{"id":"W2081811590","doi":"10.1109/tasl.2013.2271591","title":"Large Vocabulary Speech Recognition on Parallel Architectures","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Parallel computing; Graphics processing unit; Viterbi algorithm; CUDA; Speedup; Scalability; Massively parallel; Beam search; Heuristic; Multi-core processor; Computation; Search algorithm; Decoding methods; Algorithm; Artificial intelligence","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":[0.0002666084,0.0002844651,0.0002409316,0.0003561468,0.0004282504,0.0004134472,0.0002946465,0.0001384012,0.0006761507],"category_scores_gemma":[0.00002485812,0.0002462663,0.0001111366,0.000383901,0.00005553072,0.000441336,0.000004740508,0.0004164916,0.0005868481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003827178,"about_ca_system_score_gemma":0.0000484034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005806523,"about_ca_topic_score_gemma":0.0000595107,"domain_scores_codex":[0.9982214,0.0001162908,0.0002706157,0.0005679799,0.0003674038,0.0004563203],"domain_scores_gemma":[0.9991206,0.0001456847,0.00009874253,0.0003344518,0.00009285683,0.0002076622],"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":[0.00002202625,0.0001979409,0.000003982644,0.00004297231,0.0000206295,0.00006085871,0.00104637,0.00002155086,0.002600391,0.000006238959,0.0001859826,0.9957911],"study_design_scores_gemma":[0.003747079,0.0008565388,0.001201653,0.001073511,0.0001264024,0.001394811,0.003086416,0.08781938,0.889805,0.007081155,0.001542287,0.002265746],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1678213,0.0003258793,0.8256763,0.001262789,0.0002165568,0.0003822901,0.00002022746,0.0004796979,0.00381494],"genre_scores_gemma":[0.8885668,0.00006009435,0.1074302,0.002923265,0.00009885505,0.00009429812,0.000006187988,0.00003053065,0.0007898178],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9935253,"threshold_uncertainty_score":0.999999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01537962600978919,"score_gpt":0.2441980252390852,"score_spread":0.228818399229296,"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."}}