{"id":"W2806367735","doi":"10.1609/aaai.v32i1.12140","title":"Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Conversation; Computer science; Task (project management); Component (thermodynamics); Speaker diarisation; Speech recognition; Speaker recognition; Artificial intelligence; Natural language processing; Linguistics","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":[0.004465922,0.001561349,0.001071443,0.001189843,0.001297715,0.001519157,0.002112555,0.002252067,0.002296386],"category_scores_gemma":[0.01081551,0.0004496454,0.001490178,0.0009220778,0.0005998142,0.002387305,0.002759077,0.004444192,0.003410136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009820674,"about_ca_system_score_gemma":0.001695547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008725256,"about_ca_topic_score_gemma":0.01185773,"domain_scores_codex":[0.9974597,0.001378216,0.0001054705,0.0006446891,0.0002793179,0.0001326745],"domain_scores_gemma":[0.9964536,0.00144911,0.0001761829,0.001086509,0.0006036535,0.0002309006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002177258,0.002487369,0.04027375,0.000788221,0.0008564574,0.0004297959,0.001147918,0.105009,0.03499335,0.01001533,0.06837146,0.7334502],"study_design_scores_gemma":[0.000119646,0.0002557785,0.0126249,0.000126208,0.0002609267,0.0003642917,0.0006070216,0.9351328,0.01241137,0.01932779,0.01864927,0.0001200755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2684461,0.00446527,0.6879225,0.004958814,0.0009084013,0.0007640644,0.01976608,0.00716484,0.005604038],"genre_scores_gemma":[0.5807338,0.001221627,0.3443705,0.0007829852,0.0006690043,0.001614759,0.06479315,0.0003966654,0.005417423],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008725256,"threshold_uncertainty_score":0.02361834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2417889338420326,"score_gpt":0.3237499481515659,"score_spread":0.08196101430953323,"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."}}