{"id":"W3176272988","doi":"10.23641/asha.14167058.v1","title":"Forced alignment of child speech (Mahr et al., 2021)","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Phone; Two-alternative forced choice; Sample (material); Segmentation; Natural language processing; Artificial intelligence; Linguistics; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.003729035,0.0009744331,0.0004468799,0.001249418,0.000689717,0.001426636,0.0009353716,0.0007510572,0.015887],"category_scores_gemma":[0.01611652,0.0005212392,0.0007620789,0.001227088,0.0005663934,0.001158246,0.001166471,0.0007950974,0.00836789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007932195,"about_ca_system_score_gemma":0.001744226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01243517,"about_ca_topic_score_gemma":0.03051139,"domain_scores_codex":[0.9971046,0.0007735791,0.0002664369,0.0009362852,0.0008000906,0.0001189764],"domain_scores_gemma":[0.9928508,0.002235147,0.0007754128,0.00138741,0.002605435,0.0001459287],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001105204,0.00008092791,0.02610919,0.001290099,0.0002251141,0.0004629629,0.002797381,0.002632388,0.1022563,0.003464562,0.02616033,0.8334157],"study_design_scores_gemma":[0.0002243179,0.00135033,0.5166813,0.0007598763,0.0005195703,0.007318592,0.003177272,0.03989564,0.1892936,0.005593709,0.2346452,0.0005405943],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.3293697,0.004863083,0.5789277,0.0009588152,0.00123706,0.002134249,0.02836244,0.01357317,0.04057376],"genre_scores_gemma":[0.3504023,0.001331615,0.6083776,0.000555956,0.0001382101,0.0018063,0.01644353,0.002804284,0.01814013],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.015887,"threshold_uncertainty_score":0.05314726,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03463776890904033,"score_gpt":0.2646876765530524,"score_spread":0.230049907644012,"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."}}