{"id":"W4392903535","doi":"10.1109/icassp48485.2024.10446349","title":"SoundLoCD: An Efficient Conditional Discrete Contrastive Latent Diffusion Model for Text-to-Sound Generation","year":2024,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"","keywords":"Computer science; Fidelity; Connection (principal bundle); Artificial intelligence; Diffusion; Component (thermodynamics); Speech recognition; Theoretical computer science; Algorithm; Mathematics; Physics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009983211,0.0006619305,0.0006295927,0.0004700256,0.0002821139,0.0008775248,0.001787224,0.001016871,0.005008007],"category_scores_gemma":[0.003477965,0.0004303312,0.0007660099,0.0004369071,0.0004989526,0.001219456,0.001456738,0.001854531,0.002029381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007025242,"about_ca_system_score_gemma":0.0008289717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003115641,"about_ca_topic_score_gemma":0.005885403,"domain_scores_codex":[0.9996198,0.0001243502,0.00001847443,0.0001018816,0.0001082462,0.00002723587],"domain_scores_gemma":[0.9990628,0.0006288628,0.00005200105,0.00008754119,0.0001090466,0.0000596307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004227991,0.0002072137,0.00126787,0.0002757602,0.0001035797,0.0002163829,0.0002045746,0.5135562,0.02710681,0.03285426,0.01326348,0.4105211],"study_design_scores_gemma":[0.00001846601,0.00001715334,0.00005726206,0.000003445399,0.000005334909,0.00002123294,0.000004021912,0.9928603,0.001912072,0.003755818,0.001337043,0.000007859485],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003847571,0.000143688,0.9928592,0.0001378041,0.00005372648,0.00005109416,0.000216333,0.001921197,0.0007693475],"genre_scores_gemma":[0.2849268,0.0003772109,0.7018813,0.0003378731,0.0001107209,0.0003968565,0.001684471,0.0008988347,0.009385857],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005008007,"threshold_uncertainty_score":0.01675349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04054293453064117,"score_gpt":0.2964657277876325,"score_spread":0.2559227932569913,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}