{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006399314,0.0007979615,0.0007963747,0.0007602253,0.0005212871,0.001122182,0.001300068,0.0006314418,0.007809395],"category_scores_gemma":[0.002361031,0.0004227688,0.0005613383,0.001253249,0.0003948339,0.001656221,0.0008019193,0.0008918101,0.003569169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008975728,"about_ca_system_score_gemma":0.001262385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01180766,"about_ca_topic_score_gemma":0.01250297,"domain_scores_codex":[0.9993012,0.0001282171,0.00005394167,0.0001864865,0.0002359529,0.00009412019],"domain_scores_gemma":[0.9989189,0.0002884194,0.00004933334,0.0002647046,0.0004299327,0.00004888103],"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":[0.001329365,0.0002592218,0.00153684,0.0003236734,0.0002261451,0.0005454985,0.0002358053,0.2428951,0.0818952,0.02170708,0.02265203,0.6263941],"study_design_scores_gemma":[0.00009765447,0.0001240818,0.0006283383,0.0000161718,0.00002943657,0.0001183565,0.00006915961,0.952427,0.02446483,0.01317702,0.008825055,0.00002299193],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1079035,0.001079241,0.8537456,0.000659036,0.0003602422,0.000228845,0.0006627452,0.01808479,0.01727604],"genre_scores_gemma":[0.5441841,0.000541453,0.4374129,0.0002503349,0.0001349567,0.0003234076,0.001844771,0.0004693981,0.01483856],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01180766,"threshold_uncertainty_score":0.02612507,"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."}}