248383205","https://openalex.org/W4234745530","https://openalex.org/W2146383839"],"abstract_inverted_index":{"We":[0],"present":[1],"SoundLoCD,":[2],"a":[3,10,37],"novel":[4],"text-to-sound":[5],"generation":[6,22],"framework,":[7],"which":[8],"incorporates":[9],"LoRA-based":[11],"conditional":[12],"discrete":[13],"contrastive":[14,38],"latent":[15],"diffusion":[16],"model.":[17],"Unlike":[18],"recent":[19],"large-scale":[20],"sound":[21],"models,":[23],"our":[24],"model":[25],"can":[26],"be":[27],"efficiently":[28],"trained":[29],"under":[30],"limited":[31],"computational":[32,69],"resources.":[33,70],"The":[34],"integration":[35],"of":[36,79],"learning":[39],"strategy":[40],"further":[41,75],"enhances":[42],"the":[43,49,64,77],"connection":[44],"between":[45],"text":[46],"conditions":[47],"and":[48,55],"generated":[50],"outputs,":[51],"resulting":[52],"in":[53],"coherent":[54],"high-fidelity":[56],"performance.":[57],"Our":[58],"experiments":[59],"demonstrate":[60],"that":[61],"SoundLoCD":[62],"outperforms":[63],"baseline":[65],"with":[66],"greatly":[67],"reduced":[68],"A":[71],"comprehensive":[72],"ablation":[73],"study":[74],"validates":[76],"contribution":[78],"each":[80],"component":[81],"within":[82],"SoundLoCD<sup":[83],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[84],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[85]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-16T09:10:04.655348","created_date":"2025-10-10T00:00:00"}
