{"id":"W2405665360","doi":"10.21437/interspeech.2011-538","title":"On the use of linguistic features in an automatic system for speech analytics of telephone conversations","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Vocabulary; Natural language processing; Conversation; Sentence; Artificial intelligence; Boosting (machine learning); Set (abstract data type); Speech analytics; Speech recognition; Test set; Analytics; Training set; Speech processing; Voice activity detection; Data mining; 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":[0.00188738,0.0008655953,0.001026126,0.001599499,0.0007414137,0.001365464,0.0008952193,0.001017848,0.002199732],"category_scores_gemma":[0.00422835,0.0004017425,0.0006129637,0.001113258,0.0003715379,0.001587822,0.0007073865,0.0008718802,0.002405399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004758699,"about_ca_system_score_gemma":0.0005950125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003769301,"about_ca_topic_score_gemma":0.002728786,"domain_scores_codex":[0.9986221,0.0005332232,0.000089293,0.0004369837,0.0002180548,0.0001003861],"domain_scores_gemma":[0.9970154,0.002054873,0.000125077,0.0001750497,0.0005407178,0.00008905723],"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":[0.001170008,0.0006002625,0.004401715,0.0003229903,0.0001255097,0.0002697904,0.000377029,0.008553532,0.1537364,0.0006676861,0.003038795,0.8267362],"study_design_scores_gemma":[0.000168423,0.001542554,0.02141009,0.0001109835,0.0002530187,0.0009331861,0.0005003975,0.8064429,0.1593479,0.001998815,0.007152902,0.0001388822],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2833531,0.0009571031,0.6879475,0.0003238457,0.0001338357,0.0008016428,0.00131282,0.02237248,0.002797773],"genre_scores_gemma":[0.4264461,0.0003586575,0.566258,0.0001477302,0.00008284132,0.0006806334,0.003290042,0.0003255848,0.002410363],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003769301,"threshold_uncertainty_score":0.009981573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09143124079507628,"score_gpt":0.264016232605755,"score_spread":0.1725849918106787,"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."}}