{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003067139,0.0001952288,0.0002356479,0.0005168107,0.000723228,0.0001125079,0.000543443,0.00003194153,0.00008778601],"category_scores_gemma":[0.00000835053,0.0001901009,0.0002329248,0.001079023,0.00002978378,0.0001063199,0.00001538076,0.0004700953,0.00000489369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005674768,"about_ca_system_score_gemma":0.00001725149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001765177,"about_ca_topic_score_gemma":0.0007724437,"domain_scores_codex":[0.9984804,0.000138659,0.0002893642,0.0005873704,0.0002622097,0.0002420122],"domain_scores_gemma":[0.9989905,0.0002556336,0.0001082203,0.0004947236,0.00004883846,0.0001020528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008641827,0.00007447571,0.0002167572,0.000009073953,0.0001032373,0.000001501775,0.0002656354,0.5889529,0.0005614514,0.0001477121,0.000002290775,0.4096563],"study_design_scores_gemma":[0.00009077267,0.0001824143,0.001447295,0.000004204345,0.0002320476,0.00002236489,0.00003314836,0.9934439,0.003723141,0.0004268397,0.000182827,0.0002110394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008827525,0.00005447072,0.9887908,0.001603466,0.0001671086,0.000285136,0.00008230975,0.00017331,0.00001590021],"genre_scores_gemma":[0.991451,0.00001636777,0.007510019,0.0005114983,0.00002074307,0.0003712995,0.00001361793,0.0000151993,0.00009029994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9826235,"threshold_uncertainty_score":0.775209,"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."}}