{"id":"W3167565399","doi":"10.1109/tpami.2022.3194311","title":"NAAQA: A Neural Architecture for Acoustic Question Answering","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; CHIST-ERA; Nvidia","keywords":"Notation; Benchmark (surveying); Task (project management); Set (abstract data type); Question answering; Computer science; Artificial neural network; Artificial intelligence; Variable (mathematics); Architecture; Speech recognition; Mathematics; Arithmetic; Programming language; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009547999,0.001254438,0.0005243971,0.000678602,0.0005560992,0.001016058,0.003050144,0.00189684,0.006478496],"category_scores_gemma":[0.002903779,0.000563703,0.001008506,0.0006364954,0.0005266864,0.002143196,0.001913568,0.002125006,0.002462729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001059914,"about_ca_system_score_gemma":0.001184111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01319159,"about_ca_topic_score_gemma":0.01897847,"domain_scores_codex":[0.9995276,0.0001100508,0.00002523165,0.0001906032,0.00008836087,0.00005811068],"domain_scores_gemma":[0.9994224,0.0002017497,0.00002949219,0.0001213064,0.0001741809,0.0000508016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008926878,0.0006300872,0.006187096,0.0009121868,0.0005325348,0.0002530492,0.0003323944,0.2554763,0.03868318,0.009873689,0.05039731,0.6358294],"study_design_scores_gemma":[0.00006086162,0.0002129981,0.001111523,0.00003436458,0.00005164254,0.00006905357,0.00005721963,0.974474,0.007692312,0.007681569,0.00852797,0.00002646514],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1940952,0.00436921,0.7336357,0.001763407,0.0009961128,0.0007867111,0.009829716,0.03726515,0.01725877],"genre_scores_gemma":[0.619891,0.001008864,0.3333537,0.001175326,0.0001661802,0.001070072,0.02243086,0.0006562233,0.02024768],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01319159,"threshold_uncertainty_score":0.02622962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01582498051755524,"score_gpt":0.2834004161358437,"score_spread":0.2675754356182884,"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."}}