{"id":"W2963897404","doi":"10.63317/3bau89hm3k8v","title":"Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Conversation; Computer science; Task (project management); Component (thermodynamics); Speaker recognition; Speaker diarisation; Speech recognition; Artificial intelligence; Data modeling; Natural language processing; Linguistics; Database","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000289568,0.00008066046,0.00008133334,0.00005116825,0.00008450507,0.0001399414,0.0003241459,0.00003088412,0.0001009012],"category_scores_gemma":[0.00002556547,0.00005212662,0.00001730318,0.000144933,0.00006553932,0.0006358657,0.0001667091,0.00006885504,0.00005904118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001187472,"about_ca_system_score_gemma":0.00002342166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002788387,"about_ca_topic_score_gemma":0.0003050092,"domain_scores_codex":[0.9992566,0.00005817524,0.000146281,0.0002491488,0.0001381598,0.000151619],"domain_scores_gemma":[0.9995202,0.00004153943,0.0000225716,0.0003154895,0.00004863813,0.00005149437],"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":[0.00006137857,0.0003320426,0.000729941,0.00002778,0.00006664479,0.00006006975,0.01506551,0.004695456,0.0008748434,0.04333567,0.02216606,0.9125846],"study_design_scores_gemma":[0.0002523342,0.00001129924,0.0001427752,0.000003640699,0.000002158632,0.00001229225,0.0001443948,0.9963865,0.0004554965,0.00191541,0.0005907267,0.00008293874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02613378,0.0000312171,0.9668465,0.00371051,0.0001807236,0.0001363385,0.00002432785,0.00006235855,0.002874272],"genre_scores_gemma":[0.944363,0.0000125962,0.05337551,0.002109408,0.00004074695,0.000006505427,0.00001271823,0.000003680961,0.00007584837],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9916911,"threshold_uncertainty_score":0.2125662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.139276818867959,"score_gpt":0.2942934836241976,"score_spread":0.1550166647562387,"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."}}