{"id":"W2907177214","doi":"10.4000/books.aaccademia.4661","title":"A Markovian Kernel-based Approach for itaLIan Speech acT labEliNg","year":2018,"lang":"en","type":"book-chapter","venue":"Accademia University Press eBooks","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada; Università degli Studi di Napoli Federico II","keywords":"Utterance; Computer science; Task (project management); Artificial intelligence; Kernel (algebra); Context (archaeology); Support vector machine; Hidden Markov model; Natural language processing; Speech recognition; Markov process; Feature (linguistics); Linguistics; Mathematics; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001139223,0.0005910773,0.0004979591,0.0007218767,0.0004958312,0.001271572,0.001232234,0.0008133531,0.004511463],"category_scores_gemma":[0.003065885,0.0003705198,0.0006919681,0.0006921386,0.0005080838,0.00158534,0.001137996,0.001530645,0.002944088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009322051,"about_ca_system_score_gemma":0.0009256419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003865032,"about_ca_topic_score_gemma":0.004582115,"domain_scores_codex":[0.998814,0.0004927694,0.00005358536,0.0003006341,0.0002451054,0.00009384473],"domain_scores_gemma":[0.999094,0.0004036082,0.00006348907,0.000180079,0.0002171611,0.00004177221],"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":[0.0003487489,0.0002126115,0.001178878,0.0002671539,0.00008887802,0.0001811262,0.0007558011,0.1015344,0.01862332,0.08437487,0.01641097,0.7760231],"study_design_scores_gemma":[0.000005036708,0.00003678317,0.0005114278,0.00001384354,0.00001201171,0.00009639687,0.00004066268,0.9682902,0.00446935,0.01893938,0.007564092,0.00002075128],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005912553,0.0002811824,0.988151,0.0001713965,0.00006169952,0.00004170692,0.000113082,0.002053527,0.003213945],"genre_scores_gemma":[0.359226,0.0005011131,0.621698,0.0001530282,0.000142654,0.0001717722,0.001151666,0.0006782277,0.01627753],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004511463,"threshold_uncertainty_score":0.01509237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03538561528486382,"score_gpt":0.2231755777540221,"score_spread":0.1877899624691582,"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."}}