{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003705845,0.0004735086,0.0005469205,0.0004003094,0.0001822325,0.0006191783,0.002723122,0.000473406,0.0007557536],"category_scores_gemma":[0.0001159834,0.0005692933,0.0005284693,0.0009357447,0.000102198,0.0005678798,0.003066885,0.0007389507,0.0005488498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002551013,"about_ca_system_score_gemma":0.0004249424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001535114,"about_ca_topic_score_gemma":0.0000798135,"domain_scores_codex":[0.9968985,0.0002845673,0.0003023122,0.001753351,0.0002223101,0.0005389405],"domain_scores_gemma":[0.9969086,0.0001548871,0.0002499586,0.002028847,0.0003297044,0.0003279787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001564989,0.002271976,0.004624807,0.0007855138,0.001753132,0.06155245,0.001922656,0.02137806,0.003859554,0.4709179,0.02551983,0.4052576],"study_design_scores_gemma":[0.00250103,0.0001771393,0.003425209,0.0007043389,0.0004205251,0.0005242071,0.0006165836,0.8069736,0.03166083,0.1120065,0.03627672,0.004713353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4423765,0.0001382216,0.5226116,0.0005802608,0.001614218,0.0004429121,0.00002850206,0.0007183857,0.03148945],"genre_scores_gemma":[0.8825709,0.0006066802,0.0947567,0.001445619,0.0003708986,0.000003293912,0.00007122805,0.00005493285,0.0201197],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7855955,"threshold_uncertainty_score":0.9996759,"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."}}