{"id":"W3167533889","doi":"10.48550/arxiv.2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":513,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; McGill University","funders":"","keywords":"Computer science; Scripting language; Python (programming language); Inference; Architecture; Speech processing; Speech recognition; Speech technology; Natural language processing; Artificial intelligence; Programming language","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":[0.0009344483,0.002090762,0.001035472,0.001182997,0.0005969231,0.001839342,0.00257331,0.001390126,0.0647307],"category_scores_gemma":[0.004827425,0.00114055,0.001072719,0.0006692912,0.0004813892,0.002235929,0.003017886,0.002067142,0.06926867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004591332,"about_ca_system_score_gemma":0.001289588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003336742,"about_ca_topic_score_gemma":0.006060784,"domain_scores_codex":[0.9992141,0.00015144,0.00008377009,0.0002117225,0.0002652036,0.00007382525],"domain_scores_gemma":[0.9987925,0.0005580696,0.0000613696,0.0002240085,0.0002697583,0.00009428856],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008782633,0.000112425,0.001165158,0.002438882,0.000235844,0.0005826215,0.0007605764,0.009395744,0.02851437,0.009969153,0.6665984,0.2793485],"study_design_scores_gemma":[0.0003873793,0.0001994188,0.003524977,0.0004133637,0.0001457205,0.001914993,0.0004215602,0.1808187,0.06135092,0.04327035,0.7071257,0.0004268502],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.003940797,0.0006761044,0.4137305,0.0002890175,0.0004506121,0.0003044497,0.03502375,0.5330475,0.01253735],"genre_scores_gemma":[0.08356533,0.001091829,0.5462098,0.001310982,0.0002940089,0.002313898,0.1625236,0.1578991,0.04479146],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.0647307,"threshold_uncertainty_score":0.2165458,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09161433237207015,"score_gpt":0.1896422480167848,"score_spread":0.09802791564471466,"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."}}